[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-mattpocock-improve-codebase-architecture-en":3,"guides-for-mattpocock-improve-codebase-architecture":580,"similar-k17293vdws6nr5632j9vna0s6h86mz59-en":581},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":243,"isFallback":227,"parentExtension":248,"providers":279,"relations":283,"repo":284,"tags":578,"workflow":579},1778692846401.1484,"k17293vdws6nr5632j9vna0s6h86mz59",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.",{"claudeCode":12},"mattpocock/skills","improve-codebase-architecture","https://github.com/mattpocock/skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":225,"workflow":241},1778693020379.077,"kn75t059j28wnm2bzcqpaev9xx86nmzm","en",{"checks":20,"evaluatedAt":193,"extensionSummary":194,"features":195,"nonGoals":201,"promptVersionExtension":206,"promptVersionScoring":207,"purpose":208,"rationale":209,"score":210,"summary":211,"tags":212,"targetMarket":218,"tier":219,"useCases":220},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,99,103,107,110,113,116,120,123,126,129,132,135,138,142,146,150,153,157,160,163,166,169,173,176,180,183,186,190],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly names a concrete problem: finding deepening opportunities in a codebase to improve architecture, refactoring, module consolidation, and testability, directly addressing user needs.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers a unique approach to architectural improvement by focusing on 'deepening opportunities' and leveraging specific vocabulary from CONTEXT.md and LANGUAGE.md, going beyond generic refactoring advice.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill is designed for workflow integration, guiding the user through exploration, candidate presentation, and a grilling loop, covering a complete lifecycle for architectural improvements.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses on architectural deepening and refactoring opportunities, clearly named and within a coherent workflow, without straying into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description accurately reflects the skill's purpose of identifying architectural friction and proposing deepening opportunities, using domain-specific language effectively.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This skill primarily uses the agent's general exploration capabilities and structured conversations, rather than exposing specific, narrowly-scoped tools.",{"category":45,"check":46,"severity":42,"summary":47},"Documentation","Configuration & parameter reference","The skill does not appear to have explicit configuration parameters or command-line options that require documentation beyond the SKILL.md content.",{"category":33,"check":49,"severity":42,"summary":50},"Tool naming","The skill does not expose user-facing tools or commands with distinct names.",{"category":33,"check":52,"severity":42,"summary":53},"Minimal I/O surface","As this skill primarily uses agent-based exploration and conversational interaction, it does not expose distinct tools with parameter schemas or response shapes.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The MIT license is clearly stated in a dedicated LICENSE file.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The repository shows recent commits, indicating active maintenance.",{"category":59,"check":63,"severity":42,"summary":64},"Dependency Management","The skill does not appear to have third-party dependencies that require explicit management or updating.",{"category":66,"check":67,"severity":42,"summary":68},"Security","Secret Management","The skill does not handle or expose secrets.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill's design focuses on code analysis and conversation, and it does not appear to load or execute untrusted external data.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill does not fetch remote content or include scripts that could be exploited for supply-chain attacks.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill operates within the agent's environment and does not attempt to modify files or paths outside of its designated scope.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","There are no indications of detached-process spawns or deny-retry loops in the skill's execution.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill's purpose is code analysis and conversation, with no mechanisms for exfiltrating data.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled content appears free of hidden-steering tricks or obfuscation characters.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The skill's code and instructions are plain and readable, with no obfuscation techniques detected.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The skill does not appear to make rigid structural assumptions about the user's project layout beyond the typical locations for CONTEXT.md and docs/adr/.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","The ratio of open to closed issues suggests active maintenance and responsiveness from the maintainers.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The repository has recent commit activity and a meaningful versioning signal, indicating it is actively managed.",{"category":104,"check":105,"severity":42,"summary":106},"Code Execution","Validation","The skill relies on conversational interaction and agent tooling, rather than executing arbitrary input arguments or structured output requiring schema validation.",{"category":66,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","The skill is focused on analysis and suggestion, not destructive operations.",{"category":104,"check":111,"severity":24,"summary":112},"Error Handling","The skill's conversational nature and reliance on agent tools mean errors are handled within the agent's framework, not through explicit code exception handling that requires detailed review.",{"category":104,"check":114,"severity":42,"summary":115},"Logging","As this skill relies on agent conversation and code analysis rather than destructive actions or outbound calls, dedicated audit logging is not applicable.",{"category":117,"check":118,"severity":42,"summary":119},"Compliance","GDPR","The skill analyzes code and documentation and does not operate on personal data.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The skill is general-purpose and does not have region-specific logic or constraints, making it globally applicable.",{"category":92,"check":124,"severity":24,"summary":125},"Runtime stability","The skill is designed to work within the agent's environment and does not make assumptions about specific editors, shells, or operating systems.",{"category":45,"check":127,"severity":24,"summary":128},"README","The README file exists, is comprehensive, and clearly articulates the purpose and value of the skills repository.",{"category":33,"check":130,"severity":42,"summary":131},"Tool surface size","This is a skill that operates via conversation and agent tools, not by exposing a discrete set of commands.",{"category":40,"check":133,"severity":42,"summary":134},"Overlapping near-synonym tools","The skill does not expose distinct tools that could have overlapping synonyms.",{"category":45,"check":136,"severity":24,"summary":137},"Phantom features","All advertised capabilities in the README and SKILL.md appear to have corresponding implementations or are part of the skill's conversational design.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","The README provides clear installation instructions using `npx skills@latest add` and a setup command for agent configuration.",{"category":143,"check":144,"severity":42,"summary":145},"Errors","Actionable error messages","Error handling is managed by the underlying agent framework and conversational turns, not explicit error paths within the skill's direct code.",{"category":147,"check":148,"severity":42,"summary":149},"Execution","Pinned dependencies","The skill does not appear to bundle scripts with external dependencies requiring pinning.",{"category":33,"check":151,"severity":42,"summary":152},"Dry-run preview","The skill is analytical and does not perform state-changing operations or send data outward.",{"category":154,"check":155,"severity":42,"summary":156},"Protocol","Idempotent retry & timeouts","The skill's execution relies on the agent's conversational turns and tooling, not direct remote calls requiring explicit idempotency or timeouts.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","There is no indication of telemetry collection within the skill's design or documentation.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The skill's purpose is precisely defined, stating what it does (find deepening opportunities), what it operates on (codebase), and when to use it (improve architecture, refactoring, etc.), with clear boundaries implied by its focus.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The SKILL.md frontmatter is concise and effectively summarizes the core capability and usage context.",{"category":45,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md body is well-structured with clear sections and uses progressive disclosure via linked files, keeping the main document concise.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The skill utilizes progressive disclosure by linking to external files like LANGUAGE.md, DEEPENING.md, and INTERFACE-DESIGN.md for deeper information, avoiding bloat in the main SKILL.md.",{"category":170,"check":174,"severity":42,"summary":175},"Forked exploration","The skill's primary function is code analysis and suggestion, not deep, unbounded exploration that would necessitate a forked context.",{"category":22,"check":177,"severity":178,"summary":179},"Usage examples","info","While the README provides a general installation and setup guide, explicit, ready-to-use examples demonstrating the 'improve-codebase-architecture' skill's input, invocation, and observable output are not present.",{"category":22,"check":181,"severity":24,"summary":182},"Edge cases","The SKILL.md outlines the process and implicitly handles edge cases by guiding the user through exploration and presenting candidates, rather than rigidly defining inputs.",{"category":92,"check":184,"severity":42,"summary":185},"Tool Fallback","This skill does not rely on external tools like MCP servers with fallbacks; it operates within the agent's native environment.",{"category":187,"check":188,"severity":24,"summary":189},"Safety","Halt on unexpected state","The skill's process naturally involves exploration and feedback, inherently halting or redirecting when unexpected states are encountered during codebase analysis.",{"category":92,"check":191,"severity":24,"summary":192},"Cross-skill coupling","The skill is self-contained, focusing on code architecture, and does not implicitly rely on other skills being loaded concurrently.",1778693020043,"This skill analyzes a codebase, guided by domain language and architectural decisions, to identify opportunities for 'deepening' modules. It focuses on improving testability and AI-navigability by proposing refactors that increase module leverage and locality.",[196,197,198,199,200],"Identifies deepening opportunities in codebases","Leverages domain language (CONTEXT.md) and ADRs","Focuses on improving testability and AI-navigability","Guides user through exploration, candidate presentation, and decision refinement","Promotes consistent architectural vocabulary (LANGUAGE.md)",[202,203,204,205],"Performing the refactoring automatically","Suggesting architectural changes that contradict existing ADRs without clear justification","Generating code or interfaces without user input","Replacing developer judgment in architectural decisions","3.0.0","4.4.0","To help developers systematically improve the architecture of their codebase by identifying and addressing architectural friction points, making code more testable and easier for AI to navigate.","High score due to thorough documentation, clear purpose, and robust design. Minor info finding on usage examples prevents perfect score.",97,"A well-documented and focused skill for improving codebase architecture through systematic analysis and guided refactoring.",[213,214,215,216,217],"code-quality","refactoring","architecture","developer-tools","code-analysis","global","verified",[221,222,223,224],"Improving the architecture of a complex or aging codebase","Finding refactoring opportunities to consolidate tightly-coupled modules","Making modules deeper by increasing leverage at their interfaces","Enhancing the testability of critical codebase sections",{"codeQuality":226,"collectedAt":228,"documentation":229,"maintenance":232,"security":238,"testCoverage":240},{"hasLockfile":227},false,1778692998868,{"descriptionLength":230,"readmeSize":231},290,11516,{"closedIssues90d":233,"forks":234,"hasChangelog":227,"openIssues90d":235,"pushedAt":236,"stars":237},117,6767,27,1778677522000,78489,{"hasNpmPackage":227,"license":239,"smitheryVerified":227},"MIT",{"hasCi":227,"hasTests":227},{"updatedAt":242},1778693020379,{"basePath":244,"githubOwner":245,"githubRepo":246,"locale":18,"slug":13,"type":247},"skills/engineering/improve-codebase-architecture","mattpocock","skills","skill",{"_creationTime":249,"_id":250,"community":251,"display":252,"identity":256,"parentExtension":259,"providers":260,"relations":273,"tags":275,"workflow":276},1778692846401.1467,"k171mc92f05dc4v6jzgf6bng7d86mr9t",{"reviewCount":8},{"description":253,"installMethods":254,"name":255,"sourceUrl":14},"Skills for Real Engineers. Straight from my .claude directory.",{"claudeCode":255},"mattpocock-skills",{"basePath":257,"githubOwner":245,"githubRepo":246,"locale":18,"slug":246,"type":258},"","plugin",null,{"evaluate":261,"extract":268},{"promptVersionExtension":206,"promptVersionScoring":207,"score":262,"tags":263,"targetMarket":218,"tier":267},79,[264,265,266,216,213,214],"engineering","productivity","ai-tools","community",{"commitSha":269,"plugin":270},"HEAD",{"mcpCount":8,"provider":271,"skillCount":272},"classify",14,{"repoId":274},"kd70nm2vazehgqc4j28ve6cwv986mv1s",[266,213,216,264,265,214],{"evaluatedAt":277,"extractAt":278,"updatedAt":277},1778692867921,1778692846401,{"evaluate":280,"extract":282},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":281,"targetMarket":218,"tier":219},[213,214,215,216,217],{"commitSha":269},{"parentExtensionId":250,"repoId":274},{"_creationTime":285,"_id":274,"identity":286,"providers":287,"workflow":574},1778692842371.0967,{"githubOwner":245,"githubRepo":246,"sourceUrl":14},{"classify":288,"discover":569,"github":572},{"commitSha":269,"extensions":289},[290,303,312,320,328,336,347,360,371,383,401,419,427,435,447,455,463,471,479,487,497,505,513,521,529,537,545,553,561],{"basePath":257,"displayName":255,"installMethods":291,"rationale":292,"selectedPaths":293,"source":302,"sourceLanguage":18,"type":258},{"claudeCode":255},"plugin manifest at .claude-plugin/plugin.json",[294,297,299],{"path":295,"priority":296},".claude-plugin/plugin.json","mandatory",{"path":298,"priority":296},"README.md",{"path":300,"priority":301},"LICENSE","high","rule",{"basePath":304,"description":305,"displayName":306,"installMethods":307,"rationale":308,"selectedPaths":309,"source":302,"sourceLanguage":18,"type":247},"skills/deprecated/design-an-interface","Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions \"design it twice\".","design-an-interface",{"claudeCode":12},"SKILL.md frontmatter at skills/deprecated/design-an-interface/SKILL.md",[310],{"path":311,"priority":296},"SKILL.md",{"basePath":313,"description":314,"displayName":315,"installMethods":316,"rationale":317,"selectedPaths":318,"source":302,"sourceLanguage":18,"type":247},"skills/deprecated/qa","Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions \"QA session\".","qa",{"claudeCode":12},"SKILL.md frontmatter at skills/deprecated/qa/SKILL.md",[319],{"path":311,"priority":296},{"basePath":321,"description":322,"displayName":323,"installMethods":324,"rationale":325,"selectedPaths":326,"source":302,"sourceLanguage":18,"type":247},"skills/deprecated/request-refactor-plan","Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps.","request-refactor-plan",{"claudeCode":12},"SKILL.md frontmatter at skills/deprecated/request-refactor-plan/SKILL.md",[327],{"path":311,"priority":296},{"basePath":329,"description":330,"displayName":331,"installMethods":332,"rationale":333,"selectedPaths":334,"source":302,"sourceLanguage":18,"type":247},"skills/deprecated/ubiquitous-language","Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions \"domain model\" or \"DDD\".","ubiquitous-language",{"claudeCode":12},"SKILL.md frontmatter at skills/deprecated/ubiquitous-language/SKILL.md",[335],{"path":311,"priority":296},{"basePath":337,"description":338,"displayName":339,"installMethods":340,"rationale":341,"selectedPaths":342,"source":302,"sourceLanguage":18,"type":247},"skills/engineering/diagnose","Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says \"diagnose this\" / \"debug this\", reports a bug, says something is broken/throwing/failing, or describes a performance regression.","diagnose",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/diagnose/SKILL.md",[343,344],{"path":311,"priority":296},{"path":345,"priority":346},"scripts/hitl-loop.template.sh","low",{"basePath":348,"description":349,"displayName":350,"installMethods":351,"rationale":352,"selectedPaths":353,"source":302,"sourceLanguage":18,"type":247},"skills/engineering/grill-with-docs","Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.","grill-with-docs",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/grill-with-docs/SKILL.md",[354,355,358],{"path":311,"priority":296},{"path":356,"priority":357},"ADR-FORMAT.md","medium",{"path":359,"priority":357},"CONTEXT-FORMAT.md",{"basePath":244,"description":10,"displayName":13,"installMethods":361,"rationale":362,"selectedPaths":363,"source":302,"sourceLanguage":18,"type":247},{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/improve-codebase-architecture/SKILL.md",[364,365,367,369],{"path":311,"priority":296},{"path":366,"priority":357},"DEEPENING.md",{"path":368,"priority":357},"INTERFACE-DESIGN.md",{"path":370,"priority":357},"LANGUAGE.md",{"basePath":372,"description":373,"displayName":374,"installMethods":375,"rationale":376,"selectedPaths":377,"source":302,"sourceLanguage":18,"type":247},"skills/engineering/prototype","Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says \"prototype this\", \"let me play with it\", \"try a few designs\".","prototype",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/prototype/SKILL.md",[378,379,381],{"path":311,"priority":296},{"path":380,"priority":357},"LOGIC.md",{"path":382,"priority":357},"UI.md",{"basePath":384,"description":385,"displayName":386,"installMethods":387,"rationale":388,"selectedPaths":389,"source":302,"sourceLanguage":18,"type":247},"skills/engineering/setup-matt-pocock-skills","Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.","setup-matt-pocock-skills",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/setup-matt-pocock-skills/SKILL.md",[390,391,393,395,397,399],{"path":311,"priority":296},{"path":392,"priority":357},"domain.md",{"path":394,"priority":357},"issue-tracker-github.md",{"path":396,"priority":357},"issue-tracker-gitlab.md",{"path":398,"priority":357},"issue-tracker-local.md",{"path":400,"priority":357},"triage-labels.md",{"basePath":402,"description":403,"displayName":404,"installMethods":405,"rationale":406,"selectedPaths":407,"source":302,"sourceLanguage":18,"type":247},"skills/engineering/tdd","Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions \"red-green-refactor\", wants integration tests, or asks for test-first development.","tdd",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/tdd/SKILL.md",[408,409,411,413,415,417],{"path":311,"priority":296},{"path":410,"priority":357},"deep-modules.md",{"path":412,"priority":357},"interface-design.md",{"path":414,"priority":357},"mocking.md",{"path":416,"priority":357},"refactoring.md",{"path":418,"priority":357},"tests.md",{"basePath":420,"description":421,"displayName":422,"installMethods":423,"rationale":424,"selectedPaths":425,"source":302,"sourceLanguage":18,"type":247},"skills/engineering/to-issues","Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.","to-issues",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/to-issues/SKILL.md",[426],{"path":311,"priority":296},{"basePath":428,"description":429,"displayName":430,"installMethods":431,"rationale":432,"selectedPaths":433,"source":302,"sourceLanguage":18,"type":247},"skills/engineering/to-prd","Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.","to-prd",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/to-prd/SKILL.md",[434],{"path":311,"priority":296},{"basePath":436,"description":437,"displayName":438,"installMethods":439,"rationale":440,"selectedPaths":441,"source":302,"sourceLanguage":18,"type":247},"skills/engineering/triage","Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.","triage",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/triage/SKILL.md",[442,443,445],{"path":311,"priority":296},{"path":444,"priority":357},"AGENT-BRIEF.md",{"path":446,"priority":357},"OUT-OF-SCOPE.md",{"basePath":448,"description":449,"displayName":450,"installMethods":451,"rationale":452,"selectedPaths":453,"source":302,"sourceLanguage":18,"type":247},"skills/engineering/zoom-out","Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.","zoom-out",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/zoom-out/SKILL.md",[454],{"path":311,"priority":296},{"basePath":456,"description":457,"displayName":458,"installMethods":459,"rationale":460,"selectedPaths":461,"source":302,"sourceLanguage":18,"type":247},"skills/in-progress/review","Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".","review",{"claudeCode":12},"SKILL.md frontmatter at skills/in-progress/review/SKILL.md",[462],{"path":311,"priority":296},{"basePath":464,"description":465,"displayName":466,"installMethods":467,"rationale":468,"selectedPaths":469,"source":302,"sourceLanguage":18,"type":247},"skills/in-progress/writing-beats","Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.","writing-beats",{"claudeCode":12},"SKILL.md frontmatter at skills/in-progress/writing-beats/SKILL.md",[470],{"path":311,"priority":296},{"basePath":472,"description":473,"displayName":474,"installMethods":475,"rationale":476,"selectedPaths":477,"source":302,"sourceLanguage":18,"type":247},"skills/in-progress/writing-fragments","Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions \"fragments\", \"ideate\", or \"raw material\" for writing.","writing-fragments",{"claudeCode":12},"SKILL.md frontmatter at skills/in-progress/writing-fragments/SKILL.md",[478],{"path":311,"priority":296},{"basePath":480,"description":481,"displayName":482,"installMethods":483,"rationale":484,"selectedPaths":485,"source":302,"sourceLanguage":18,"type":247},"skills/in-progress/writing-shape","Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.","writing-shape",{"claudeCode":12},"SKILL.md frontmatter at skills/in-progress/writing-shape/SKILL.md",[486],{"path":311,"priority":296},{"basePath":488,"description":489,"displayName":490,"installMethods":491,"rationale":492,"selectedPaths":493,"source":302,"sourceLanguage":18,"type":247},"skills/misc/git-guardrails-claude-code","Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.","git-guardrails-claude-code",{"claudeCode":12},"SKILL.md frontmatter at skills/misc/git-guardrails-claude-code/SKILL.md",[494,495],{"path":311,"priority":296},{"path":496,"priority":346},"scripts/block-dangerous-git.sh",{"basePath":498,"description":499,"displayName":500,"installMethods":501,"rationale":502,"selectedPaths":503,"source":302,"sourceLanguage":18,"type":247},"skills/misc/migrate-to-shoehorn","Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.","migrate-to-shoehorn",{"claudeCode":12},"SKILL.md frontmatter at skills/misc/migrate-to-shoehorn/SKILL.md",[504],{"path":311,"priority":296},{"basePath":506,"description":507,"displayName":508,"installMethods":509,"rationale":510,"selectedPaths":511,"source":302,"sourceLanguage":18,"type":247},"skills/misc/scaffold-exercises","Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.","scaffold-exercises",{"claudeCode":12},"SKILL.md frontmatter at skills/misc/scaffold-exercises/SKILL.md",[512],{"path":311,"priority":296},{"basePath":514,"description":515,"displayName":516,"installMethods":517,"rationale":518,"selectedPaths":519,"source":302,"sourceLanguage":18,"type":247},"skills/misc/setup-pre-commit","Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.","setup-pre-commit",{"claudeCode":12},"SKILL.md frontmatter at skills/misc/setup-pre-commit/SKILL.md",[520],{"path":311,"priority":296},{"basePath":522,"description":523,"displayName":524,"installMethods":525,"rationale":526,"selectedPaths":527,"source":302,"sourceLanguage":18,"type":247},"skills/personal/edit-article","Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.","edit-article",{"claudeCode":12},"SKILL.md frontmatter at skills/personal/edit-article/SKILL.md",[528],{"path":311,"priority":296},{"basePath":530,"description":531,"displayName":532,"installMethods":533,"rationale":534,"selectedPaths":535,"source":302,"sourceLanguage":18,"type":247},"skills/personal/obsidian-vault","Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.","obsidian-vault",{"claudeCode":12},"SKILL.md frontmatter at skills/personal/obsidian-vault/SKILL.md",[536],{"path":311,"priority":296},{"basePath":538,"description":539,"displayName":540,"installMethods":541,"rationale":542,"selectedPaths":543,"source":302,"sourceLanguage":18,"type":247},"skills/productivity/caveman","Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says \"caveman mode\", \"talk like caveman\", \"use caveman\", \"less tokens\", \"be brief\", or invokes /caveman.\n","caveman",{"claudeCode":12},"SKILL.md frontmatter at skills/productivity/caveman/SKILL.md",[544],{"path":311,"priority":296},{"basePath":546,"description":547,"displayName":548,"installMethods":549,"rationale":550,"selectedPaths":551,"source":302,"sourceLanguage":18,"type":247},"skills/productivity/grill-me","Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions \"grill me\".","grill-me",{"claudeCode":12},"SKILL.md frontmatter at skills/productivity/grill-me/SKILL.md",[552],{"path":311,"priority":296},{"basePath":554,"description":555,"displayName":556,"installMethods":557,"rationale":558,"selectedPaths":559,"source":302,"sourceLanguage":18,"type":247},"skills/productivity/handoff","Compact the current conversation into a handoff document for another agent to pick up.","handoff",{"claudeCode":12},"SKILL.md frontmatter at skills/productivity/handoff/SKILL.md",[560],{"path":311,"priority":296},{"basePath":562,"description":563,"displayName":564,"installMethods":565,"rationale":566,"selectedPaths":567,"source":302,"sourceLanguage":18,"type":247},"skills/productivity/write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.","write-a-skill",{"claudeCode":12},"SKILL.md frontmatter at skills/productivity/write-a-skill/SKILL.md",[568],{"path":311,"priority":296},{"sources":570},[571],"manual",{"closedIssues90d":233,"description":253,"forks":234,"license":239,"openIssues90d":235,"pushedAt":236,"readmeSize":231,"stars":237,"topics":573},[],{"classifiedAt":575,"discoverAt":576,"extractAt":577,"githubAt":577,"updatedAt":575},1778692846116,1778692842371,1778692844195,[215,217,213,216,214],{"evaluatedAt":242,"extractAt":278,"updatedAt":242},[],[582,612,642,669,696,724],{"_creationTime":583,"_id":584,"community":585,"display":586,"identity":592,"providers":597,"relations":605,"tags":607,"workflow":608},1778698056313.1528,"k176pxdjxvnyex7jv6abt3myd586n5vv",{"reviewCount":8},{"description":587,"installMethods":588,"name":590,"sourceUrl":591},"Map a codebase into feature-grouped flowcharts, identify duplicated concerns across features, and propose a unified architecture. Use when asked to \"find the ideal path,\" unify duplicated systems, or audit architecture before a refactor. Emits a proposed unified flowchart plus per-system /make-plan prompts.",{"claudeCode":589},"thedotmack/claude-mem","Pathfinder","https://github.com/thedotmack/claude-mem",{"basePath":593,"githubOwner":594,"githubRepo":595,"locale":18,"slug":596,"type":247},"plugin/skills/pathfinder","thedotmack","claude-mem","pathfinder",{"evaluate":598,"extract":603},{"promptVersionExtension":206,"promptVersionScoring":207,"score":599,"tags":600,"targetMarket":218,"tier":219},100,[217,215,601,214,602],"documentation","flowchart",{"commitSha":269,"license":604},"Apache-2.0",{"repoId":606},"kd70jnxgm695az2wtf37zbqdj986mp7k",[215,217,601,602,214],{"evaluatedAt":609,"extractAt":610,"updatedAt":611},1778698228002,1778698056313,1778698443446,{"_creationTime":613,"_id":614,"community":615,"display":616,"identity":622,"providers":628,"relations":634,"tags":637,"workflow":638},1778698296017.8315,"k17dzgrxxkxpeqmtcn5v3tjmad86n5tm",{"reviewCount":8},{"description":617,"installMethods":618,"name":620,"sourceUrl":621},"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":619},"uucz/moyu","Moyu (摸鱼)","https://github.com/uucz/moyu",{"basePath":623,"githubOwner":624,"githubRepo":625,"locale":626,"slug":627,"type":247},"skills/moyu-ko","uucz","moyu","ko","moyu-ko",{"evaluate":629,"extract":633},{"promptVersionExtension":206,"promptVersionScoring":207,"score":599,"tags":630,"targetMarket":218,"tier":219},[631,213,632,216,214],"ai-assist","prompt-engineering",{"commitSha":269,"license":239},{"parentExtensionId":635,"repoId":636},"k17a8j7hxkm1n8dabrtcwp2z2d86nr39","kd7ccbpk8y3xm113xt8wy1c5jd86n94h",[631,213,216,632,214],{"evaluatedAt":639,"extractAt":640,"updatedAt":641},1778698415064,1778698296017,1778698589704,{"_creationTime":643,"_id":644,"community":645,"display":646,"identity":652,"providers":656,"relations":663,"tags":665,"workflow":666},1778696691708.3062,"k178rt0mhkwtjj1axhgtt0tfth86mt09",{"reviewCount":8},{"description":647,"installMethods":648,"name":650,"sourceUrl":651},"Domain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern.",{"claudeCode":649},"ruvnet/ruflo","v3-ddd-architecture","https://github.com/ruvnet/ruflo",{"basePath":653,"githubOwner":654,"githubRepo":655,"locale":18,"slug":650,"type":247},".claude/skills/v3-ddd-architecture","ruvnet","ruflo",{"evaluate":657,"extract":662},{"promptVersionExtension":206,"promptVersionScoring":207,"score":599,"tags":658,"targetMarket":218,"tier":219},[659,215,214,660,661],"ddd","clean-architecture","typescript",{"commitSha":269},{"repoId":664},"kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[215,660,659,214,661],{"evaluatedAt":667,"extractAt":668,"updatedAt":667},1778699412094,1778696691708,{"_creationTime":670,"_id":671,"community":672,"display":673,"identity":679,"providers":683,"relations":689,"tags":691,"workflow":692},1778692549705.5164,"k17cmt6ekj6t5bf5dbscrqa3an86m6p3",{"reviewCount":8},{"description":674,"installMethods":675,"name":677,"sourceUrl":678},"Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships",{"claudeCode":676},"Lum1104/Understand-Anything","understand","https://github.com/Lum1104/Understand-Anything",{"basePath":680,"githubOwner":681,"githubRepo":682,"locale":18,"slug":677,"type":247},"understand-anything-plugin/skills/understand","Lum1104","Understand-Anything",{"evaluate":684,"extract":688},{"promptVersionExtension":206,"promptVersionScoring":207,"score":599,"tags":685,"targetMarket":218,"tier":219},[217,686,216,215,687],"knowledge-graph","code-exploration",{"commitSha":269},{"repoId":690},"kd78egfytykkxxbpr6k3t7wsph86n83x",[215,217,687,216,686],{"evaluatedAt":693,"extractAt":694,"updatedAt":695},1778692606129,1778692549705,1778692824891,{"_creationTime":697,"_id":698,"community":699,"display":700,"identity":706,"providers":709,"relations":717,"tags":719,"workflow":720},1778699438912.8826,"k170fxxh22hdspg4vr94whgj1986mpr9",{"reviewCount":8},{"description":701,"installMethods":702,"name":704,"sourceUrl":705},"Context Runtime for AI Agents — 59 MCP tools, 10 read modes, 95+ shell patterns, tree-sitter AST for 18 languages. Compresses LLM context by up to 99%. Use when reading files, running shell commands, searching code, or exploring directories. Auto-installs if not present.",{"claudeCode":703},"yvgude/lean-ctx","lean-ctx","https://github.com/yvgude/lean-ctx",{"basePath":707,"githubOwner":708,"githubRepo":704,"locale":18,"slug":704,"type":247},"skills/lean-ctx","yvgude",{"evaluate":710,"extract":716},{"promptVersionExtension":206,"promptVersionScoring":207,"score":599,"tags":711,"targetMarket":218,"tier":219},[712,713,714,216,715,217],"context-compression","ai-agent","cli-tools","rust",{"commitSha":269},{"repoId":718},"kd7dxtfr9j3z54hs3bz0218e1n86may0",[713,714,217,712,216,715],{"evaluatedAt":721,"extractAt":722,"updatedAt":723},1778699456179,1778699438912,1778699517795,{"_creationTime":725,"_id":726,"community":727,"display":728,"identity":732,"providers":734,"relations":742,"tags":744,"workflow":745},1778696691708.3264,"k179thjzaw5kepc7zhdj9sat3n86mcqp",{"reviewCount":8},{"description":729,"installMethods":730,"name":731,"sourceUrl":651},"Validate pending migrations for foreign key consistency, rollback safety, and best practices",{"claudeCode":649},"migrate-validate",{"basePath":733,"githubOwner":654,"githubRepo":655,"locale":18,"slug":731,"type":247},"plugins/ruflo-migrations/skills/migrate-validate",{"evaluate":735,"extract":741},{"promptVersionExtension":206,"promptVersionScoring":207,"score":599,"tags":736,"targetMarket":218,"tier":219},[737,738,739,740,213,216],"database","migrations","sql","validation",{"commitSha":269},{"parentExtensionId":743,"repoId":664},"k176me0sh9b6bc3gzttnywx4w986njzh",[213,737,216,738,739,740],{"evaluatedAt":746,"extractAt":668,"updatedAt":746},1778701008912]