[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-NeoLabHQ-fix-tests-zh-CN":3,"guides-for-NeoLabHQ-fix-tests":1161,"similar-k173mzz0jfwzdeehjvhm34mdpn86nmrs-zh-CN":1162},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":261,"isFallback":244,"parentExtension":267,"providers":322,"relations":326,"repo":327,"tags":1159,"workflow":1160},1778694480889.9622,"k173mzz0jfwzdeehjvhm34mdpn86nmrs",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Systematically fix all failing tests after business logic changes or refactoring",{"claudeCode":12},"NeoLabHQ/context-engineering-kit","Fix Tests","https://github.com/NeoLabHQ/context-engineering-kit",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":242,"workflow":259},1778695812100.3347,"kn7d3zzyqjm7b841822yhn2mx986mb58","en",{"checks":20,"evaluatedAt":195,"extensionSummary":196,"features":197,"nonGoals":203,"practices":207,"prerequisites":211,"promptVersionExtension":214,"promptVersionScoring":215,"purpose":216,"rationale":217,"score":218,"summary":219,"tags":220,"targetMarket":226,"tier":227,"useCases":228,"workflow":232},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,99,103,107,110,114,117,121,124,127,130,133,136,139,143,147,150,153,157,160,163,166,169,173,176,179,182,185,188,192],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of fixing failing tests after code changes.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill systematically orchestrates specialized agents to fix failing tests, offering value beyond simple manual debugging or generic LLM instructions.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill's workflow covers the complete lifecycle from test discovery to verification and iteration, making it suitable for real-world use.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses solely on the task of fixing failing tests, without venturing into unrelated domains like refactoring or new feature development.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's purpose of systematically fixing failing tests.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This skill does not expose explicit tools; its functionality is orchestrated internally.",{"category":45,"check":46,"severity":24,"summary":47},"Documentation","Configuration & parameter reference","The skill clearly documents user arguments for focusing on specific tests or modules, with a default behavior described.",{"category":33,"check":49,"severity":42,"summary":50},"Tool naming","This skill does not expose user-facing tools.",{"category":33,"check":52,"severity":24,"summary":53},"Minimal I/O surface","User arguments are clearly defined and optional, with a default behavior for broad application.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The project is licensed under GPL-3.0, a widely usable open-source license.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The latest commit was 7 days ago, indicating active maintenance.",{"category":59,"check":63,"severity":24,"summary":64},"Dependency Management","No third-party dependencies are explicitly mentioned or seem to be required for the skill's operation based on the SKILL.md.",{"category":66,"check":67,"severity":24,"summary":68},"Security","Secret Management","The skill does not appear to handle or expose secrets.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill orchestrates agents and processes existing test files; there's no indication of loading untrusted external data as instructions.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill operates on local files and internal agent orchestration, with no apparent runtime downloads or execution of external content.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill orchestrates other agents and operates on test files within the project context, with no indication of writing outside the designated scope.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","No detached process spawns or deny-retry loops were detected in the skill's logic.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill's purpose is to fix tests locally and does not involve submitting confidential data to third parties.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled content is free of hidden-steering tricks, and descriptions are clean.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The skill's logic appears to be plain and readable, without obfuscation or runtime code fetching.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The skill identifies test infrastructure by reading project configuration files, which is a standard approach and not overly specific.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","With 6 issues opened and 8 closed in the last 90 days, the closure rate is over 50%, indicating good maintainer engagement.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The README frontmatter declares the skill with a clear name and description, and the plugin is available on agentskills.io.",{"category":104,"check":105,"severity":24,"summary":106},"Execution","Validation","User arguments are clearly defined and optional, indicating a structured approach to input handling.",{"category":66,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","The skill focuses on fixing tests, not destructive operations, and has safeguards like preserving test intent.",{"category":111,"check":112,"severity":24,"summary":113},"Code Execution","Error Handling","The workflow includes steps for verifying fixes and iterating if tests still fail, indicating a robust error handling approach.",{"category":111,"check":115,"severity":42,"summary":116},"Logging","This skill is an agent orchestration skill and does not involve direct user-facing destructive actions that require local audit logging.",{"category":118,"check":119,"severity":42,"summary":120},"Compliance","GDPR","The skill operates on code and test files, not personal data.",{"category":118,"check":122,"severity":24,"summary":123},"Target market","The skill is universally applicable to any codebase with tests and has no regional limitations.",{"category":92,"check":125,"severity":24,"summary":126},"Runtime stability","The skill's logic is self-contained and relies on standard project tooling (test runners), making it portable across different environments.",{"category":45,"check":128,"severity":24,"summary":129},"README","The README provides a comprehensive overview of the Context Engineering Kit, including installation and plugin details.",{"category":33,"check":131,"severity":42,"summary":132},"Tool surface size","This is a single-function skill, not a collection of tools.",{"category":40,"check":134,"severity":42,"summary":135},"Overlapping near-synonym tools","This skill does not expose multiple tools with overlapping functionality.",{"category":45,"check":137,"severity":24,"summary":138},"Phantom features","All advertised capabilities within the SKILL.md are implemented in the workflow steps.",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","Installation instructions for various platforms are clearly provided in the README, along with an example usage.",{"category":144,"check":145,"severity":24,"summary":146},"Errors","Actionable error messages","The workflow includes iteration based on test results, implying that failure states are handled and re-evaluated.",{"category":104,"check":148,"severity":24,"summary":149},"Pinned dependencies","The skill does not appear to rely on external dependencies that would require pinning.",{"category":33,"check":151,"severity":42,"summary":152},"Dry-run preview","The skill's primary function is to fix existing tests, not to perform state-changing operations that would benefit from a dry-run.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The workflow includes iteration and retries for failing tests, suggesting an idempotent approach to fixing.",{"category":118,"check":158,"severity":24,"summary":159},"Telemetry opt-in","There is no mention of telemetry collection in the skill's description or documentation.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The skill clearly states its purpose: to fix failing tests after code changes, and its context is defined by project structure and test output.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter is concise and effectively summarizes the skill's core capability and user arguments.",{"category":45,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is well-structured and under 500 lines, outlining the workflow steps clearly.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md outlines the main workflow and delegates deeper material implicitly to the agents it orchestrates.",{"category":170,"check":174,"severity":42,"summary":175},"Forked exploration","This skill does not involve deep exploration or code review that would necessitate forked context.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The skill provides a clear user argument example and a detailed agent instruction template, illustrating its usage.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The skill's workflow accounts for scenarios where tests might still fail after initial attempts and includes an iteration step.",{"category":111,"check":183,"severity":42,"summary":184},"Tool Fallback","This skill does not rely on external MCP servers or tools that would require fallback mechanisms.",{"category":92,"check":186,"severity":24,"summary":187},"Stack assumptions","The skill's assumptions are generic (e.g., presence of test runners, README, package.json), making it broadly portable.",{"category":189,"check":190,"severity":24,"summary":191},"Safety","Halt on unexpected state","The workflow includes steps for identifying failing tests and iterating, implying a halt on unexpected states until resolution.",{"category":92,"check":193,"severity":24,"summary":194},"Cross-skill coupling","The skill is self-contained and orchestrates agents based on the immediate task of fixing tests, without relying on other specific skills being loaded.",1778695811976,"This skill automates the process of fixing failing test cases that arise after code modifications or refactoring by orchestrating specialized agents. It identifies failing tests, analyzes their context, and guides agents to fix them while preserving test intent and business logic.",[198,199,200,201,202],"Automated test failure identification","Orchestrated agent-based test fixing","Preserves test intent and business logic","Iterative fixing process for remaining failures","Supports user-specified focus on specific tests or modules",[204,205,206],"Writing new business logic or features.","Refactoring code that is not directly related to test failures.","Adding new tests where none existed previously.",[208,209,210],"Test-Driven Development","Code Quality","Automation",[212,213],"A project with a test suite discoverable by standard commands (e.g., via package.json or README.md)","Agents capable of understanding and executing code changes (e.g., provided by the Claude Code environment)","3.0.0","4.4.0","To ensure code stability and maintainability by systematically resolving all failing tests after changes.","The skill is well-documented, follows best practices, and demonstrates a clear, actionable workflow for fixing tests. The comprehensive documentation and robust error handling contribute to its high score.",97,"Excellent skill for systematically fixing failing tests, well-documented and robust.",[221,222,223,224,225],"testing","debugging","automation","code-quality","refactoring","global","verified",[229,230,231],"Automatically fix broken tests after a refactoring session.","Ensure all regression tests pass after a dependency update.","Systematically resolve test failures following a major code change.",[233,234,235,236,237,238,239,240,241],"Read available 'sadd' skill if present.","Discover test infrastructure (test commands, project structure).","Run all tests to establish a baseline.","Identify all failing test files.","Verify single test execution can be reliably run.","Launch 'developer' agents in parallel for each failing test file.","Provide agents with context, target file, guidance, resources, command, and goal to fix tests.","Verify all fixes by running the full test suite again.","Iterate by launching new agents for remaining failures until 100% pass rate.",{"codeQuality":243,"collectedAt":245,"documentation":246,"maintenance":249,"security":256,"testCoverage":258},{"hasLockfile":244},true,1778695796009,{"descriptionLength":247,"readmeSize":248},80,40436,{"closedIssues90d":250,"forks":251,"hasChangelog":252,"openIssues90d":253,"pushedAt":254,"stars":255},8,89,false,6,1778029371000,993,{"hasNpmPackage":252,"license":257,"smitheryVerified":252},"GPL-3.0",{"hasCi":252,"hasTests":244},{"updatedAt":260},1778695812100,{"basePath":262,"githubOwner":263,"githubRepo":264,"locale":18,"slug":265,"type":266},"plugins/tdd/skills/fix-tests","NeoLabHQ","context-engineering-kit","fix-tests","skill",{"_creationTime":268,"_id":269,"community":270,"display":271,"identity":275,"parentExtension":278,"providers":310,"relations":318,"tags":319,"workflow":320},1778694480889.9453,"k171c9t45bz5sww3f8cc6m40bx86n7rq",{"reviewCount":8},{"description":272,"installMethods":273,"name":274,"sourceUrl":14},"Introduces commands for test-driven development, common anti-patterns and skills for testing using subagents.",{"claudeCode":274},"tdd",{"basePath":276,"githubOwner":263,"githubRepo":264,"locale":18,"slug":274,"type":277},"plugins/tdd","plugin",{"_creationTime":279,"_id":280,"community":281,"display":282,"identity":286,"providers":289,"relations":304,"tags":306,"workflow":307},1778694480889.9443,"k173g7jx10ba2yhdcc5s3cc1jd86mzfh",{"reviewCount":8},{"description":283,"installMethods":284,"name":285,"sourceUrl":14},"Hand-crafted collection of advanced context engineering techniques and patterns with minimal token footprint focused on improving agent result quality.",{"claudeCode":12},"Context Engineering Kit",{"basePath":287,"githubOwner":263,"githubRepo":264,"locale":18,"slug":264,"type":288},"","marketplace",{"evaluate":290,"extract":297},{"promptVersionExtension":291,"promptVersionScoring":215,"score":218,"tags":292,"targetMarket":226,"tier":227},"3.1.0",[293,294,295,224,296],"context-engineering","agent-productivity","llm-patterns","developer-tools",{"commitSha":298,"license":299,"marketplace":300,"plugin":302},"HEAD","GPL-3.0-or-later",{"name":264,"pluginCount":301,"version":214},13,{"mcpCount":8,"provider":303,"skillCount":8},"classify",{"repoId":305},"kd7a3rj13ezgx1wgm0jfh08hsx86n0sz",[294,224,293,296,295],{"evaluatedAt":308,"extractAt":309,"updatedAt":308},1778694497063,1778694480890,{"evaluate":311,"extract":315},{"promptVersionExtension":214,"promptVersionScoring":215,"score":312,"tags":313,"targetMarket":226,"tier":314},75,[274,221,296,224,223],"flagged",{"commitSha":298,"plugin":316},{"mcpCount":8,"provider":303,"skillCount":317},3,{"parentExtensionId":280,"repoId":305},[223,224,296,274,221],{"evaluatedAt":321,"extractAt":309,"updatedAt":321},1778694565755,{"evaluate":323,"extract":325},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":324,"targetMarket":226,"tier":227},[221,222,223,224,225],{"commitSha":298,"license":299},{"parentExtensionId":269,"repoId":305},{"_creationTime":328,"_id":305,"identity":329,"providers":330,"workflow":1155},1778694475065.1633,{"githubOwner":263,"githubRepo":264,"sourceUrl":14},{"classify":331,"discover":1140,"github":1143},{"commitSha":298,"extensions":332},[333,346,385,410,433,445,478,487,524,547,582,595,604,623,646,655,663,670,678,686,694,702,710,718,726,734,742,750,758,766,774,782,790,798,806,814,822,830,838,846,854,862,870,878,886,893,901,909,917,925,933,941,949,957,965,973,981,989,997,1005,1013,1021,1029,1037,1045,1053,1061,1069,1077,1085,1093,1101,1109,1119,1124,1132],{"basePath":287,"description":283,"displayName":264,"installMethods":334,"rationale":335,"selectedPaths":336,"source":345,"sourceLanguage":18,"type":288},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[337,340,342],{"path":338,"priority":339},".claude-plugin/marketplace.json","mandatory",{"path":341,"priority":339},"README.md",{"path":343,"priority":344},"LICENSE","high","rule",{"basePath":347,"description":348,"displayName":349,"installMethods":350,"rationale":351,"selectedPaths":352,"source":345,"sourceLanguage":18,"type":277},"plugins/reflexion","Collection of commands that force LLM to reflect on previous response and output. Based on papers like Self-Refine and Reflexion. These techniques improve the output of large language models by introducing feedback and refinement loops.","reflexion",{"claudeCode":349},"plugin manifest at plugins/reflexion/.claude-plugin/plugin.json",[353,355,356,359,361,363,365,367,369,371,373,375,377,379,381,383],{"path":354,"priority":339},".claude-plugin/plugin.json",{"path":341,"priority":339},{"path":357,"priority":358},"skills/critique/SKILL.md","medium",{"path":360,"priority":358},"skills/memorize/SKILL.md",{"path":362,"priority":358},"skills/reflect/SKILL.md",{"path":364,"priority":344},"hooks/.gitignore",{"path":366,"priority":344},"hooks/README.md",{"path":368,"priority":344},"hooks/hooks.json",{"path":370,"priority":344},"hooks/package.json",{"path":372,"priority":344},"hooks/src/index.ts",{"path":374,"priority":344},"hooks/src/lib.ts",{"path":376,"priority":344},"hooks/src/onStopHandler.test.ts",{"path":378,"priority":344},"hooks/src/onStopHandler.ts",{"path":380,"priority":344},"hooks/src/session.ts",{"path":382,"priority":344},"hooks/tsconfig.json",{"path":384,"priority":344},"hooks/vitest.config.ts",{"basePath":386,"description":387,"displayName":388,"installMethods":389,"rationale":390,"selectedPaths":391,"source":345,"sourceLanguage":18,"type":277},"plugins/review","Introduce codebase and PR review commands and skills using multiple specialized agents.","review",{"claudeCode":388},"plugin manifest at plugins/review/.claude-plugin/plugin.json",[392,393,394,396,398,400,402,404,406,408],{"path":354,"priority":339},{"path":341,"priority":339},{"path":395,"priority":358},"skills/review-local-changes/SKILL.md",{"path":397,"priority":358},"skills/review-pr/SKILL.md",{"path":399,"priority":344},"agents/bug-hunter.md",{"path":401,"priority":344},"agents/code-quality-reviewer.md",{"path":403,"priority":344},"agents/contracts-reviewer.md",{"path":405,"priority":344},"agents/historical-context-reviewer.md",{"path":407,"priority":344},"agents/security-auditor.md",{"path":409,"priority":344},"agents/test-coverage-reviewer.md",{"basePath":411,"description":412,"displayName":413,"installMethods":414,"rationale":415,"selectedPaths":416,"source":345,"sourceLanguage":18,"type":277},"plugins/git","Introduces commands for commit and PRs creation, plus skills for git worktrees and notes.","git",{"claudeCode":413},"plugin manifest at plugins/git/.claude-plugin/plugin.json",[417,418,419,421,423,425,427,429,431],{"path":354,"priority":339},{"path":341,"priority":339},{"path":420,"priority":358},"skills/analyze-issue/SKILL.md",{"path":422,"priority":358},"skills/attach-review-to-pr/SKILL.md",{"path":424,"priority":358},"skills/commit/SKILL.md",{"path":426,"priority":358},"skills/create-pr/SKILL.md",{"path":428,"priority":358},"skills/git-notes/SKILL.md",{"path":430,"priority":358},"skills/git-worktrees/SKILL.md",{"path":432,"priority":358},"skills/load-issues/SKILL.md",{"basePath":276,"description":272,"displayName":274,"installMethods":434,"rationale":435,"selectedPaths":436,"source":345,"sourceLanguage":18,"type":277},{"claudeCode":274},"plugin manifest at plugins/tdd/.claude-plugin/plugin.json",[437,438,439,441,443],{"path":354,"priority":339},{"path":341,"priority":339},{"path":440,"priority":358},"skills/fix-tests/SKILL.md",{"path":442,"priority":358},"skills/test-driven-development/SKILL.md",{"path":444,"priority":358},"skills/write-tests/SKILL.md",{"basePath":446,"description":447,"displayName":448,"installMethods":449,"rationale":450,"selectedPaths":451,"source":345,"sourceLanguage":18,"type":277},"plugins/sadd","Introduces skills for subagent-driven development, dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates.","sadd",{"claudeCode":448},"plugin manifest at plugins/sadd/.claude-plugin/plugin.json",[452,453,454,456,458,460,462,464,466,468,470,472,474,476],{"path":354,"priority":339},{"path":341,"priority":339},{"path":455,"priority":358},"skills/do-and-judge/SKILL.md",{"path":457,"priority":358},"skills/do-competitively/SKILL.md",{"path":459,"priority":358},"skills/do-in-parallel/SKILL.md",{"path":461,"priority":358},"skills/do-in-steps/SKILL.md",{"path":463,"priority":358},"skills/judge/SKILL.md",{"path":465,"priority":358},"skills/judge-with-debate/SKILL.md",{"path":467,"priority":358},"skills/launch-sub-agent/SKILL.md",{"path":469,"priority":358},"skills/multi-agent-patterns/SKILL.md",{"path":471,"priority":358},"skills/subagent-driven-development/SKILL.md",{"path":473,"priority":358},"skills/tree-of-thoughts/SKILL.md",{"path":475,"priority":344},"agents/judge.md",{"path":477,"priority":344},"agents/meta-judge.md",{"basePath":479,"description":480,"displayName":481,"installMethods":482,"rationale":483,"selectedPaths":484,"source":345,"sourceLanguage":18,"type":277},"plugins/ddd","Introduces command to update CLAUDE.md with best practices for domain-driven development, focused on quality of code, includes Clean Architecture, SOLID principles, and other design patterns.","ddd",{"claudeCode":481},"plugin manifest at plugins/ddd/.claude-plugin/plugin.json",[485,486],{"path":354,"priority":339},{"path":341,"priority":339},{"basePath":488,"description":489,"displayName":490,"installMethods":491,"rationale":492,"selectedPaths":493,"source":345,"sourceLanguage":18,"type":277},"plugins/sdd","Specification Driven Development workflow commands and agents, based on Github Spec Kit and OpenSpec. Uses specialized agents for effective context management and quality review.","sdd",{"claudeCode":490},"plugin manifest at plugins/sdd/.claude-plugin/plugin.json",[494,495,496,498,500,502,504,506,508,510,512,514,516,518,520,522],{"path":354,"priority":339},{"path":341,"priority":339},{"path":497,"priority":358},"skills/add-task/SKILL.md",{"path":499,"priority":358},"skills/brainstorm/SKILL.md",{"path":501,"priority":358},"skills/create-ideas/SKILL.md",{"path":503,"priority":358},"skills/implement-task/SKILL.md",{"path":505,"priority":358},"skills/plan-task/SKILL.md",{"path":507,"priority":344},"agents/business-analyst.md",{"path":509,"priority":344},"agents/code-explorer.md",{"path":511,"priority":344},"agents/developer.md",{"path":513,"priority":344},"agents/qa-engineer.md",{"path":515,"priority":344},"agents/researcher.md",{"path":517,"priority":344},"agents/software-architect.md",{"path":519,"priority":344},"agents/team-lead.md",{"path":521,"priority":344},"agents/tech-lead.md",{"path":523,"priority":344},"agents/tech-writer.md",{"basePath":525,"description":526,"displayName":527,"installMethods":528,"rationale":529,"selectedPaths":530,"source":345,"sourceLanguage":18,"type":277},"plugins/kaizen","Inspired by Japanese continuous improvement philosophy, Agile and Lean development practices. Introduces commands for analysis of root cause of issues and problems, including 5 Whys, Cause and Effect Analysis, and other techniques.","kaizen",{"claudeCode":527},"plugin manifest at plugins/kaizen/.claude-plugin/plugin.json",[531,532,533,535,537,539,541,543,545],{"path":354,"priority":339},{"path":341,"priority":339},{"path":534,"priority":358},"skills/analyse/SKILL.md",{"path":536,"priority":358},"skills/analyse-problem/SKILL.md",{"path":538,"priority":358},"skills/cause-and-effect/SKILL.md",{"path":540,"priority":358},"skills/kaizen/SKILL.md",{"path":542,"priority":358},"skills/plan-do-check-act/SKILL.md",{"path":544,"priority":358},"skills/root-cause-tracing/SKILL.md",{"path":546,"priority":358},"skills/why/SKILL.md",{"basePath":548,"description":549,"displayName":550,"installMethods":551,"rationale":552,"selectedPaths":553,"source":345,"sourceLanguage":18,"type":277},"plugins/customaize-agent","Commands and skills for writing and refining commands, hooks, skills for Claude Code, includes Anthropic Best Practices and Agent Persuasion Principles that can be useful for sub-agent workflows.","customaize-agent",{"claudeCode":550},"plugin manifest at plugins/customaize-agent/.claude-plugin/plugin.json",[554,555,556,558,560,562,564,566,568,570,572,574,576,578,580],{"path":354,"priority":339},{"path":341,"priority":339},{"path":557,"priority":358},"skills/agent-evaluation/SKILL.md",{"path":559,"priority":358},"skills/apply-anthropic-skill-best-practices/SKILL.md",{"path":561,"priority":358},"skills/context-engineering/SKILL.md",{"path":563,"priority":358},"skills/create-agent/SKILL.md",{"path":565,"priority":358},"skills/create-command/SKILL.md",{"path":567,"priority":358},"skills/create-hook/SKILL.md",{"path":569,"priority":358},"skills/create-rule/SKILL.md",{"path":571,"priority":358},"skills/create-skill/SKILL.md",{"path":573,"priority":358},"skills/create-workflow-command/SKILL.md",{"path":575,"priority":358},"skills/prompt-engineering/SKILL.md",{"path":577,"priority":358},"skills/test-prompt/SKILL.md",{"path":579,"priority":358},"skills/test-skill/SKILL.md",{"path":581,"priority":358},"skills/thought-based-reasoning/SKILL.md",{"basePath":583,"description":584,"displayName":585,"installMethods":586,"rationale":587,"selectedPaths":588,"source":345,"sourceLanguage":18,"type":277},"plugins/docs","Commands for analysing project, writing and refining documentation.","docs",{"claudeCode":585},"plugin manifest at plugins/docs/.claude-plugin/plugin.json",[589,590,591,593],{"path":354,"priority":339},{"path":341,"priority":339},{"path":592,"priority":358},"skills/update-docs/SKILL.md",{"path":594,"priority":358},"skills/write-concisely/SKILL.md",{"basePath":596,"description":597,"displayName":598,"installMethods":599,"rationale":600,"selectedPaths":601,"source":345,"sourceLanguage":18,"type":277},"plugins/tech-stack","Commands for setup or update of CLAUDE.md file with best practices for specific language or framework.","tech-stack",{"claudeCode":598},"plugin manifest at plugins/tech-stack/.claude-plugin/plugin.json",[602,603],{"path":354,"priority":339},{"path":341,"priority":339},{"basePath":605,"description":606,"displayName":607,"installMethods":608,"rationale":609,"selectedPaths":610,"source":345,"sourceLanguage":18,"type":277},"plugins/mcp","Commands for setup well known MCP server integration if needed and update CLAUDE.md file with requirement to use this MCP server for current project.","mcp",{"claudeCode":607},"plugin manifest at plugins/mcp/.claude-plugin/plugin.json",[611,612,613,615,617,619,621],{"path":354,"priority":339},{"path":341,"priority":339},{"path":614,"priority":358},"skills/build-mcp/SKILL.md",{"path":616,"priority":358},"skills/setup-arxiv-mcp/SKILL.md",{"path":618,"priority":358},"skills/setup-codemap-cli/SKILL.md",{"path":620,"priority":358},"skills/setup-context7-mcp/SKILL.md",{"path":622,"priority":358},"skills/setup-serena-mcp/SKILL.md",{"basePath":624,"description":625,"displayName":626,"installMethods":627,"rationale":628,"selectedPaths":629,"source":345,"sourceLanguage":18,"type":277},"plugins/fpf","First Principles Framework (FPF) for structured reasoning using workflow command pattern. Implements ADI (Abduction-Deduction-Induction) cycle via propose-hypotheses workflow with fpf-agent for hypothesis generation, logical verification, empirical validation, and auditable decision-making. Includes utility commands for status, query, decay, actualize, and reset.","fpf",{"claudeCode":626},"plugin manifest at plugins/fpf/.claude-plugin/plugin.json",[630,631,632,634,636,638,640,642,644],{"path":354,"priority":339},{"path":341,"priority":339},{"path":633,"priority":358},"skills/actualize/SKILL.md",{"path":635,"priority":358},"skills/decay/SKILL.md",{"path":637,"priority":358},"skills/propose-hypotheses/SKILL.md",{"path":639,"priority":358},"skills/query/SKILL.md",{"path":641,"priority":358},"skills/reset/SKILL.md",{"path":643,"priority":358},"skills/status/SKILL.md",{"path":645,"priority":344},"agents/fpf-agent.md",{"basePath":647,"description":648,"displayName":649,"installMethods":650,"rationale":651,"selectedPaths":652,"source":345,"sourceLanguage":18,"type":266},"plugins/customaize-agent/skills/agent-evaluation","Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.","agent-evaluation",{"claudeCode":12},"SKILL.md frontmatter at plugins/customaize-agent/skills/agent-evaluation/SKILL.md",[653],{"path":654,"priority":339},"SKILL.md",{"basePath":656,"description":657,"displayName":658,"installMethods":659,"rationale":660,"selectedPaths":661,"source":345,"sourceLanguage":18,"type":266},"plugins/customaize-agent/skills/apply-anthropic-skill-best-practices","Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure","apply-anthropic-skill-best-practices",{"claudeCode":12},"SKILL.md frontmatter at plugins/customaize-agent/skills/apply-anthropic-skill-best-practices/SKILL.md",[662],{"path":654,"priority":339},{"basePath":664,"description":665,"displayName":293,"installMethods":666,"rationale":667,"selectedPaths":668,"source":345,"sourceLanguage":18,"type":266},"plugins/customaize-agent/skills/context-engineering","Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.",{"claudeCode":12},"SKILL.md frontmatter at plugins/customaize-agent/skills/context-engineering/SKILL.md",[669],{"path":654,"priority":339},{"basePath":671,"description":672,"displayName":673,"installMethods":674,"rationale":675,"selectedPaths":676,"source":345,"sourceLanguage":18,"type":266},"plugins/customaize-agent/skills/create-agent","Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthropic best practices with proven patterns","create-agent",{"claudeCode":12},"SKILL.md frontmatter at plugins/customaize-agent/skills/create-agent/SKILL.md",[677],{"path":654,"priority":339},{"basePath":679,"description":680,"displayName":681,"installMethods":682,"rationale":683,"selectedPaths":684,"source":345,"sourceLanguage":18,"type":266},"plugins/customaize-agent/skills/create-command","Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration","create-command",{"claudeCode":12},"SKILL.md frontmatter at plugins/customaize-agent/skills/create-command/SKILL.md",[685],{"path":654,"priority":339},{"basePath":687,"description":688,"displayName":689,"installMethods":690,"rationale":691,"selectedPaths":692,"source":345,"sourceLanguage":18,"type":266},"plugins/customaize-agent/skills/create-rule","Use when found gap or repetative issue, that produced by you or implemenataion agent. Esentially use it each time when you say \"You absolutly right, I should have done it differently.\" -> need create rule for this issue so it not appears again.","create-rule",{"claudeCode":12},"SKILL.md frontmatter at plugins/customaize-agent/skills/create-rule/SKILL.md",[693],{"path":654,"priority":339},{"basePath":695,"description":696,"displayName":697,"installMethods":698,"rationale":699,"selectedPaths":700,"source":345,"sourceLanguage":18,"type":266},"plugins/customaize-agent/skills/create-skill","Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization","create-skill",{"claudeCode":12},"SKILL.md frontmatter at plugins/customaize-agent/skills/create-skill/SKILL.md",[701],{"path":654,"priority":339},{"basePath":703,"description":704,"displayName":705,"installMethods":706,"rationale":707,"selectedPaths":708,"source":345,"sourceLanguage":18,"type":266},"plugins/customaize-agent/skills/create-workflow-command","Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts","create-workflow-command",{"claudeCode":12},"SKILL.md frontmatter at plugins/customaize-agent/skills/create-workflow-command/SKILL.md",[709],{"path":654,"priority":339},{"basePath":711,"description":712,"displayName":713,"installMethods":714,"rationale":715,"selectedPaths":716,"source":345,"sourceLanguage":18,"type":266},"plugins/customaize-agent/skills/prompt-engineering","Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.","prompt-engineering",{"claudeCode":12},"SKILL.md frontmatter at plugins/customaize-agent/skills/prompt-engineering/SKILL.md",[717],{"path":654,"priority":339},{"basePath":719,"description":720,"displayName":721,"installMethods":722,"rationale":723,"selectedPaths":724,"source":345,"sourceLanguage":18,"type":266},"plugins/customaize-agent/skills/test-prompt","Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTOR cycle to prompt engineering using subagents for isolated testing","test-prompt",{"claudeCode":12},"SKILL.md frontmatter at plugins/customaize-agent/skills/test-prompt/SKILL.md",[725],{"path":654,"priority":339},{"basePath":727,"description":728,"displayName":729,"installMethods":730,"rationale":731,"selectedPaths":732,"source":345,"sourceLanguage":18,"type":266},"plugins/customaize-agent/skills/test-skill","Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes","test-skill",{"claudeCode":12},"SKILL.md frontmatter at plugins/customaize-agent/skills/test-skill/SKILL.md",[733],{"path":654,"priority":339},{"basePath":735,"description":736,"displayName":737,"installMethods":738,"rationale":739,"selectedPaths":740,"source":345,"sourceLanguage":18,"type":266},"plugins/customaize-agent/skills/thought-based-reasoning","Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or problems where simple prompting fails - provides comprehensive guide to Chain-of-Thought and related prompting techniques (Zero-shot CoT, Self-Consistency, Tree of Thoughts, Least-to-Most, ReAct, PAL, Reflexion) with templates, decision matrices, and research-backed patterns","thought-based-reasoning",{"claudeCode":12},"SKILL.md frontmatter at plugins/customaize-agent/skills/thought-based-reasoning/SKILL.md",[741],{"path":654,"priority":339},{"basePath":743,"description":744,"displayName":745,"installMethods":746,"rationale":747,"selectedPaths":748,"source":345,"sourceLanguage":18,"type":266},"plugins/docs/skills/update-docs","Update and maintain project documentation for local code changes using multi-agent workflow with tech-writer agents. Covers docs/, READMEs, JSDoc, and API documentation.","update-docs",{"claudeCode":12},"SKILL.md frontmatter at plugins/docs/skills/update-docs/SKILL.md",[749],{"path":654,"priority":339},{"basePath":751,"description":752,"displayName":753,"installMethods":754,"rationale":755,"selectedPaths":756,"source":345,"sourceLanguage":18,"type":266},"plugins/docs/skills/write-concisely","Apply writing rules to any documentation that humans will read. Makes your writing clearer, stronger, and more professional.","write-concisely",{"claudeCode":12},"SKILL.md frontmatter at plugins/docs/skills/write-concisely/SKILL.md",[757],{"path":654,"priority":339},{"basePath":759,"description":760,"displayName":761,"installMethods":762,"rationale":763,"selectedPaths":764,"source":345,"sourceLanguage":18,"type":266},"plugins/fpf/skills/actualize","Reconcile the project's FPF state with recent repository changes","actualize",{"claudeCode":12},"SKILL.md frontmatter at plugins/fpf/skills/actualize/SKILL.md",[765],{"path":654,"priority":339},{"basePath":767,"description":768,"displayName":769,"installMethods":770,"rationale":771,"selectedPaths":772,"source":345,"sourceLanguage":18,"type":266},"plugins/fpf/skills/decay","Manage evidence freshness by identifying stale decisions and providing governance actions","decay",{"claudeCode":12},"SKILL.md frontmatter at plugins/fpf/skills/decay/SKILL.md",[773],{"path":654,"priority":339},{"basePath":775,"description":776,"displayName":777,"installMethods":778,"rationale":779,"selectedPaths":780,"source":345,"sourceLanguage":18,"type":266},"plugins/fpf/skills/propose-hypotheses","Execute complete FPF cycle from hypothesis generation to decision","propose-hypotheses",{"claudeCode":12},"SKILL.md frontmatter at plugins/fpf/skills/propose-hypotheses/SKILL.md",[781],{"path":654,"priority":339},{"basePath":783,"description":784,"displayName":785,"installMethods":786,"rationale":787,"selectedPaths":788,"source":345,"sourceLanguage":18,"type":266},"plugins/fpf/skills/query","Search the FPF knowledge base and display hypothesis details with assurance information","query",{"claudeCode":12},"SKILL.md frontmatter at plugins/fpf/skills/query/SKILL.md",[789],{"path":654,"priority":339},{"basePath":791,"description":792,"displayName":793,"installMethods":794,"rationale":795,"selectedPaths":796,"source":345,"sourceLanguage":18,"type":266},"plugins/fpf/skills/reset","Reset the FPF reasoning cycle to start fresh","reset",{"claudeCode":12},"SKILL.md frontmatter at plugins/fpf/skills/reset/SKILL.md",[797],{"path":654,"priority":339},{"basePath":799,"description":800,"displayName":801,"installMethods":802,"rationale":803,"selectedPaths":804,"source":345,"sourceLanguage":18,"type":266},"plugins/fpf/skills/status","Display the current state of the FPF knowledge base","status",{"claudeCode":12},"SKILL.md frontmatter at plugins/fpf/skills/status/SKILL.md",[805],{"path":654,"priority":339},{"basePath":807,"description":808,"displayName":809,"installMethods":810,"rationale":811,"selectedPaths":812,"source":345,"sourceLanguage":18,"type":266},"plugins/git/skills/analyze-issue","Analyze a GitHub issue and create a detailed technical specification","analyze-issue",{"claudeCode":12},"SKILL.md frontmatter at plugins/git/skills/analyze-issue/SKILL.md",[813],{"path":654,"priority":339},{"basePath":815,"description":816,"displayName":817,"installMethods":818,"rationale":819,"selectedPaths":820,"source":345,"sourceLanguage":18,"type":266},"plugins/git/skills/attach-review-to-pr","Add line-specific review comments to pull requests using GitHub CLI API","attach-review-to-pr",{"claudeCode":12},"SKILL.md frontmatter at plugins/git/skills/attach-review-to-pr/SKILL.md",[821],{"path":654,"priority":339},{"basePath":823,"description":824,"displayName":825,"installMethods":826,"rationale":827,"selectedPaths":828,"source":345,"sourceLanguage":18,"type":266},"plugins/git/skills/commit","Create well-formatted commits with conventional commit messages and emoji","commit",{"claudeCode":12},"SKILL.md frontmatter at plugins/git/skills/commit/SKILL.md",[829],{"path":654,"priority":339},{"basePath":831,"description":832,"displayName":833,"installMethods":834,"rationale":835,"selectedPaths":836,"source":345,"sourceLanguage":18,"type":266},"plugins/git/skills/create-pr","Create pull requests using GitHub CLI with proper templates and formatting","create-pr",{"claudeCode":12},"SKILL.md frontmatter at plugins/git/skills/create-pr/SKILL.md",[837],{"path":654,"priority":339},{"basePath":839,"description":840,"displayName":841,"installMethods":842,"rationale":843,"selectedPaths":844,"source":345,"sourceLanguage":18,"type":266},"plugins/git/skills/git-notes","Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands and patterns for attaching non-invasive metadata to Git objects.","git-notes",{"claudeCode":12},"SKILL.md frontmatter at plugins/git/skills/git-notes/SKILL.md",[845],{"path":654,"priority":339},{"basePath":847,"description":848,"displayName":849,"installMethods":850,"rationale":851,"selectedPaths":852,"source":345,"sourceLanguage":18,"type":266},"plugins/git/skills/git-worktrees","Use when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparing implementations across branches - provides git worktree commands and workflow patterns for parallel development with multiple working directories.","git-worktrees",{"claudeCode":12},"SKILL.md frontmatter at plugins/git/skills/git-worktrees/SKILL.md",[853],{"path":654,"priority":339},{"basePath":855,"description":856,"displayName":857,"installMethods":858,"rationale":859,"selectedPaths":860,"source":345,"sourceLanguage":18,"type":266},"plugins/git/skills/load-issues","Load all open issues from GitHub and save them as markdown files","load-issues",{"claudeCode":12},"SKILL.md frontmatter at plugins/git/skills/load-issues/SKILL.md",[861],{"path":654,"priority":339},{"basePath":863,"description":864,"displayName":865,"installMethods":866,"rationale":867,"selectedPaths":868,"source":345,"sourceLanguage":18,"type":266},"plugins/kaizen/skills/analyse","Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target","analyse",{"claudeCode":12},"SKILL.md frontmatter at plugins/kaizen/skills/analyse/SKILL.md",[869],{"path":654,"priority":339},{"basePath":871,"description":872,"displayName":873,"installMethods":874,"rationale":875,"selectedPaths":876,"source":345,"sourceLanguage":18,"type":266},"plugins/kaizen/skills/analyse-problem","Comprehensive A3 one-page problem analysis with root cause and action plan","analyse-problem",{"claudeCode":12},"SKILL.md frontmatter at plugins/kaizen/skills/analyse-problem/SKILL.md",[877],{"path":654,"priority":339},{"basePath":879,"description":880,"displayName":881,"installMethods":882,"rationale":883,"selectedPaths":884,"source":345,"sourceLanguage":18,"type":266},"plugins/kaizen/skills/cause-and-effect","Systematic Fishbone analysis exploring problem causes across six categories","cause-and-effect",{"claudeCode":12},"SKILL.md frontmatter at plugins/kaizen/skills/cause-and-effect/SKILL.md",[885],{"path":654,"priority":339},{"basePath":887,"description":888,"displayName":527,"installMethods":889,"rationale":890,"selectedPaths":891,"source":345,"sourceLanguage":18,"type":266},"plugins/kaizen/skills/kaizen","Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide tehniquest to avoid over-engineering and apply iterative improvements.",{"claudeCode":12},"SKILL.md frontmatter at plugins/kaizen/skills/kaizen/SKILL.md",[892],{"path":654,"priority":339},{"basePath":894,"description":895,"displayName":896,"installMethods":897,"rationale":898,"selectedPaths":899,"source":345,"sourceLanguage":18,"type":266},"plugins/kaizen/skills/plan-do-check-act","Iterative PDCA cycle for systematic experimentation and continuous improvement","plan-do-check-act",{"claudeCode":12},"SKILL.md frontmatter at plugins/kaizen/skills/plan-do-check-act/SKILL.md",[900],{"path":654,"priority":339},{"basePath":902,"description":903,"displayName":904,"installMethods":905,"rationale":906,"selectedPaths":907,"source":345,"sourceLanguage":18,"type":266},"plugins/kaizen/skills/root-cause-tracing","Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior","root-cause-tracing",{"claudeCode":12},"SKILL.md frontmatter at plugins/kaizen/skills/root-cause-tracing/SKILL.md",[908],{"path":654,"priority":339},{"basePath":910,"description":911,"displayName":912,"installMethods":913,"rationale":914,"selectedPaths":915,"source":345,"sourceLanguage":18,"type":266},"plugins/kaizen/skills/why","Iterative Five Whys root cause analysis drilling from symptoms to fundamentals","why",{"claudeCode":12},"SKILL.md frontmatter at plugins/kaizen/skills/why/SKILL.md",[916],{"path":654,"priority":339},{"basePath":918,"description":919,"displayName":920,"installMethods":921,"rationale":922,"selectedPaths":923,"source":345,"sourceLanguage":18,"type":266},"plugins/mcp/skills/build-mcp","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).","build-mcp",{"claudeCode":12},"SKILL.md frontmatter at plugins/mcp/skills/build-mcp/SKILL.md",[924],{"path":654,"priority":339},{"basePath":926,"description":927,"displayName":928,"installMethods":929,"rationale":930,"selectedPaths":931,"source":345,"sourceLanguage":18,"type":266},"plugins/mcp/skills/setup-arxiv-mcp","Guide for setup arXiv paper search MCP server using Docker MCP","setup-arxiv-mcp",{"claudeCode":12},"SKILL.md frontmatter at plugins/mcp/skills/setup-arxiv-mcp/SKILL.md",[932],{"path":654,"priority":339},{"basePath":934,"description":935,"displayName":936,"installMethods":937,"rationale":938,"selectedPaths":939,"source":345,"sourceLanguage":18,"type":266},"plugins/mcp/skills/setup-codemap-cli","Guide for setup Codemap CLI for intelligent codebase visualization and navigation","setup-codemap-cli",{"claudeCode":12},"SKILL.md frontmatter at plugins/mcp/skills/setup-codemap-cli/SKILL.md",[940],{"path":654,"priority":339},{"basePath":942,"description":943,"displayName":944,"installMethods":945,"rationale":946,"selectedPaths":947,"source":345,"sourceLanguage":18,"type":266},"plugins/mcp/skills/setup-context7-mcp","Guide for setup Context7 MCP server to load documentation for specific technologies.","setup-context7-mcp",{"claudeCode":12},"SKILL.md frontmatter at plugins/mcp/skills/setup-context7-mcp/SKILL.md",[948],{"path":654,"priority":339},{"basePath":950,"description":951,"displayName":952,"installMethods":953,"rationale":954,"selectedPaths":955,"source":345,"sourceLanguage":18,"type":266},"plugins/mcp/skills/setup-serena-mcp","Guide for setup Serena MCP server for semantic code retrieval and editing capabilities","setup-serena-mcp",{"claudeCode":12},"SKILL.md frontmatter at plugins/mcp/skills/setup-serena-mcp/SKILL.md",[956],{"path":654,"priority":339},{"basePath":958,"description":959,"displayName":960,"installMethods":961,"rationale":962,"selectedPaths":963,"source":345,"sourceLanguage":18,"type":266},"plugins/reflexion/skills/critique","Comprehensive multi-perspective review using specialized judges with debate and consensus building","critique",{"claudeCode":12},"SKILL.md frontmatter at plugins/reflexion/skills/critique/SKILL.md",[964],{"path":654,"priority":339},{"basePath":966,"description":967,"displayName":968,"installMethods":969,"rationale":970,"selectedPaths":971,"source":345,"sourceLanguage":18,"type":266},"plugins/reflexion/skills/memorize","Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering","memorize",{"claudeCode":12},"SKILL.md frontmatter at plugins/reflexion/skills/memorize/SKILL.md",[972],{"path":654,"priority":339},{"basePath":974,"description":975,"displayName":976,"installMethods":977,"rationale":978,"selectedPaths":979,"source":345,"sourceLanguage":18,"type":266},"plugins/reflexion/skills/reflect","Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification","reflect",{"claudeCode":12},"SKILL.md frontmatter at plugins/reflexion/skills/reflect/SKILL.md",[980],{"path":654,"priority":339},{"basePath":982,"description":983,"displayName":984,"installMethods":985,"rationale":986,"selectedPaths":987,"source":345,"sourceLanguage":18,"type":266},"plugins/review/skills/review-local-changes","Comprehensive review of local uncommitted changes using specialized agents with code improvement suggestions","review-local-changes",{"claudeCode":12},"SKILL.md frontmatter at plugins/review/skills/review-local-changes/SKILL.md",[988],{"path":654,"priority":339},{"basePath":990,"description":991,"displayName":992,"installMethods":993,"rationale":994,"selectedPaths":995,"source":345,"sourceLanguage":18,"type":266},"plugins/review/skills/review-pr","Comprehensive pull request review using specialized agents","review-pr",{"claudeCode":12},"SKILL.md frontmatter at plugins/review/skills/review-pr/SKILL.md",[996],{"path":654,"priority":339},{"basePath":998,"description":999,"displayName":1000,"installMethods":1001,"rationale":1002,"selectedPaths":1003,"source":345,"sourceLanguage":18,"type":266},"plugins/sadd/skills/do-and-judge","Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop","do-and-judge",{"claudeCode":12},"SKILL.md frontmatter at plugins/sadd/skills/do-and-judge/SKILL.md",[1004],{"path":654,"priority":339},{"basePath":1006,"description":1007,"displayName":1008,"installMethods":1009,"rationale":1010,"selectedPaths":1011,"source":345,"sourceLanguage":18,"type":266},"plugins/sadd/skills/do-competitively","Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis","do-competitively",{"claudeCode":12},"SKILL.md frontmatter at plugins/sadd/skills/do-competitively/SKILL.md",[1012],{"path":654,"priority":339},{"basePath":1014,"description":1015,"displayName":1016,"installMethods":1017,"rationale":1018,"selectedPaths":1019,"source":345,"sourceLanguage":18,"type":266},"plugins/sadd/skills/do-in-parallel","Launch multiple sub-agents in parallel to execute tasks across files or targets with intelligent model selection, quality-focused prompting, and meta-judge → LLM-as-a-judge verification","do-in-parallel",{"claudeCode":12},"SKILL.md frontmatter at plugins/sadd/skills/do-in-parallel/SKILL.md",[1020],{"path":654,"priority":339},{"basePath":1022,"description":1023,"displayName":1024,"installMethods":1025,"rationale":1026,"selectedPaths":1027,"source":345,"sourceLanguage":18,"type":266},"plugins/sadd/skills/do-in-steps","Execute complex tasks through sequential sub-agent orchestration with intelligent model selection, meta-judge → LLM-as-a-judge verification","do-in-steps",{"claudeCode":12},"SKILL.md frontmatter at plugins/sadd/skills/do-in-steps/SKILL.md",[1028],{"path":654,"priority":339},{"basePath":1030,"description":1031,"displayName":1032,"installMethods":1033,"rationale":1034,"selectedPaths":1035,"source":345,"sourceLanguage":18,"type":266},"plugins/sadd/skills/judge","Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation","judge",{"claudeCode":12},"SKILL.md frontmatter at plugins/sadd/skills/judge/SKILL.md",[1036],{"path":654,"priority":339},{"basePath":1038,"description":1039,"displayName":1040,"installMethods":1041,"rationale":1042,"selectedPaths":1043,"source":345,"sourceLanguage":18,"type":266},"plugins/sadd/skills/judge-with-debate","Evaluate solutions through multi-round debate between independent judges until consensus","judge-with-debate",{"claudeCode":12},"SKILL.md frontmatter at plugins/sadd/skills/judge-with-debate/SKILL.md",[1044],{"path":654,"priority":339},{"basePath":1046,"description":1047,"displayName":1048,"installMethods":1049,"rationale":1050,"selectedPaths":1051,"source":345,"sourceLanguage":18,"type":266},"plugins/sadd/skills/launch-sub-agent","Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification","launch-sub-agent",{"claudeCode":12},"SKILL.md frontmatter at plugins/sadd/skills/launch-sub-agent/SKILL.md",[1052],{"path":654,"priority":339},{"basePath":1054,"description":1055,"displayName":1056,"installMethods":1057,"rationale":1058,"selectedPaths":1059,"source":345,"sourceLanguage":18,"type":266},"plugins/sadd/skills/multi-agent-patterns","Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.","multi-agent-patterns",{"claudeCode":12},"SKILL.md frontmatter at plugins/sadd/skills/multi-agent-patterns/SKILL.md",[1060],{"path":654,"priority":339},{"basePath":1062,"description":1063,"displayName":1064,"installMethods":1065,"rationale":1066,"selectedPaths":1067,"source":345,"sourceLanguage":18,"type":266},"plugins/sadd/skills/subagent-driven-development","Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates","subagent-driven-development",{"claudeCode":12},"SKILL.md frontmatter at plugins/sadd/skills/subagent-driven-development/SKILL.md",[1068],{"path":654,"priority":339},{"basePath":1070,"description":1071,"displayName":1072,"installMethods":1073,"rationale":1074,"selectedPaths":1075,"source":345,"sourceLanguage":18,"type":266},"plugins/sadd/skills/tree-of-thoughts","Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi-agent evaluation","tree-of-thoughts",{"claudeCode":12},"SKILL.md frontmatter at plugins/sadd/skills/tree-of-thoughts/SKILL.md",[1076],{"path":654,"priority":339},{"basePath":1078,"description":1079,"displayName":1080,"installMethods":1081,"rationale":1082,"selectedPaths":1083,"source":345,"sourceLanguage":18,"type":266},"plugins/sdd/skills/add-task","creates draft task file in .specs/tasks/draft/ with original user intent","add-task",{"claudeCode":12},"SKILL.md frontmatter at plugins/sdd/skills/add-task/SKILL.md",[1084],{"path":654,"priority":339},{"basePath":1086,"description":1087,"displayName":1088,"installMethods":1089,"rationale":1090,"selectedPaths":1091,"source":345,"sourceLanguage":18,"type":266},"plugins/sdd/skills/brainstorm","Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes","brainstorm",{"claudeCode":12},"SKILL.md frontmatter at plugins/sdd/skills/brainstorm/SKILL.md",[1092],{"path":654,"priority":339},{"basePath":1094,"description":1095,"displayName":1096,"installMethods":1097,"rationale":1098,"selectedPaths":1099,"source":345,"sourceLanguage":18,"type":266},"plugins/sdd/skills/create-ideas","Generate ideas in one shot using creative sampling","create-ideas",{"claudeCode":12},"SKILL.md frontmatter at plugins/sdd/skills/create-ideas/SKILL.md",[1100],{"path":654,"priority":339},{"basePath":1102,"description":1103,"displayName":1104,"installMethods":1105,"rationale":1106,"selectedPaths":1107,"source":345,"sourceLanguage":18,"type":266},"plugins/sdd/skills/implement-task","Implement a task with automated LLM-as-Judge verification for critical steps","implement-task",{"claudeCode":12},"SKILL.md frontmatter at plugins/sdd/skills/implement-task/SKILL.md",[1108],{"path":654,"priority":339},{"basePath":1110,"description":1111,"displayName":1112,"installMethods":1113,"rationale":1114,"selectedPaths":1115,"source":345,"sourceLanguage":18,"type":266},"plugins/sdd/skills/plan-task","Refine, parallelize, and verify a draft task specification into a fully planned implementation-ready task","plan-task",{"claudeCode":12},"SKILL.md frontmatter at plugins/sdd/skills/plan-task/SKILL.md",[1116,1117],{"path":654,"priority":339},{"path":1118,"priority":358},"analyse-business-requirements.md",{"basePath":262,"description":10,"displayName":265,"installMethods":1120,"rationale":1121,"selectedPaths":1122,"source":345,"sourceLanguage":18,"type":266},{"claudeCode":12},"SKILL.md frontmatter at plugins/tdd/skills/fix-tests/SKILL.md",[1123],{"path":654,"priority":339},{"basePath":1125,"description":1126,"displayName":1127,"installMethods":1128,"rationale":1129,"selectedPaths":1130,"source":345,"sourceLanguage":18,"type":266},"plugins/tdd/skills/test-driven-development","Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first","test-driven-development",{"claudeCode":12},"SKILL.md frontmatter at plugins/tdd/skills/test-driven-development/SKILL.md",[1131],{"path":654,"priority":339},{"basePath":1133,"description":1134,"displayName":1135,"installMethods":1136,"rationale":1137,"selectedPaths":1138,"source":345,"sourceLanguage":18,"type":266},"plugins/tdd/skills/write-tests","Systematically add test coverage for all local code changes using specialized review and development agents. Add tests for uncommitted changes (including untracked files), or if everything is commited, then will cover latest commit.","write-tests",{"claudeCode":12},"SKILL.md frontmatter at plugins/tdd/skills/write-tests/SKILL.md",[1139],{"path":654,"priority":339},{"sources":1141},[1142],"manual",{"closedIssues90d":250,"description":1144,"forks":251,"homepage":1145,"license":257,"openIssues90d":253,"pushedAt":254,"readmeSize":248,"stars":255,"topics":1146},"Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.","https://cek.neolab.finance/",[1147,1148,1149,1150,288,1151,1152,1153,1154],"agent","ai","claude","llm","cline","cursor","opencode","windsurf",{"classifiedAt":1156,"discoverAt":1157,"extractAt":1158,"githubAt":1158,"updatedAt":1156},1778694480631,1778694475065,1778694478670,[223,224,222,225,221],{"evaluatedAt":260,"extractAt":309,"updatedAt":260},[],[1163,1195,1222,1242,1270,1299],{"_creationTime":1164,"_id":1165,"community":1166,"display":1167,"identity":1173,"providers":1179,"relations":1187,"tags":1190,"workflow":1191},1778699366078.7817,"k173mj3k9wcdq512bp1532xkwx86nrh4",{"reviewCount":8},{"description":1168,"installMethods":1169,"name":1171,"sourceUrl":1172},"当工作依赖于用户实时浏览器会话或可见的渲染状态，而不是静态抓取时使用，尤其是在浏览器调试上下文或 DevTools 选择的元素或请求、登录仪表板或 CMS 流程、localhost 应用、上传、下载、媒体检查、DOM 或 iframe 检查、Shadow DOM，或看起来像软 404、身份验证墙、反机器人检查或速率限制的浏览器故障时。",{"claudeCode":1170},"xixu-me/skills","使用我的浏览器","https://github.com/xixu-me/skills",{"basePath":1174,"githubOwner":1175,"githubRepo":1176,"locale":1177,"slug":1178,"type":266},"skills/use-my-browser","xixu-me","skills","zh-CN","use-my-browser",{"evaluate":1180,"extract":1185},{"promptVersionExtension":214,"promptVersionScoring":215,"score":1181,"tags":1182,"targetMarket":226,"tier":227},100,[1183,222,223,1184,296],"browser","ux",{"commitSha":298,"license":1186},"MIT",{"repoId":1188,"translatedFrom":1189},"kd77r2vb42jmgam0qbr9f2c6kn86mebv","k179cgk616p3xva37r5jqsfwvh86mcp2",[223,1183,222,296,1184],{"evaluatedAt":1192,"extractAt":1193,"updatedAt":1194},1778699261239,1778699106670,1778699366078,{"_creationTime":1196,"_id":1197,"community":1198,"display":1199,"identity":1205,"providers":1209,"relations":1216,"tags":1218,"workflow":1219},1778697652123.8857,"k179k1n5nw0md1x1j3dak31evn86mb5f",{"reviewCount":8},{"description":1200,"installMethods":1201,"name":1203,"sourceUrl":1204},"Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.",{"claudeCode":1202},"steipete/clawdis","telegram-crabbox-e2e-proof","https://github.com/steipete/clawdis",{"basePath":1206,"githubOwner":1207,"githubRepo":1208,"locale":18,"slug":1203,"type":266},".agents/skills/telegram-crabbox-e2e-proof","steipete","clawdis",{"evaluate":1210,"extract":1215},{"promptVersionExtension":214,"promptVersionScoring":215,"score":1181,"tags":1211,"targetMarket":226,"tier":227},[221,1212,223,1213,1214],"telegram","qa","cli",{"commitSha":298},{"repoId":1217},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[223,1214,1213,1212,221],{"evaluatedAt":1220,"extractAt":1221,"updatedAt":1220},1778698038113,1778697652123,{"_creationTime":1223,"_id":1224,"community":1225,"display":1226,"identity":1230,"providers":1232,"relations":1238,"tags":1239,"workflow":1240},1778697652123.8845,"k17bexjjjsz81ysk7bd3ggdm8s86mt2t",{"reviewCount":8},{"description":1227,"installMethods":1228,"name":1229,"sourceUrl":1204},"Choose, run, rerun, or debug OpenClaw tests, CI checks, Docker E2E lanes, release validation, and the cheapest safe verification path.",{"claudeCode":1202},"openclaw-testing",{"basePath":1231,"githubOwner":1207,"githubRepo":1208,"locale":18,"slug":1229,"type":266},".agents/skills/openclaw-testing",{"evaluate":1233,"extract":1237},{"promptVersionExtension":214,"promptVersionScoring":215,"score":1181,"tags":1234,"targetMarket":226,"tier":227},[221,1235,1236,223,296],"ci","validation",{"commitSha":298},{"repoId":1217},[223,1235,296,221,1236],{"evaluatedAt":1241,"extractAt":1221,"updatedAt":1241},1778697962962,{"_creationTime":1243,"_id":1244,"community":1245,"display":1246,"identity":1252,"providers":1256,"relations":1262,"tags":1265,"workflow":1266},1778697369634.8499,"k17333g8dacqsmw8kk79h77vmx86n0d1",{"reviewCount":8},{"description":1247,"installMethods":1248,"name":1250,"sourceUrl":1251},"AI 代理的浏览器自动化 CLI。当用户需要与网站交互时使用，包括浏览页面、填写表单、点击按钮、截屏、提取数据、测试 Web 应用或自动化任何浏览器任务。触发条件包括请求“打开网站”、“填表”、“点击按钮”、“截屏”、“抓取页面数据”、“测试此 Web 应用”、“登录网站”、“自动化浏览器操作”或任何需要以编程方式进行 Web 交互的任务。",{"claudeCode":1249},"shanraisshan/claude-code-best-practice","agent-browser","https://github.com/shanraisshan/claude-code-best-practice",{"basePath":1253,"githubOwner":1254,"githubRepo":1255,"locale":1177,"slug":1250,"type":266},".claude/skills/agent-browser","shanraisshan","claude-code-best-practice",{"evaluate":1257,"extract":1261},{"promptVersionExtension":214,"promptVersionScoring":215,"score":1181,"tags":1258,"targetMarket":226,"tier":227},[1259,1260,221,1214,223],"browser-automation","web-scraping",{"commitSha":298},{"repoId":1263,"translatedFrom":1264},"kd74710g49kxgwbfjxeb7s132d86myxr","k17ej9360g7468qswf3svnrx9186m1ng",[223,1259,1214,221,1260],{"evaluatedAt":1267,"extractAt":1268,"updatedAt":1269},1778697222051,1778697205743,1778697369634,{"_creationTime":1271,"_id":1272,"community":1273,"display":1274,"identity":1280,"providers":1285,"relations":1290,"tags":1294,"workflow":1295},1778698527362.5261,"k176bk4qe9ak5pqbq1p4acm18d86n19t",{"reviewCount":8},{"description":1275,"installMethods":1276,"name":1278,"sourceUrl":1279},"감지된 과잉 엔지니어링 패턴: (1) 사용자가 명시적으로 요청하지 않은 코드나 파일을 수정할 때 (2) 요청되지 않은 새로운 추상화 계층(클래스, 인터페이스, 팩토리, 래퍼)을 생성할 때 (3) 요청되지 않은 주석, 문서, JSDoc, 타입 주석을 추가할 때 (4) 요청되지 않은 새로운 종속성을 도입할 때 (5) 최소 편집 대신 파일 전체를 다시 작성할 때 (6) diff 범위가 사용자의 요청을 명백히 초과할 때 (7) 사용자가 \"너무 많아\", \"거기는 건드리지 마\", \"X만 변경해\", \"간단하게\", \"그만\"과 같은 신호를 보낼 때 (8) 발생할 수 없는 시나리오에 대한 오류 처리, 유효성 검사, 방어적 코드를 추가할 때 (9) 요청되지 않은 테스트, 설정 스캐폴딩, 문서를 생성할 때\n",{"claudeCode":1277},"uucz/moyu","Moyu (摸鱼)","https://github.com/uucz/moyu",{"basePath":1281,"githubOwner":1282,"githubRepo":1283,"locale":1177,"slug":1284,"type":266},"skills/moyu-ko","uucz","moyu","moyu-ko",{"evaluate":1286,"extract":1289},{"promptVersionExtension":214,"promptVersionScoring":215,"score":1181,"tags":1287,"targetMarket":226,"tier":227},[1288,224,713,296,225],"ai-assist",{"commitSha":298,"license":1186},{"parentExtensionId":1291,"repoId":1292,"translatedFrom":1293},"k17a8j7hxkm1n8dabrtcwp2z2d86nr39","kd7ccbpk8y3xm113xt8wy1c5jd86n94h","k17dzgrxxkxpeqmtcn5v3tjmad86n5tm",[1288,224,296,713,225],{"evaluatedAt":1296,"extractAt":1297,"updatedAt":1298},1778698415064,1778698296017,1778698527362,{"_creationTime":1300,"_id":1301,"community":1302,"display":1303,"identity":1309,"providers":1313,"relations":1323,"tags":1325,"workflow":1326},1778696052276.0203,"k17bgxxgryq8edg32egypsvqtn86m1h7",{"reviewCount":8},{"description":1304,"installMethods":1305,"name":1307,"sourceUrl":1308},"Detect and untangle circular dependencies. Runs madge/skott (TS), pycycle (Py), or compiler-only checks (Go/Rust). Auto-fixes leaf-extractable cycles; reports core cycles for human review. Use when the user asks to find circular imports, fix dependency cycles, or untangle module graph. Example queries — \"find circular imports\", \"fix dependency cycles\", \"untangle our module graph\", \"why is madge complaining\".",{"claudeCode":1306},"raintree-technology/claude-starter","cleanup-cycles","https://github.com/raintree-technology/claude-starter",{"basePath":1310,"githubOwner":1311,"githubRepo":1312,"locale":18,"slug":1307,"type":266},"templates/.claude/skills/cleanup-cycles","raintree-technology","claude-starter",{"evaluate":1314,"extract":1322},{"promptVersionExtension":214,"promptVersionScoring":215,"score":1181,"tags":1315,"targetMarket":226,"tier":227},[224,1316,1317,1318,1319,1320,1321,225],"dependencies","javascript","python","typescript","go","rust",{"commitSha":298},{"repoId":1324},"kd78ywakatnz4sjfx781sy14vh86mtty",[224,1316,1320,1317,1318,225,1321,1319],{"evaluatedAt":1327,"extractAt":1328,"updatedAt":1327},1778696977114,1778696052276]