[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-majiayu000-fixflow-en":3,"guides-for-majiayu000-fixflow":430,"similar-k17bwx69hk0p0w7rnpzvv2p16h86mp2k-en":431},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":246,"isFallback":241,"parentExtension":251,"providers":252,"relations":257,"repo":259,"tags":426,"workflow":427},1778692607327.2307,"k17bwx69hk0p0w7rnpzvv2p16h86mp2k",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Execute coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run tests continuously, and commit by default after each step (`per_step`). Support explicit commit policy overrides (`final_only`, `milestone`) and optional BDD (Given/When/Then) when users ask for behavior-driven delivery or requirements are unclear.",{"claudeCode":12},"majiayu000/vibeguard","fixflow","https://github.com/majiayu000/vibeguard",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":227,"workflow":244},1778692812461.2673,"kn78d596sdsqypfy31v1t7sac586mkrf","en",{"checks":20,"evaluatedAt":194,"extensionSummary":195,"features":196,"nonGoals":202,"promptVersionExtension":206,"promptVersionScoring":207,"purpose":208,"rationale":209,"score":210,"summary":211,"tags":212,"targetMarket":219,"tier":220,"useCases":221},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,89,93,97,101,105,108,111,114,118,121,124,127,130,133,136,140,144,148,151,155,158,161,164,167,171,175,178,181,184,187,191],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of AI coding agents making expensive mistakes and the solution of VibeGuard preventing them before they reach the codebase.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","VibeGuard offers significant value beyond default AI behavior by providing native rules, real-time hooks, and static guards to intercept and correct AI mistakes.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension provides a comprehensive set of tools, rules, and hooks covering the full lifecycle of AI code generation and review, making it suitable for production use.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","VibeGuard focuses on enforcing quality and safety in AI code generation, a coherent domain, with clear product boundaries between its Core and Workflow layers.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the extension's capabilities and purpose, highlighting its workflow and commit policy features.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The extension utilizes specific, narrow tools and commands for its various checks and guards, rather than a single generalist execution tool.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","All configuration options and parameters, including defaults and installation profiles, are clearly documented in the README and SKILL.md.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","Tools and commands are descriptively named and follow a consistent naming convention.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","Inputs and outputs for tools are well-defined and minimal, requesting only necessary data and returning promised payloads.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The extension is distributed under the MIT license, a permissive open-source license, clearly indicated by a LICENSE file.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The repository shows recent commit activity, indicating active maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The project utilizes Rust/Cargo and Python, and the installation script suggests it manages dependencies effectively.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","The extension's documentation and design principles emphasize avoiding hardcoded secrets and handling them appropriately, with no evidence of secrets being echoed.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The extension's design principles and documentation indicate a strong focus on treating loaded data as untrusted and bundling all assets, preventing injection vulnerabilities.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The extension bundles all assets and does not fetch remote content at runtime for execution, mitigating supply-chain risks.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","The extension's design focuses on operating within project boundaries and does not demonstrate attempts to modify files outside the extension or project folder.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","There is no evidence of detached process spawns or deny-retry loops in the provided documentation or code structure.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The extension's principles and documentation indicate a focus on preventing data exfiltration, with no undocumented outbound calls or submission of confidential data.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","The bundled content appears free of hidden-steering tricks, and descriptions use clean printable ASCII and expected Unicode.",{"category":65,"check":87,"severity":24,"summary":88},"Opaque code execution","The bundled scripts are plain and readable, with no indication of obfuscation techniques like base64 payloads or runtime fetching of code.",{"category":90,"check":91,"severity":24,"summary":92},"Portability","Structural Assumption","The extension uses relative paths and provides clear error messages for missing project structures, avoiding hardcoded user-specific paths.",{"category":94,"check":95,"severity":24,"summary":96},"Trust","Issues Attention","The project has a healthy ratio of closed to open issues, indicating active maintenance and responsiveness from the maintainers.",{"category":98,"check":99,"severity":24,"summary":100},"Versioning","Release Management","A meaningful versioning scheme is in place, with recent commits and clear indications of updates.",{"category":102,"check":103,"severity":24,"summary":104},"Code Execution","Validation","The extension appears to validate inputs and outputs, as suggested by its focus on code quality and safety guards.",{"category":65,"check":106,"severity":24,"summary":107},"Unguarded Destructive Operations","The extension's design includes guards against dangerous commands like `rm -rf` and `git push --force`, suggesting destructive operations are guarded.",{"category":102,"check":109,"severity":24,"summary":110},"Error Handling","The extension's design principle 'Error messages = fix instructions' implies robust error handling with clear messages and remediation steps.",{"category":102,"check":112,"severity":24,"summary":113},"Logging","The extension provides observability features including metrics and audit logs, with opt-in verbosity for detailed logging.",{"category":115,"check":116,"severity":24,"summary":117},"Compliance","GDPR","The extension focuses on code quality and safety, with no explicit mention or indication of operating on personal data without sanitization.",{"category":115,"check":119,"severity":24,"summary":120},"Target market","The extension appears to be globally applicable, with no regional or jurisdictional limitations identified in the documentation.",{"category":90,"check":122,"severity":24,"summary":123},"Runtime stability","The extension is designed to work with Claude Code and Codex CLI, and installation scripts support multiple platforms, indicating good runtime stability.",{"category":44,"check":125,"severity":24,"summary":126},"README","The README file exists, is comprehensive, and clearly states the extension's purpose and value proposition.",{"category":33,"check":128,"severity":24,"summary":129},"Tool surface size","The extension exposes a well-defined set of tools and commands, fitting within the recommended range for clarity and focus.",{"category":40,"check":131,"severity":24,"summary":132},"Overlapping near-synonym tools","The extension's tools are distinct and do not appear to have overlapping near-synonym names, avoiding ambiguity.",{"category":44,"check":134,"severity":24,"summary":135},"Phantom features","All advertised features, such as rules, hooks, and static guards, have corresponding implementations detailed in the documentation and code structure.",{"category":137,"check":138,"severity":24,"summary":139},"Install","Installation instruction","The README provides clear, copy-pasteable installation and verification instructions, including setup for different profiles and IDEs.",{"category":141,"check":142,"severity":24,"summary":143},"Errors","Actionable error messages","The extension's design principle 'Error messages = fix instructions' ensures that emitted error messages are actionable and provide remediation steps.",{"category":145,"check":146,"severity":24,"summary":147},"Execution","Pinned dependencies","The project relies on standard language runtimes (Python, Rust) and the installation script implies dependency management, suggesting pinned dependencies.",{"category":33,"check":149,"severity":24,"summary":150},"Dry-run preview","While not explicitly detailed for all operations, the extension's focus on safety and verification implies a strong inclination towards previewing changes before execution.",{"category":152,"check":153,"severity":24,"summary":154},"Protocol","Idempotent retry & timeouts","The extension's focus on safety and structured error handling suggests that operations are designed to be idempotent where possible and have appropriate timeouts.",{"category":115,"check":156,"severity":24,"summary":157},"Telemetry opt-in","The extension's documentation emphasizes a focus on user privacy and control, with no indication of opt-out telemetry or collection of sensitive data without explicit user action.",{"category":40,"check":159,"severity":24,"summary":160},"Precise Purpose","The description clearly defines the artifact (code generated by AI agents) and the user intent (execute coding tasks with a strict delivery workflow), with clear trigger cues.",{"category":40,"check":162,"severity":24,"summary":163},"Concise Frontmatter","The frontmatter is concise, self-contained, and accurately summarizes the core capability, making it effective for precise routing.",{"category":44,"check":165,"severity":24,"summary":166},"Concise Body","The SKILL.md body is concise and delegates deeper material to separate reference files, adhering to progressive disclosure.",{"category":168,"check":169,"severity":24,"summary":170},"Context","Progressive Disclosure","The SKILL.md outlines the overall flow and links to separate reference files for detailed sub-tasks, implementing progressive disclosure.",{"category":168,"check":172,"severity":173,"summary":174},"Forked exploration","not_applicable","This skill is not designed for deep exploration or code review that would necessitate a forked context.",{"category":22,"check":176,"severity":24,"summary":177},"Usage examples","The README provides clear, end-to-end usage examples for installation, verification, and various guard scripts, demonstrating their expected outcomes.",{"category":22,"check":179,"severity":24,"summary":180},"Edge cases","The documentation addresses potential issues like false positives and lists known issues with mitigation notes, indicating handling of edge cases.",{"category":102,"check":182,"severity":24,"summary":183},"Tool Fallback","The extension is designed to work with Claude Code and Codex CLI directly and mentions an app-server wrapper, indicating robust integration with minimal reliance on external, unlisted MCP servers.",{"category":90,"check":185,"severity":24,"summary":186},"Stack assumptions","The documentation clearly states stack assumptions (Python 3, Rust/Cargo) and runtime surfaces (Bash, Python scripts) and installation instructions cover multiple platforms.",{"category":188,"check":189,"severity":24,"summary":190},"Safety","Halt on unexpected state","The extension's design principles and guard mechanisms inherently halt workflows on unexpected states or dangerous operations, ensuring safety.",{"category":90,"check":192,"severity":24,"summary":193},"Cross-skill coupling","The skill appears self-contained, focusing on AI code generation quality, and does not implicitly rely on other skills being loaded concurrently.",1778692812351,"VibeGuard provides native rules, real-time hooks, and static guards to intercept and correct common mistakes made by AI coding agents like Claude Code and Codex. It enforces coding standards, prevents dangerous commands, and ensures code quality before it impacts a codebase.",[197,198,199,200,201],"Native rules to bias AI away from bad decisions","Real-time hooks for critical interception (write, bash, commit)","Static guards for project-wide analysis","Automated error fixing with actionable instructions","Closed-loop learning system to evolve defenses",[203,204,205],"Replacing human code review entirely","Providing a full IDE or code editor experience","Executing code in a sandboxed environment for security testing","3.0.0","4.4.0","To prevent AI coding agents from making common, expensive mistakes by enforcing quality, safety, and workflow standards through native rules, real-time hooks, and static analysis.","All checks passed with high quality, indicating a mature and well-documented extension.",100,"A robust set of guards and workflows to enforce quality and safety in AI code generation.",[213,214,215,216,217,218],"code-quality","ai-safety","developer-tools","code-generation","workflow-automation","security","global","verified",[222,223,224,225,226],"Preventing duplicate files and reinvented modules","Catching invented APIs, fake libraries, and hardcoded placeholders","Blocking dangerous shell/git commands","Ensuring code quality and test verification before commits","Automating code review and identifying AI-specific code slop",{"codeQuality":228,"collectedAt":230,"documentation":231,"maintenance":234,"security":240,"testCoverage":243},{"hasLockfile":229},true,1778692790328,{"descriptionLength":232,"readmeSize":233},355,20185,{"closedIssues90d":235,"forks":236,"hasChangelog":229,"openIssues90d":237,"pushedAt":238,"stars":239},48,2,10,1778682269000,8,{"hasNpmPackage":241,"license":242,"smitheryVerified":241},false,"MIT",{"hasCi":229,"hasTests":229},{"updatedAt":245},1778692812461,{"basePath":247,"githubOwner":248,"githubRepo":249,"locale":18,"slug":13,"type":250},"workflows/fixflow","majiayu000","vibeguard","skill",null,{"evaluate":253,"extract":255},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":254,"targetMarket":219,"tier":220},[213,214,215,216,217,218],{"commitSha":256},"HEAD",{"repoId":258},"kd7b0vh258xpbyerk68bk3e1ks86mk58",{"_creationTime":260,"_id":258,"identity":261,"providers":262,"workflow":422},1778692601876.5544,{"githubOwner":248,"githubRepo":249,"sourceUrl":14},{"classify":263,"discover":404,"github":407},{"commitSha":256,"extensions":264},[265,276,285,293,301,309,317,331,339,346,355,385,394],{"basePath":266,"description":267,"displayName":268,"installMethods":269,"rationale":270,"selectedPaths":271,"source":275,"sourceLanguage":18,"type":250},"skills/agentsmd-audit","Audit AGENTS.md / CLAUDE.md against the five high-leverage patterns (progressive disclosure, procedural workflows, decision tables, production code examples, domain rules with concrete alternatives). Reports per-pattern coverage, anti-patterns, and a prioritized fix list.","agentsmd-audit",{"claudeCode":12},"SKILL.md frontmatter at skills/agentsmd-audit/SKILL.md",[272],{"path":273,"priority":274},"SKILL.md","mandatory","rule",{"basePath":277,"description":278,"displayName":279,"installMethods":280,"rationale":281,"selectedPaths":282,"source":275,"sourceLanguage":284,"type":250},"skills/awk-posix-compat","Shell 脚本中 awk 的 POSIX 兼容性指南。\nUse when: 编写或审查包含 awk 的 shell 脚本，\n尤其是需要 macOS + Linux 跨平台运行的场景。\n触发词: awk, BSD awk, POSIX regex, [[:space:]],\nguard 脚本, 跨平台 shell\n","awk-posix-compat",{"claudeCode":12},"SKILL.md frontmatter at skills/awk-posix-compat/SKILL.md",[283],{"path":273,"priority":274},"zh-CN",{"basePath":286,"description":287,"displayName":288,"installMethods":289,"rationale":290,"selectedPaths":291,"source":275,"sourceLanguage":18,"type":250},"skills/eval-harness","Assessment-driven development — Quantify code generation quality with pass@k / pass^k metrics, automatically scored by Grader.","eval-harness",{"claudeCode":12},"SKILL.md frontmatter at skills/eval-harness/SKILL.md",[292],{"path":273,"priority":274},{"basePath":294,"description":295,"displayName":296,"installMethods":297,"rationale":298,"selectedPaths":299,"source":275,"sourceLanguage":18,"type":250},"skills/iterative-retrieval","Iterative retrieval — 4-stage loop (DISPATCH→EVALUATE→REFINE→LOOP) to pinpoint relevant information in the code base. Up to 3 rounds.","iterative-retrieval",{"claudeCode":12},"SKILL.md frontmatter at skills/iterative-retrieval/SKILL.md",[300],{"path":273,"priority":274},{"basePath":302,"description":303,"displayName":304,"installMethods":305,"rationale":306,"selectedPaths":307,"source":275,"sourceLanguage":18,"type":250},"skills/strategic-compact","Strategic compression — Manual compression of contexts at logical boundaries rather than arbitrary automatic compression. Key decisions and constraints are preserved and intermediate exploration is discarded.","strategic-compact",{"claudeCode":12},"SKILL.md frontmatter at skills/strategic-compact/SKILL.md",[308],{"path":273,"priority":274},{"basePath":310,"description":311,"displayName":312,"installMethods":313,"rationale":314,"selectedPaths":315,"source":275,"sourceLanguage":18,"type":250},"skills/trajectory-review","Post-hoc diagnosis of a failed agent trajectory. Classifies the first unrecoverable step into one of nine failure categories (plan adherence, hallucinated information, invalid tool call, misread tool output, intent–plan mismatch, under-specified intent, unsupported intent, guardrail trigger, system failure) and produces an evidence-backed root-cause report.","trajectory-review",{"claudeCode":12},"SKILL.md frontmatter at skills/trajectory-review/SKILL.md",[316],{"path":273,"priority":274},{"basePath":318,"description":319,"displayName":249,"installMethods":320,"rationale":321,"selectedPaths":322,"source":275,"sourceLanguage":18,"type":250},"skills/vibeguard","AI-assisted development of anti-hallucination specifications. Check out the seven-layer defense architecture, quantitative indicators, execution templates and practical cases. Used for code review, task startup inspection, and weekly review.",{"claudeCode":12},"SKILL.md frontmatter at skills/vibeguard/SKILL.md",[323,324,327,329],{"path":273,"priority":274},{"path":325,"priority":326},"references/review-template.md","medium",{"path":328,"priority":326},"references/scoring-matrix.md",{"path":330,"priority":326},"references/task-contract.yaml",{"basePath":332,"description":333,"displayName":334,"installMethods":335,"rationale":336,"selectedPaths":337,"source":275,"sourceLanguage":18,"type":250},"workflows/auto-optimize","Automate analysis, evaluation, design and optimization of target projects. Integrate VibeGuard as a baseline scan, the remediation process adheres to VibeGuard specifications, and a compliance check is run at the end. Support auto-run-agent autonomous execution.","auto-optimize",{"claudeCode":12},"SKILL.md frontmatter at workflows/auto-optimize/SKILL.md",[338],{"path":273,"priority":274},{"basePath":247,"description":10,"displayName":13,"installMethods":340,"rationale":341,"selectedPaths":342,"source":275,"sourceLanguage":18,"type":250},{"claudeCode":12},"SKILL.md frontmatter at workflows/fixflow/SKILL.md",[343,344],{"path":273,"priority":274},{"path":345,"priority":326},"CLAUDE.md",{"basePath":347,"description":348,"displayName":349,"installMethods":350,"rationale":351,"selectedPaths":352,"source":275,"sourceLanguage":18,"type":250},"workflows/optflow","Discover and deliver repository optimization work end to end: identify performance/reliability/maintainability/security/dx/cost optimization points, prioritize by impact-effort-risk, then execute fixes step by step with continuous testing and explicit commit policy (`final_only`, `per_step`, `milestone`). Default to `per_step` for implementation work so each feature is tested then committed before the next feature. Supports optional BDD (Given/When/Then).","optflow",{"claudeCode":12},"SKILL.md frontmatter at workflows/optflow/SKILL.md",[353,354],{"path":273,"priority":274},{"path":345,"priority":326},{"basePath":356,"description":357,"displayName":358,"installMethods":359,"rationale":360,"selectedPaths":361,"source":275,"sourceLanguage":18,"type":250},"workflows/plan-flow","Analyze repository-level duplicate/redundant design first, then build and execute a strict step-test-update plan in docs/plan. Use for deep architecture review, convergence planning, and traceable one-step-at-a-time delivery.","plan-flow",{"claudeCode":12},"SKILL.md frontmatter at workflows/plan-flow/SKILL.md",[362,363,364,366,368,370,372,374,376,378,381,383],{"path":273,"priority":274},{"path":345,"priority":326},{"path":365,"priority":326},"references/CLAUDE.md",{"path":367,"priority":326},"references/analysis-playbook.md",{"path":369,"priority":326},"references/execplan-integration.md",{"path":371,"priority":326},"references/execplan-template.md",{"path":373,"priority":326},"references/plan-accomplishments.md",{"path":375,"priority":326},"references/plan-template.md",{"path":377,"priority":326},"references/risk-impact-scoring.md",{"path":379,"priority":380},"scripts/findings_to_plan.py","low",{"path":382,"priority":380},"scripts/plan_lint.py",{"path":384,"priority":380},"scripts/redundancy_scan.sh",{"basePath":386,"description":387,"displayName":388,"installMethods":389,"rationale":390,"selectedPaths":391,"source":275,"sourceLanguage":18,"type":250},"workflows/plan-mode","Use when the user asks to enter Plan mode, says /prompts:plan or /plan, or wants a structured execution plan written to plan/.","plan-mode",{"claudeCode":12},"SKILL.md frontmatter at workflows/plan-mode/SKILL.md",[392,393],{"path":273,"priority":274},{"path":345,"priority":326},{"basePath":395,"installMethods":396,"rationale":397,"selectedPaths":398,"source":275,"sourceLanguage":18,"type":403},"vg-helper",{"cargo":395},"cli ecosystem detected at vg-helper",[399,401],{"path":400,"priority":274},"Cargo.toml",{"path":402,"priority":326},"src/main.rs","cli",{"sources":405},[406],"manual",{"closedIssues90d":235,"description":408,"forks":236,"homepage":409,"license":242,"openIssues90d":237,"pushedAt":238,"readmeSize":233,"stars":239,"topics":410},"Native rules, hooks, and guards that prevent Claude Code and Codex from hallucinating code, duplicating files, or shipping unverified changes.","https://majiayu000.github.io/vibeguard/",[411,213,412,215,413,414,415,416,214,417,418,419,420,421],"claude-code","codex","guardrails","hooks","agent-harness","ai-agents","anti-hallucination","codex-cli","linter","llm","static-analysis",{"classifiedAt":423,"discoverAt":424,"extractAt":425,"githubAt":425,"updatedAt":423},1778692606860,1778692601876,1778692604872,[214,216,213,215,218,217],{"evaluatedAt":245,"extractAt":428,"updatedAt":429},1778692607327,1778693059223,[],[432,459,483,514,543,574],{"_creationTime":433,"_id":434,"community":435,"display":436,"identity":442,"providers":447,"relations":452,"tags":455,"workflow":456},1778698175626.3276,"k17cj6pbcgtrw523a4sw8mhcxn86mzvv",{"reviewCount":8},{"description":437,"installMethods":438,"name":440,"sourceUrl":441},"Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Use when writing Semgrep rules or building custom static analysis detections.",{"claudeCode":439},"trailofbits/skills","Semgrep Rule Creator","https://github.com/trailofbits/skills",{"basePath":443,"githubOwner":444,"githubRepo":445,"locale":18,"slug":446,"type":250},"plugins/semgrep-rule-creator/skills/semgrep-rule-creator","trailofbits","skills","semgrep-rule-creator",{"evaluate":448,"extract":451},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":449,"targetMarket":219,"tier":220},[450,218,421,213,215],"semgrep",{"commitSha":256},{"parentExtensionId":453,"repoId":454},"k1757483sd0rdv04r5773w2tb986mb9g","kd7d5sbrd9m157hjv9c7v4wfyn86mk2f",[213,215,218,450,421],{"evaluatedAt":457,"extractAt":458,"updatedAt":457},1778699451460,1778698175626,{"_creationTime":460,"_id":461,"community":462,"display":463,"identity":469,"providers":472,"relations":477,"tags":479,"workflow":480},1778695021936.555,"k1715rn9402s29yge55y9nt0x986n2tf",{"reviewCount":8},{"description":464,"installMethods":465,"name":467,"sourceUrl":468},"Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.",{"claudeCode":466},"openai/skills","cli-creator","https://github.com/openai/skills",{"basePath":470,"githubOwner":471,"githubRepo":445,"locale":18,"slug":467,"type":250},"skills/.curated/cli-creator","openai",{"evaluate":473,"extract":476},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":474,"targetMarket":219,"tier":220},[403,216,215,412,475],"automation",{"commitSha":256},{"repoId":478},"kd75n2zj3yh472p25zffgycved86mnpx",[475,403,216,412,215],{"evaluatedAt":481,"extractAt":482,"updatedAt":481},1778695068759,1778695021936,{"_creationTime":484,"_id":485,"community":486,"display":487,"identity":493,"providers":497,"relations":507,"tags":509,"workflow":510},1778693511416.365,"k1758b69g51wttzw4r6epd3jrs86mtk8",{"reviewCount":8},{"description":488,"installMethods":489,"name":491,"sourceUrl":492},"Manage context-mode GitHub issues, PRs, releases, and marketing with parallel subagent army. Orchestrates 10-20 dynamic agents per task. Use when triaging issues, reviewing PRs, releasing versions, writing LinkedIn posts, announcing releases, fixing bugs, merging contributions, validating ENV vars, testing adapters, or syncing branches.",{"claudeCode":490},"mksglu/context-mode","context-mode-ops","https://github.com/mksglu/context-mode",{"basePath":494,"githubOwner":495,"githubRepo":496,"locale":18,"slug":491,"type":250},".claude/skills/context-mode-ops","mksglu","context-mode",{"evaluate":498,"extract":506},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":499,"targetMarket":219,"tier":220},[500,501,502,216,503,504,218,505],"context-window","llm-optimization","session-continuity","developer-tool","productivity","compliance",{"commitSha":256},{"repoId":508},"kd764b2fctbqg4b8j8y6xvmkvs86m29m",[216,505,500,503,501,504,218,502],{"evaluatedAt":511,"extractAt":512,"updatedAt":513},1778693567505,1778693511416,1778693817147,{"_creationTime":515,"_id":516,"community":517,"display":518,"identity":524,"providers":528,"relations":536,"tags":539,"workflow":540},1778696691708.3264,"k179thjzaw5kepc7zhdj9sat3n86mcqp",{"reviewCount":8},{"description":519,"installMethods":520,"name":522,"sourceUrl":523},"Validate pending migrations for foreign key consistency, rollback safety, and best practices",{"claudeCode":521},"ruvnet/ruflo","migrate-validate","https://github.com/ruvnet/ruflo",{"basePath":525,"githubOwner":526,"githubRepo":527,"locale":18,"slug":522,"type":250},"plugins/ruflo-migrations/skills/migrate-validate","ruvnet","ruflo",{"evaluate":529,"extract":535},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":530,"targetMarket":219,"tier":220},[531,532,533,534,213,215],"database","migrations","sql","validation",{"commitSha":256},{"parentExtensionId":537,"repoId":538},"k176me0sh9b6bc3gzttnywx4w986njzh","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[213,531,215,532,533,534],{"evaluatedAt":541,"extractAt":542,"updatedAt":541},1778701008912,1778696691708,{"_creationTime":544,"_id":545,"community":546,"display":547,"identity":553,"providers":559,"relations":566,"tags":569,"workflow":570},1778698296017.8315,"k17dzgrxxkxpeqmtcn5v3tjmad86n5tm",{"reviewCount":8},{"description":548,"installMethods":549,"name":551,"sourceUrl":552},"과잉 엔지니어링 패턴이 감지되면 자동으로 활성화됩니다: (1) 사용자가 명시적으로 변경을 요청하지 않은 코드나 파일을 수정하는 경우 (2) 요청되지 않은 새로운 추상화 레이어(class, interface, factory, wrapper)를 생성하는 경우 (3) 요청되지 않은 주석, 문서, JSDoc, 타입 어노테이션을 추가하는 경우 (4) 요청되지 않은 새로운 의존성을 도입하는 경우 (5) 최소한의 편집 대신 파일 전체를 다시 작성하는 경우 (6) diff 범위가 사용자의 요청을 명백히 초과하는 경우 (7) 사용자가 \"너무 많아\", \"거기는 건드리지 마\", \"X만 변경해\", \"간단하게\", \"그만\" 등의 신호를 보내는 경우 (8) 발생할 수 없는 시나리오에 대한 에러 처리, 유효성 검사, 방어적 코드를 추가하는 경우 (9) 요청되지 않은 테스트, 설정 스캐폴딩, 문서를 생성하는 경우\n",{"claudeCode":550},"uucz/moyu","Moyu (摸鱼)","https://github.com/uucz/moyu",{"basePath":554,"githubOwner":555,"githubRepo":556,"locale":557,"slug":558,"type":250},"skills/moyu-ko","uucz","moyu","ko","moyu-ko",{"evaluate":560,"extract":565},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":561,"targetMarket":219,"tier":220},[562,213,563,215,564],"ai-assist","prompt-engineering","refactoring",{"commitSha":256,"license":242},{"parentExtensionId":567,"repoId":568},"k17a8j7hxkm1n8dabrtcwp2z2d86nr39","kd7ccbpk8y3xm113xt8wy1c5jd86n94h",[562,213,215,563,564],{"evaluatedAt":571,"extractAt":572,"updatedAt":573},1778698415064,1778698296017,1778698589704,{"_creationTime":575,"_id":576,"community":577,"display":578,"identity":584,"providers":588,"relations":593,"tags":596,"workflow":597},1778696595410.5671,"k17anj41t8hgk7k78wc98gw6a186n8ks",{"reviewCount":8},{"description":579,"installMethods":580,"name":582,"sourceUrl":583},"Prevent destructive operations using Claude Code hooks. Three modes — cautious (warn on dangerous commands), lockdown (restrict edits to one directory), and clear (remove restrictions). Uses PreToolUse matchers for Bash, Edit, and Write.",{"claudeCode":581},"rohitg00/pro-workflow","safe-mode","https://github.com/rohitg00/pro-workflow",{"basePath":585,"githubOwner":586,"githubRepo":587,"locale":18,"slug":582,"type":250},"skills/safe-mode","rohitg00","pro-workflow",{"evaluate":589,"extract":592},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":590,"targetMarket":219,"tier":220},[218,413,591,213,414],"operations",{"commitSha":256},{"parentExtensionId":594,"repoId":595},"k17fxtjcfh5gvxdrhv2dmgn1t986mdhv","kd7am4e918eq98hrd9s31jm4vs86nn0b",[213,413,414,591,218],{"evaluatedAt":598,"extractAt":599,"updatedAt":598},1778696971063,1778696595410]