[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-ckorhonen-capture-knowledge-en":3,"guides-for-ckorhonen-capture-knowledge":477,"similar-k17ev60xfqgtzpxcffcecxmfb986mvqp-en":478},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":240,"isFallback":232,"parentExtension":245,"providers":267,"relations":271,"repo":272,"tags":475,"workflow":476},1778683790179.7793,"k17ev60xfqgtzpxcffcecxmfb986mvqp",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Audits a repository's code and docs to find important conventions, workflows, and architectural decisions that are missing from agent-facing guidance, then drafts review-ready updates. Use when a user says `capture repo knowledge`, `document implicit conventions`, `turn repo patterns into agent rules`, or asks what future agents should remember about a codebase. Do NOT use for a generic repo tour, onboarding walkthrough, or architecture summary that does not need reusable guidance updates.",{"claudeCode":12},"ckorhonen/swe-skills","capture-knowledge","https://github.com/ckorhonen/swe-skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":224,"workflow":238},1778683858983.8433,"kn75zer2gcnmz4m37hcq242pe586nc4j","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"promptVersionExtension":205,"promptVersionScoring":206,"purpose":207,"rationale":208,"score":209,"summary":210,"tags":211,"targetMarket":217,"tier":218,"useCases":219},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,99,103,107,110,113,116,120,123,126,129,132,135,138,142,146,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of missing agent-facing guidance for repo conventions and workflows, with specific use cases and non-goals.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill uniquely audits existing guidance against repo reality to identify and draft missing knowledge, offering significant value beyond standard summarization or documentation.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill is designed for real workflows, covering the full lifecycle from inspection to drafting and pausing for review, with clear inputs and output requirements.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses on a single, well-defined task: capturing and drafting missing repo conventions for agent guidance.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description accurately reflects the skill's functionality, providing clear use cases and explicit non-goals.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This skill does not expose specific tools; it is a single-purpose prompt-based skill.",{"category":45,"check":46,"severity":42,"summary":47},"Documentation","Configuration & parameter reference","The skill does not appear to have configurable parameters beyond its core function and inputs specified in the documentation.",{"category":33,"check":49,"severity":42,"summary":50},"Tool naming","This is a single-purpose skill and does not expose multiple tools with distinct names.",{"category":33,"check":52,"severity":42,"summary":53},"Minimal I/O surface","As a skill, its I/O is conversational and defined by the prompt, not explicit tool schemas.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The extension is licensed under the MIT license, which is a permissive open-source license.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The latest commit was on May 9, 2026, which is within the last 90 days.",{"category":59,"check":63,"severity":42,"summary":64},"Dependency Management","The skill does not appear to use third-party dependencies directly.",{"category":66,"check":67,"severity":24,"summary":68},"Security","Secret Management","The skill's described function does not involve handling secrets.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill's documented process involves analyzing existing code and documentation, not executing untrusted external data as instructions.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill operates on the local codebase and documentation, with no indication of runtime network fetches for instructions.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill's documented workflow focuses on analysis and drafting, with no indication of modifying files outside the project scope.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","No detached process spawns or denial-retry loops are suggested by the skill's description or documented workflow.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill's purpose is to analyze local code and documentation; there are no instructions for submitting confidential data to a third party.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled markdown files appear to be free of hidden steering tricks or obfuscated content.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The skill's implementation relies on analysis and drafting, not opaque code execution.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The skill relies on a local repository checkout and standard tools, but its documentation frames these as prerequisites rather than assumptions of a specific project structure.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","There are no open issues in the last 90 days, and no closed issues in the last 90 days, indicating low recent activity but no unresolved issues.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The repository shows recent commits, and while there isn't a formal versioning scheme like semver or CHANGELOG, the install instruction points to a specific commit, implying versioning.",{"category":104,"check":105,"severity":42,"summary":106},"Code Execution","Validation","The skill does not expose executable code or structured output that requires schema validation beyond conversational input.",{"category":66,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","The skill's primary function is drafting and review, with no destructive operations described.",{"category":104,"check":111,"severity":24,"summary":112},"Error Handling","The skill's workflow is designed to halt and report when faced with ambiguity or missing information, rather than proceeding with unverified data.",{"category":104,"check":114,"severity":42,"summary":115},"Logging","As a skill operating within the agent's conversational context, dedicated audit logging is not applicable.",{"category":117,"check":118,"severity":24,"summary":119},"Compliance","GDPR","The skill analyzes code and documentation and does not appear to operate on personal data.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The skill's function is globally applicable and does not have regional or jurisdictional limitations.",{"category":92,"check":124,"severity":24,"summary":125},"Runtime stability","The skill relies on standard repository access and tools, with compatibility notes indicating it works best with common repo discovery tools.",{"category":45,"check":127,"severity":24,"summary":128},"README","The README file exists and provides a good overview of the repository's structure, conventions, and development workflow.",{"category":33,"check":130,"severity":42,"summary":131},"Tool surface size","This is a single-purpose skill, not an extension with multiple tools.",{"category":40,"check":133,"severity":42,"summary":134},"Overlapping near-synonym tools","As a single-purpose skill, there are no overlapping tools.",{"category":45,"check":136,"severity":24,"summary":137},"Phantom features","All advertised features in the README and SKILL.md correspond to the described functionality.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","The README provides clear installation instructions using `npx` and an example invocation.",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","The skill's documentation indicates it will report on ambiguous evidence or missing scope, implying actionable error reporting.",{"category":147,"check":148,"severity":42,"summary":149},"Execution","Pinned dependencies","The skill does not directly manage third-party dependencies in a way that requires pinning.",{"category":33,"check":151,"severity":24,"summary":152},"Dry-run preview","The skill explicitly states it pauses for review before writing, serving as a form of dry-run.",{"category":154,"check":155,"severity":42,"summary":156},"Protocol","Idempotent retry & timeouts","The skill operates conversationally and does not involve remote calls or state-changing operations requiring idempotency or timeouts.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","There is no indication of telemetry collection; the skill operates locally on provided context.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The skill's purpose is precisely defined, stating what it does (audits repo, drafts guidance) and when to use it (capture repo knowledge, document conventions) with clear non-goals.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter is concise, clearly stating the skill's core capability and providing relevant trigger phrases.",{"category":45,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is well-structured and reasonably concise, outlining the workflow and delegating deeper details implicitly to the codebase.",{"category":170,"check":171,"severity":42,"summary":172},"Context","Progressive Disclosure","The skill's workflow is described inline and is not overly complex, negating the need for extensive progressive disclosure via separate files.",{"category":170,"check":174,"severity":42,"summary":175},"Forked exploration","The skill's primary function is analysis and drafting, not deep code exploration that would necessitate a forked context.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","Sufficient examples are provided, illustrating user prompts and expected actions, which plausibly lead to the claimed outcomes.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The documentation addresses potential edge cases such as ambiguous evidence and user requests for immediate write-back, providing guidance on how to handle them.",{"category":104,"check":183,"severity":42,"summary":184},"Tool Fallback","This skill does not rely on external tools like MCP servers; it operates within the agent's native environment.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The skill's instructions emphasize pausing for review and reporting on ambiguity, implying it halts on unexpected states rather than proceeding blindly.",{"category":92,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill is self-contained and does not appear to rely on other specific skills being loaded concurrently.",1778683858443,"This skill audits a repository's code and documentation to identify conventions, workflows, and architectural decisions that are not present in existing agent-facing guidance. It then drafts review-ready updates based on concrete evidence found in the codebase.",[195,196,197,198,199],"Audits repo conventions and architectural decisions","Compares repo reality to existing agent guidance","Identifies and drafts missing knowledge gaps","Creates review-ready update packets","Pauses for explicit user review before saving",[201,202,203,204],"Generic repo orientation reports","Broad architecture reviews without guidance updates","Human-facing documentation rewrite","Automatic write-back without explicit review","3.0.0","4.4.0","To convert implicit knowledge within a codebase into explicit, reusable guidance for AI agents, ensuring they can reliably understand and adhere to repository conventions and decisions.","The skill is well-documented, has a clear purpose, and follows best practices for prompt-based extensions, with no significant warnings or critical findings.",96,"High-quality skill for capturing and drafting missing repo conventions for agent guidance.",[212,213,214,215,216],"code-analysis","documentation","knowledge-capture","agent-guidance","code-review","global","verified",[220,221,222,223],"Capture undocumented repo conventions","Turn repeated implementation patterns into reusable agent guidance","Find what current rules or skills are missing","Draft agent-facing guidance updates before saving",{"codeQuality":225,"collectedAt":227,"documentation":228,"maintenance":231,"security":235,"testCoverage":237},{"hasLockfile":226},true,1778683840097,{"descriptionLength":229,"readmeSize":230},494,8683,{"closedIssues90d":8,"forks":8,"hasChangelog":232,"openIssues90d":8,"pushedAt":233,"stars":234},false,1778361321000,1,{"hasNpmPackage":232,"license":236,"smitheryVerified":232},"MIT",{"hasCi":226,"hasTests":232},{"updatedAt":239},1778683858983,{"basePath":241,"githubOwner":242,"githubRepo":243,"locale":18,"slug":13,"type":244},"skills/capture-knowledge","ckorhonen","swe-skills","skill",{"_creationTime":246,"_id":247,"community":248,"display":249,"identity":252,"parentExtension":255,"providers":256,"relations":262,"tags":264,"workflow":265},1778683790179.7788,"k17d2yq229g61qvea0x8t60w1h86mgr8",{"reviewCount":8},{"description":250,"installMethods":251,"name":243,"sourceUrl":14},"17 agent skills for engineering analysis and judgment — PR risk review, repo introspection, audits, ownership maps, refactor opportunities. See https://cdd.dev/skill/.",{"claudeCode":243},{"basePath":253,"githubOwner":242,"githubRepo":243,"locale":18,"slug":243,"type":254},"","plugin",null,{"extract":257},{"commitSha":258,"plugin":259},"HEAD",{"mcpCount":8,"provider":260,"skillCount":261},"classify",17,{"repoId":263},"kd7b5kvzw3q7dgvym5bdx3m53986mann",[],{"extractAt":266,"updatedAt":266},1778683790179,{"evaluate":268,"extract":270},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":269,"targetMarket":217,"tier":218},[212,213,214,215,216],{"commitSha":258},{"parentExtensionId":247,"repoId":263},{"_creationTime":273,"_id":263,"identity":274,"providers":275,"workflow":471},1778683785537.182,{"githubOwner":242,"githubRepo":243,"sourceUrl":14},{"classify":276,"discover":460,"github":463},{"commitSha":258,"extensions":277},[278,326,335,340,348,356,364,372,380,388,396,404,412,420,428,436,444,452],{"basePath":253,"description":250,"displayName":243,"installMethods":279,"rationale":280,"selectedPaths":281,"source":325,"sourceLanguage":18,"type":254},{"claudeCode":243},"plugin manifest at .claude-plugin/plugin.json",[282,285,287,290,293,295,297,299,301,303,305,307,309,311,313,315,317,319,321,323],{"path":283,"priority":284},".claude-plugin/plugin.json","mandatory",{"path":286,"priority":284},"README.md",{"path":288,"priority":289},"LICENSE","high",{"path":291,"priority":292},"skills/babysit-pr/SKILL.md","medium",{"path":294,"priority":292},"skills/capture-knowledge/SKILL.md",{"path":296,"priority":292},"skills/change-validation-planner/SKILL.md",{"path":298,"priority":292},"skills/create-skill/SKILL.md",{"path":300,"priority":292},"skills/docs-drift-audit/SKILL.md",{"path":302,"priority":292},"skills/incident-followup-audit/SKILL.md",{"path":304,"priority":292},"skills/init/SKILL.md",{"path":306,"priority":292},"skills/merged-pr-monitoring/SKILL.md",{"path":308,"priority":292},"skills/observability-gap-hunt/SKILL.md",{"path":310,"priority":292},"skills/ownership-risk-map/SKILL.md",{"path":312,"priority":292},"skills/performance-hunt/SKILL.md",{"path":314,"priority":292},"skills/pr-risk-review/SKILL.md",{"path":316,"priority":292},"skills/recent-commit-bug-hunt/SKILL.md",{"path":318,"priority":292},"skills/refactor-opportunities/SKILL.md",{"path":320,"priority":292},"skills/repo-introspection/SKILL.md",{"path":322,"priority":292},"skills/security-audit/SKILL.md",{"path":324,"priority":292},"skills/test-gap-hunt/SKILL.md","rule",{"basePath":327,"description":328,"displayName":329,"installMethods":330,"rationale":331,"selectedPaths":332,"source":325,"sourceLanguage":18,"type":244},"skills/babysit-pr","Babysits an open pull request end-to-end by polling every minute, triaging new comments and reviews, handling CI failures, iterating on reviewer scores, and stopping only when the PR is ready to merge. Use when a user says `babysit this PR`, `watch this PR until it's merge-ready`, `handle review feedback on my PR`, or `keep iterating on this PR until reviewers are happy`. Do NOT use for a one-shot PR risk review, merged PR production monitoring, or repo-wide CI debugging with no scoped PR.","babysit-pr",{"claudeCode":12},"SKILL.md frontmatter at skills/babysit-pr/SKILL.md",[333],{"path":334,"priority":284},"SKILL.md",{"basePath":241,"description":10,"displayName":13,"installMethods":336,"rationale":337,"selectedPaths":338,"source":325,"sourceLanguage":18,"type":244},{"claudeCode":12},"SKILL.md frontmatter at skills/capture-knowledge/SKILL.md",[339],{"path":334,"priority":284},{"basePath":341,"description":342,"displayName":343,"installMethods":344,"rationale":345,"selectedPaths":346,"source":325,"sourceLanguage":18,"type":244},"skills/change-validation-planner","Plans the narrowest trustworthy validation path for a scoped code change or diff. Use when a user asks what to run before merging, how to validate a specific change, whether the current checks are enough, or wants a bounded command order from narrow to broad. Do NOT use for writing tests, fixing the code change itself, broad QA sweeps, or generic debugging that needs root cause analysis.","change-validation-planner",{"claudeCode":12},"SKILL.md frontmatter at skills/change-validation-planner/SKILL.md",[347],{"path":334,"priority":284},{"basePath":349,"description":350,"displayName":351,"installMethods":352,"rationale":353,"selectedPaths":354,"source":325,"sourceLanguage":18,"type":244},"skills/create-skill","Creates or revises `swe:` skills for this repository using a repeatable authoring workflow: define concrete use cases, tune trigger boundaries, apply progressive disclosure, add matching eval assets, and validate the package. Use when adding a new skill, tightening an existing skill that over- or under-triggers, or distilling an external workflow into a repo-ready skill. Do NOT use for generic documentation edits or for executing the workflow the skill would describe.","create-skill",{"claudeCode":12},"SKILL.md frontmatter at skills/create-skill/SKILL.md",[355],{"path":334,"priority":284},{"basePath":357,"description":358,"displayName":359,"installMethods":360,"rationale":361,"selectedPaths":362,"source":325,"sourceLanguage":18,"type":244},"skills/docs-drift-audit","Audits a repository for human-facing or operational documentation that drifted from code, config, interfaces, workflows, or repo structure changes. Use when a user says `check docs drift`, `docs are stale`, `update the runbook after this change`, or `what documentation is missing after this change`. Do NOT use for agent-guidance updates, generic documentation rewrites, or writing docs without evidence that they are stale.","docs-drift-audit",{"claudeCode":12},"SKILL.md frontmatter at skills/docs-drift-audit/SKILL.md",[363],{"path":334,"priority":284},{"basePath":365,"description":366,"displayName":367,"installMethods":368,"rationale":369,"selectedPaths":370,"source":325,"sourceLanguage":18,"type":244},"skills/incident-followup-audit","Audits post-incident engineering follow-through after a sev or incident to verify whether the durable follow-up happened: regression tests, monitors, docs, runbooks, ownership updates, tickets, rollback learnings, and remaining backlog. Use when a user asks whether incident follow-up is complete, what still needs to be done after a postmortem, or how to close the engineering loop. Do NOT use for live incident response, root-cause analysis, or a generic bug hunt unrelated to an incident.","incident-followup-audit",{"claudeCode":12},"SKILL.md frontmatter at skills/incident-followup-audit/SKILL.md",[371],{"path":334,"priority":284},{"basePath":373,"description":374,"displayName":375,"installMethods":376,"rationale":377,"selectedPaths":378,"source":325,"sourceLanguage":18,"type":244},"skills/init","Initializes an optional repo-local agent collaboration preference file at `.ai/swe.json` by running a short interview or a zero-question quick mode. Use when a user says `initialize agent settings for this repo`, `set up my local agent prefs here`, `run quick init for this project`, or `create .ai/swe.json for how I like to work`. Do NOT use for `npm init`, project scaffolding, dependency installation, or environment bootstrap.","init",{"claudeCode":12},"SKILL.md frontmatter at skills/init/SKILL.md",[379],{"path":334,"priority":284},{"basePath":381,"description":382,"displayName":383,"installMethods":384,"rationale":385,"selectedPaths":386,"source":325,"sourceLanguage":18,"type":244},"skills/merged-pr-monitoring","Reviews recently merged pull requests, confirms whether they reached production, compares pre- and post-deploy signals, and summarizes observable impact. Use when a user says `monitor merged PRs`, `did this deploy hurt prod`, `check production impact of yesterday's merges`, or asks for a post-deploy readout tied to merged GitHub PRs. Do NOT use for a pre-merge code review, incident analysis with no PR scope, or generic dashboard triage disconnected from merged changes.","merged-pr-monitoring",{"claudeCode":12},"SKILL.md frontmatter at skills/merged-pr-monitoring/SKILL.md",[387],{"path":334,"priority":284},{"basePath":389,"description":390,"displayName":391,"installMethods":392,"rationale":393,"selectedPaths":394,"source":325,"sourceLanguage":18,"type":244},"skills/observability-gap-hunt","Inspects services, jobs, and code paths for missing or weak logs, metrics, traces, alerts, dashboards, or deployment-linked telemetry, then returns a tightly scoped backlog of observability gaps. Use when a user says `find observability gaps`, `audit telemetry coverage`, `what logs or metrics are missing`, `check alerting coverage`, or asks for a recurring telemetry review. Do NOT use for live incident response, root-cause analysis, generic performance tuning, or a broad code review.","observability-gap-hunt",{"claudeCode":12},"SKILL.md frontmatter at skills/observability-gap-hunt/SKILL.md",[395],{"path":334,"priority":284},{"basePath":397,"description":398,"displayName":399,"installMethods":400,"rationale":401,"selectedPaths":402,"source":325,"sourceLanguage":18,"type":244},"skills/ownership-risk-map","Maps engineering ownership risk in a repository using repo evidence such as git history, churn, bus factor, CODEOWNERS coverage, test density, and orphaned or unclear-owner surfaces. Use when a user says `map ownership risk`, `find bus factor hotspots`, `which files look orphaned`, `high-change low-test areas`, or asks for a recurring maintenance pass that identifies risky surfaces before they become incidents. Do NOT use for org charts, HR ownership assignments, or generic maintainer lists without repo evidence.","ownership-risk-map",{"claudeCode":12},"SKILL.md frontmatter at skills/ownership-risk-map/SKILL.md",[403],{"path":334,"priority":284},{"basePath":405,"description":406,"displayName":407,"installMethods":408,"rationale":409,"selectedPaths":410,"source":325,"sourceLanguage":18,"type":244},"skills/performance-hunt","Hunts for concrete performance bottlenecks in a scoped repository surface using profiler output, benchmarks, query plans, traces, bundle analysis, or repo evidence, then returns the smallest high-value follow-up experiments or fixes. Use when a user says `find performance bottlenecks`, `why is this slow`, `profile this flow`, `hunt hot paths`, or asks for a recurring performance review. Do NOT use for live incident response, generic observability audits, speculative micro-optimization, or broad architecture rewrites with no bottleneck evidence.","performance-hunt",{"claudeCode":12},"SKILL.md frontmatter at skills/performance-hunt/SKILL.md",[411],{"path":334,"priority":284},{"basePath":413,"description":414,"displayName":415,"installMethods":416,"rationale":417,"selectedPaths":418,"source":325,"sourceLanguage":18,"type":244},"skills/pr-risk-review","Reviews open or draft pull requests for engineering risk before merge, focusing on missing validation, hidden coupling, rollout and rollback gaps, migrations, feature flags, and other agent-safe next actions. Use when a user says `review this PR for risk`, `pre-merge review`, `is this PR safe to merge`, or asks for a risk-focused PR review. Do NOT use for post-merge production monitoring, broad code smell review, or commit-scoped bug hunting.","pr-risk-review",{"claudeCode":12},"SKILL.md frontmatter at skills/pr-risk-review/SKILL.md",[419],{"path":334,"priority":284},{"basePath":421,"description":422,"displayName":423,"installMethods":424,"rationale":425,"selectedPaths":426,"source":325,"sourceLanguage":18,"type":244},"skills/recent-commit-bug-hunt","Scans recent commits in one or more repositories, identifies likely bugs using concrete repo evidence only, and proposes tightly scoped remediation sessions. Use when a user says `scan recent commits for bugs`, `what did I probably break`, `review yesterday's changes for regressions`, or asks for a commit-scoped bug hunt. Do NOT use for a broad code health review, full security audit, or speculative bug hunting with no repo or time scope.","recent-commit-bug-hunt",{"claudeCode":12},"SKILL.md frontmatter at skills/recent-commit-bug-hunt/SKILL.md",[427],{"path":334,"priority":284},{"basePath":429,"description":430,"displayName":431,"installMethods":432,"rationale":433,"selectedPaths":434,"source":325,"sourceLanguage":18,"type":244},"skills/refactor-opportunities","Reviews a repository and returns a short, best-first backlog of small, low-risk refactor tickets with clear write boundaries and validation paths. Use when a user says `find refactor opportunities`, `what small cleanup tickets should we hand to agents`, `give me parallelizable refactors`, or asks for narrow maintainability wins in an existing repo. Do NOT use for a broad architecture redesign, style-only cleanup sweep, or bug hunt focused on functional regressions.","refactor-opportunities",{"claudeCode":12},"SKILL.md frontmatter at skills/refactor-opportunities/SKILL.md",[435],{"path":334,"priority":284},{"basePath":437,"description":438,"displayName":439,"installMethods":440,"rationale":441,"selectedPaths":442,"source":325,"sourceLanguage":18,"type":244},"skills/repo-introspection","Inspects an unfamiliar software repository and produces a concrete orientation report covering structure, tooling, entry points, boundaries, active surfaces, and safe places to start work. Use when a user says `help me understand this repo`, `map this codebase before I edit it`, `where should I start`, or asks for an engineering walkthrough before planning or delegation. Do NOT use when the user already knows the target change and wants implementation, or when they need a specific bug diagnosis rather than repo orientation.","repo-introspection",{"claudeCode":12},"SKILL.md frontmatter at skills/repo-introspection/SKILL.md",[443],{"path":334,"priority":284},{"basePath":445,"description":446,"displayName":447,"installMethods":448,"rationale":449,"selectedPaths":450,"source":325,"sourceLanguage":18,"type":244},"skills/security-audit","Audits a repository, workspace, or monorepo for dependency vulnerabilities, outdated security-sensitive packages, license issues, and dependency hygiene gaps, then compiles one evidence-backed report. Use when a user says `run a security audit`, `check dependencies and licenses`, `audit this monorepo for vulnerable packages`, or asks for a package-level security review. Do NOT use for a general secure-code review, threat model, or speculative vulnerability hunt without manifests, lockfiles, or package surfaces to inspect.","security-audit",{"claudeCode":12},"SKILL.md frontmatter at skills/security-audit/SKILL.md",[451],{"path":334,"priority":284},{"basePath":453,"description":454,"displayName":455,"installMethods":456,"rationale":457,"selectedPaths":458,"source":325,"sourceLanguage":18,"type":244},"skills/test-gap-hunt","Identifies and prioritizes the highest-value test coverage gaps in a repository or workspace, then incrementally adds or strengthens tests using the local test stack and cleanly scoped subagent work when available. Use when a user says `improve test coverage`, `find weak tests`, `add missing test cases`, `run a recurring test-improvement pass`, or asks for a language-agnostic workflow to strengthen mocks, fixtures, and test structure without chasing raw coverage numbers. Do NOT use for first-time framework selection, broad test-stack migrations, or large production refactors.","test-gap-hunt",{"claudeCode":12},"SKILL.md frontmatter at skills/test-gap-hunt/SKILL.md",[459],{"path":334,"priority":284},{"sources":461},[462],"manual",{"closedIssues90d":8,"description":464,"forks":8,"homepage":465,"license":236,"openIssues90d":8,"pushedAt":233,"readmeSize":230,"stars":234,"topics":466},"Claude Code skills for on-demand engineering work — PR risk review, repo introspection, audits, ownership maps. Published at cdd.dev/skills/swe.","https://cdd.dev/skills/swe/",[467,468,469,216,470],"agent-skills","claude-code","claude-plugins","codex",{"classifiedAt":472,"discoverAt":473,"extractAt":474,"githubAt":474,"updatedAt":472},1778683789715,1778683785537,1778683787839,[215,212,216,213,214],{"evaluatedAt":239,"extractAt":266,"updatedAt":239},[],[479,510,540,569,597,626],{"_creationTime":480,"_id":481,"community":482,"display":483,"identity":489,"providers":494,"relations":503,"tags":505,"workflow":506},1778698056313.1528,"k176pxdjxvnyex7jv6abt3myd586n5vv",{"reviewCount":8},{"description":484,"installMethods":485,"name":487,"sourceUrl":488},"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":486},"thedotmack/claude-mem","Pathfinder","https://github.com/thedotmack/claude-mem",{"basePath":490,"githubOwner":491,"githubRepo":492,"locale":18,"slug":493,"type":244},"plugin/skills/pathfinder","thedotmack","claude-mem","pathfinder",{"evaluate":495,"extract":501},{"promptVersionExtension":205,"promptVersionScoring":206,"score":496,"tags":497,"targetMarket":217,"tier":218},100,[212,498,213,499,500],"architecture","refactoring","flowchart",{"commitSha":258,"license":502},"Apache-2.0",{"repoId":504},"kd70jnxgm695az2wtf37zbqdj986mp7k",[498,212,213,500,499],{"evaluatedAt":507,"extractAt":508,"updatedAt":509},1778698228002,1778698056313,1778698443446,{"_creationTime":511,"_id":512,"community":513,"display":514,"identity":520,"providers":525,"relations":533,"tags":536,"workflow":537},1778695548458.377,"k17esa27yncbsd0bz8hcg2crg986mjqk",{"reviewCount":8},{"description":515,"installMethods":516,"name":518,"sourceUrl":519},"Extract the conceptual essence of a repository as skills, agents, and teams — the project's roles, procedures, and coordination patterns expressed as agentskills.io-standard definitions. Reads an arbitrary codebase and produces generalized definitions that capture WHAT the project does and WHO operates it, without replicating HOW it does it. Use when onboarding to a new codebase and wanting to understand its conceptual architecture, when bootstrapping an agentic system from an existing project, when studying a project's organizational DNA for cross-pollination, or when creating a skill/agent/team library inspired by a reference implementation.\n",{"claudeCode":517},"pjt222/agent-almanac","Metal","https://github.com/pjt222/agent-almanac",{"basePath":521,"githubOwner":522,"githubRepo":523,"locale":18,"slug":524,"type":244},"skills/metal","pjt222","agent-almanac","metal",{"evaluate":526,"extract":532},{"promptVersionExtension":205,"promptVersionScoring":206,"score":496,"tags":527,"targetMarket":217,"tier":218},[212,528,529,530,531],"conceptualization","agent-definition","repository-structure","software-architecture",{"commitSha":258,"license":236},{"parentExtensionId":534,"repoId":535},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[529,212,528,530,531],{"evaluatedAt":538,"extractAt":539,"updatedAt":538},1778699463464,1778695548458,{"_creationTime":541,"_id":542,"community":543,"display":544,"identity":550,"providers":553,"relations":562,"tags":564,"workflow":565},1778699438912.8826,"k170fxxh22hdspg4vr94whgj1986mpr9",{"reviewCount":8},{"description":545,"installMethods":546,"name":548,"sourceUrl":549},"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":547},"yvgude/lean-ctx","lean-ctx","https://github.com/yvgude/lean-ctx",{"basePath":551,"githubOwner":552,"githubRepo":548,"locale":18,"slug":548,"type":244},"skills/lean-ctx","yvgude",{"evaluate":554,"extract":561},{"promptVersionExtension":205,"promptVersionScoring":206,"score":496,"tags":555,"targetMarket":217,"tier":218},[556,557,558,559,560,212],"context-compression","ai-agent","cli-tools","developer-tools","rust",{"commitSha":258},{"repoId":563},"kd7dxtfr9j3z54hs3bz0218e1n86may0",[557,558,212,556,559,560],{"evaluatedAt":566,"extractAt":567,"updatedAt":568},1778699456179,1778699438912,1778699517795,{"_creationTime":570,"_id":571,"community":572,"display":573,"identity":579,"providers":582,"relations":591,"tags":593,"workflow":594},1778694578248.103,"k17712r7xw99tfa8w7xzre9a4d86m8re",{"reviewCount":8},{"description":574,"installMethods":575,"name":577,"sourceUrl":578},"Codacy Cloud workflow for this repository -- run Codacy's analyzers locally before `git push` (mirrors what Codacy CI runs), and fetch/cluster Codacy issues for any PR via the v3 API. Use when the user mentions Codacy, \"codacy analysis\", `codacy-analysis-cli`, \"codacy issues on PR\", \"fix codacy CI\", \"codacy markdownlint findings\", or any Codacy gate failing on a netdata-org PR. Ships scripts analyze-local.sh (docker/binary runner for codacy-analysis-cli) and pr-issues.sh (paginated v3 issue fetch + group-by tool/pattern/severity/file). Token-safe -- CODACY_TOKEN never reaches assistant-visible stdout. Read-only by design in the current SOW; write actions (mark FP, mark fixed) are deferred.",{"claudeCode":576},"netdata/netdata","codacy-audit","https://github.com/netdata/netdata",{"basePath":580,"githubOwner":581,"githubRepo":581,"locale":18,"slug":577,"type":244},".agents/skills/codacy-audit","netdata",{"evaluate":583,"extract":590},{"promptVersionExtension":205,"promptVersionScoring":206,"score":496,"tags":584,"targetMarket":217,"tier":218},[585,212,586,587,588,589],"codacy","ci","pr-review","linting","security-analysis",{"commitSha":258},{"repoId":592},"kd70yp91ybn40a638h3hzz6nbd86m2cw",[586,585,212,588,587,589],{"evaluatedAt":595,"extractAt":596,"updatedAt":595},1778694601008,1778694578248,{"_creationTime":598,"_id":599,"community":600,"display":601,"identity":607,"providers":611,"relations":619,"tags":622,"workflow":623},1778692488329.0144,"k1724vjyyetw8qcfh8anb4c3tn86ngy7",{"reviewCount":8},{"description":602,"installMethods":603,"name":605,"sourceUrl":606},"Extract domain knowledge from existing project sources and generate domain rules. Also handles vault sync and domain listing.",{"claudeCode":604},"luiseiman/claude-kit","domain-extract","https://github.com/luiseiman/claude-kit",{"basePath":608,"githubOwner":609,"githubRepo":610,"locale":18,"slug":605,"type":244},"skills/domain-extract","luiseiman","claude-kit",{"evaluate":612,"extract":618},{"promptVersionExtension":205,"promptVersionScoring":206,"score":496,"tags":613,"targetMarket":217,"tier":218},[614,615,616,212,617],"domain-extraction","knowledge-management","rule-generation","automation",{"commitSha":258},{"parentExtensionId":620,"repoId":621},"k17650xadq8363kzchr4w0gmf186nq24","kd79wqc8an5wh20cc2znr8tyb586mxwx",[617,212,614,615,616],{"evaluatedAt":624,"extractAt":625,"updatedAt":624},1778693090713,1778692488329,{"_creationTime":627,"_id":628,"community":629,"display":630,"identity":636,"providers":640,"relations":645,"tags":647,"workflow":648},1778692607327.2305,"k170rpk64k5rypx65jra7hetvx86nt23",{"reviewCount":8},{"description":631,"installMethods":632,"name":634,"sourceUrl":635},"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.",{"claudeCode":633},"majiayu000/vibeguard","auto-optimize","https://github.com/majiayu000/vibeguard",{"basePath":637,"githubOwner":638,"githubRepo":639,"locale":18,"slug":634,"type":244},"workflows/auto-optimize","majiayu000","vibeguard",{"evaluate":641,"extract":644},{"promptVersionExtension":205,"promptVersionScoring":206,"score":496,"tags":642,"targetMarket":217,"tier":218},[212,643,639,617,559],"optimization",{"commitSha":258},{"repoId":646},"kd7b0vh258xpbyerk68bk3e1ks86mk58",[617,212,559,643,639],{"evaluatedAt":649,"extractAt":650,"updatedAt":651},1778692790049,1778692607327,1778693059018]