[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-ckorhonen-pr-risk-review-de":3,"guides-for-ckorhonen-pr-risk-review":479,"similar-k171yjxfdtbbxak49apmnpetp986mbt1-de":480},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":242,"isFallback":228,"parentExtension":247,"providers":269,"relations":273,"repo":274,"tags":477,"workflow":478},1778683790179.7817,"k171yjxfdtbbxak49apmnpetp986mbt1",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"claudeCode":12},"ckorhonen/swe-skills","pr-risk-review","https://github.com/ckorhonen/swe-skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":226,"workflow":240},1778684098339.342,"kn79kx1g07g3rf68fs5t44wzt986mwjs","en",{"checks":20,"evaluatedAt":195,"extensionSummary":196,"features":197,"nonGoals":202,"promptVersionExtension":207,"promptVersionScoring":208,"purpose":209,"rationale":210,"score":211,"summary":212,"tags":213,"targetMarket":219,"tier":220,"useCases":221},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,99,103,107,110,113,116,120,123,126,129,132,135,138,142,146,150,153,157,160,163,166,169,173,176,179,182,185,188,192],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of reviewing open pull requests for engineering risk before merge, and the use cases specify when to use it and when not to.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers a focused risk assessment for PRs, specifically targeting validation, coupling, rollout/rollback, migrations, and feature flags, which goes beyond a generic code review.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill's instructions and documented approach suggest it can be used in a real workflow to assess PR readiness, covering the necessary aspects for a pre-merge review.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses specifically on reviewing pull requests for engineering risk before merge, adhering to a single, well-defined scope.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description accurately reflects the skill's purpose, use cases, and non-goals, providing a clear and concise overview for end users.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This skill does not expose explicit tools in the manifest; its functionality is driven by the LLM's interpretation of its instructions.",{"category":45,"check":46,"severity":42,"summary":47},"Documentation","Configuration & parameter reference","The skill does not appear to have configurable parameters or options beyond what can be inferred from the prompt context.",{"category":33,"check":49,"severity":42,"summary":50},"Tool naming","The skill does not expose explicit tools, so tool naming conventions do not apply.",{"category":33,"check":52,"severity":42,"summary":53},"Minimal I/O surface","As the skill does not expose explicit tools, its I/O surface cannot be evaluated in this manner.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The extension is distributed under the MIT License, which is a permissive open-source license, and this is clearly indicated in the LICENSE file.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The last commit was on May 9, 2026, which is within the last 90 days.",{"category":59,"check":63,"severity":24,"summary":64},"Dependency Management","The repository has a lockfile (package-lock.json is implied by package.json and npm install), indicating good dependency management practices.",{"category":66,"check":67,"severity":24,"summary":68},"Security","Secret Management","The skill's purpose involves reviewing code and metadata, not handling or exposing secrets. No secrets appear to be used or exposed in the provided code.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill's instructions focus on interpreting provided context (PRs, diffs) and do not indicate loading untrusted external data or instructions.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill does not fetch remote content at runtime or execute arbitrary code, relying solely on the provided PR context and its own bundled instructions.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill's function is analytical and does not involve file manipulation or operations outside its intended scope. It operates on provided PR data.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","No detached processes or retry loops around denied tool calls were observed in the skill's instructions.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill's purpose is analytical and confined to PR data. There are no indications of it reading or submitting confidential data to a third party.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled files and descriptions appear free of hidden steering tricks, Unicode tag characters, or other obfuscation methods.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The skill's instructions are written in plain markdown and do not contain obfuscated code, base64 payloads, or runtime script fetching.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The skill operates on PR data and does not make assumptions about the user's project file structure.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","There are 0 open and 0 closed issues in the last 90 days, indicating the repository is either new, unused, or has issues disabled. This does not negatively impact the score due to the low volume.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The repository has a meaningful commit date (May 9, 2026) and a clear MIT license, but no formal versioning in frontmatter or tags. Installation via `npx skills install ckorhonen/swe-skills` implies use of the main branch, but the recency is strong.",{"category":104,"check":105,"severity":42,"summary":106},"Code Execution","Validation","The skill's core logic is instruction-based and does not involve direct execution of user-provided input arguments or structured output that would require schema validation libraries.",{"category":66,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","The skill is purely analytical and performs no destructive operations.",{"category":104,"check":111,"severity":24,"summary":112},"Error Handling","The skill's instructions outline error reporting and recovery steps for potential issues like vague requests or insufficient data, guiding the LLM to handle errors meaningfully.",{"category":104,"check":114,"severity":42,"summary":115},"Logging","This skill is instruction-based and does not involve destructive actions or outbound calls that would necessitate local audit logging.",{"category":117,"check":118,"severity":24,"summary":119},"Compliance","GDPR","The skill operates on PR metadata and code, which may contain personal data, but it does not submit this data to third parties and focuses on analysis within the LLM context.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The skill's function is universal to software development and does not contain any regional or legal jurisdiction-specific logic, making its target market global.",{"category":92,"check":124,"severity":24,"summary":125},"Runtime stability","The skill's instructions are written in standard markdown and do not rely on specific OS features, shells, or runtime environments beyond the LLM's execution context.",{"category":45,"check":127,"severity":24,"summary":128},"README","The README.md file exists and provides a good overview of the repository's structure, conventions, and development practices.",{"category":33,"check":130,"severity":42,"summary":131},"Tool surface size","This is a single-purpose skill and does not expose multiple distinct tools.",{"category":40,"check":133,"severity":42,"summary":134},"Overlapping near-synonym tools","The skill does not expose explicit tools, so overlapping tool names are not applicable.",{"category":45,"check":136,"severity":24,"summary":137},"Phantom features","All advertised features in the description and SKILL.md are implemented through the skill's instructional logic.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","The README provides clear installation instructions using 'npx skills install ckorhonen/swe-skills'.",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","The SKILL.md outlines how to handle vague requests and insufficient data by asking clarifying questions or reporting limitations, providing a path forward.",{"category":147,"check":148,"severity":24,"summary":149},"Execution","Pinned dependencies","The repository has a lockfile (implied by package.json and `npm install`), indicating that dependencies are pinned.",{"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, thus a dry-run mode is not applicable.",{"category":154,"check":155,"severity":42,"summary":156},"Protocol","Idempotent retry & timeouts","The skill is instruction-based and does not involve remote calls or state-changing operations that would require idempotency or timeouts.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","There is no indication of telemetry collection in the provided files; if any were present, it would be expected to be opt-in by default.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The description and SKILL.md clearly state the skill's purpose (review PRs for merge risk) and provide specific trigger phrases and non-goals.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter in SKILL.md is concise, clearly states the skill's core capability, and includes relevant trigger phrases.",{"category":45,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is well-structured and under 500 lines, delegating deeper material appropriately.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md is well-structured and does not embed large amounts of bulk material, adhering to progressive disclosure principles.",{"category":170,"check":174,"severity":42,"summary":175},"Forked exploration","The skill's task is a focused review, not deep exploration, so `context: fork` is not applicable.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","While not explicitly showing example invocations and outputs in the SKILL.md, the detailed instructions and output requirements provide sufficient guidance for the LLM to generate accurate reviews.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The SKILL.md documents failure modes such as vague requests and insufficient data, providing recovery steps like asking clarifying questions.",{"category":104,"check":183,"severity":42,"summary":184},"Tool Fallback","The skill does not rely on external tools like a custom MCP server and has no documented fallback path requirement.",{"category":92,"check":186,"severity":24,"summary":187},"Stack assumptions","The skill operates within the LLM's context and does not assume specific local development environments or tooling beyond what is standard for PR review.",{"category":189,"check":190,"severity":24,"summary":191},"Safety","Halt on unexpected state","The SKILL.md instructs the skill to ask clarifying questions or report limitations when faced with vague requests or insufficient data, effectively halting unproductive workflows.",{"category":92,"check":193,"severity":24,"summary":194},"Cross-skill coupling","The skill is self-contained and focuses solely on PR risk review, without implicitly relying on or handling tasks from adjacent skills.",1778684098229,"This skill reviews open or draft pull requests to identify engineering risks before merging, focusing on aspects like missing validation, hidden coupling, rollout/rollback gaps, migrations, and feature flags. It aims to provide a concise risk report and actionable next steps.",[198,199,200,201],"Reviews PRs for engineering risk before merge","Identifies missing validation, coupling, rollout/rollback gaps","Analyzes migrations and feature flag implementation","Provides ranked risk findings and actionable next steps",[203,204,205,206],"Post-merge production monitoring","Scanning recent commits for regressions after the fact","Broad code style or architecture review outside PR scope","General project planning or roadmap feedback","3.0.0","4.4.0","To help engineers assess the safety and readiness of pull requests for merging by identifying potential engineering risks and gaps in validation or planning.","The skill is well-documented, adheres to principles of single responsibility and secure practices, and is production-ready. The 'Release Management' check received a pass due to strong recency and a clear license, despite the lack of formal versioning, which is a minor point for a well-maintained skill.",97,"Excellent skill for focused PR risk assessment before merge, with clear documentation and secure practices.",[214,215,216,217,218],"pull-request","code-review","risk-assessment","engineering-practices","automation","global","verified",[222,223,224,225],"Reviewing a PR before merge to determine safety","Identifying missing tests, checks, or rollout plans on open PRs","Assessing caution needed for migrations, flags, or interface changes","Getting agent-safe follow-up actions for a PR",{"codeQuality":227,"collectedAt":229,"documentation":230,"maintenance":233,"security":237,"testCoverage":239},{"hasLockfile":228},true,1778684077266,{"descriptionLength":231,"readmeSize":232},446,8683,{"closedIssues90d":8,"forks":8,"hasChangelog":234,"openIssues90d":8,"pushedAt":235,"stars":236},false,1778361321000,1,{"hasNpmPackage":234,"license":238,"smitheryVerified":234},"MIT",{"hasCi":228,"hasTests":234},{"updatedAt":241},1778684098339,{"basePath":243,"githubOwner":244,"githubRepo":245,"locale":18,"slug":13,"type":246},"skills/pr-risk-review","ckorhonen","swe-skills","skill",{"_creationTime":248,"_id":249,"community":250,"display":251,"identity":254,"parentExtension":257,"providers":258,"relations":264,"tags":266,"workflow":267},1778683790179.7788,"k17d2yq229g61qvea0x8t60w1h86mgr8",{"reviewCount":8},{"description":252,"installMethods":253,"name":245,"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":245},{"basePath":255,"githubOwner":244,"githubRepo":245,"locale":18,"slug":245,"type":256},"","plugin",null,{"extract":259},{"commitSha":260,"plugin":261},"HEAD",{"mcpCount":8,"provider":262,"skillCount":263},"classify",17,{"repoId":265},"kd7b5kvzw3q7dgvym5bdx3m53986mann",[],{"extractAt":268,"updatedAt":268},1778683790179,{"evaluate":270,"extract":272},{"promptVersionExtension":207,"promptVersionScoring":208,"score":211,"tags":271,"targetMarket":219,"tier":220},[214,215,216,217,218],{"commitSha":260},{"parentExtensionId":249,"repoId":265},{"_creationTime":275,"_id":265,"identity":276,"providers":277,"workflow":473},1778683785537.182,{"githubOwner":244,"githubRepo":245,"sourceUrl":14},{"classify":278,"discover":462,"github":465},{"commitSha":260,"extensions":279},[280,328,337,345,353,361,369,377,385,393,401,409,417,422,430,438,446,454],{"basePath":255,"description":252,"displayName":245,"installMethods":281,"rationale":282,"selectedPaths":283,"source":327,"sourceLanguage":18,"type":256},{"claudeCode":245},"plugin manifest at .claude-plugin/plugin.json",[284,287,289,292,295,297,299,301,303,305,307,309,311,313,315,317,319,321,323,325],{"path":285,"priority":286},".claude-plugin/plugin.json","mandatory",{"path":288,"priority":286},"README.md",{"path":290,"priority":291},"LICENSE","high",{"path":293,"priority":294},"skills/babysit-pr/SKILL.md","medium",{"path":296,"priority":294},"skills/capture-knowledge/SKILL.md",{"path":298,"priority":294},"skills/change-validation-planner/SKILL.md",{"path":300,"priority":294},"skills/create-skill/SKILL.md",{"path":302,"priority":294},"skills/docs-drift-audit/SKILL.md",{"path":304,"priority":294},"skills/incident-followup-audit/SKILL.md",{"path":306,"priority":294},"skills/init/SKILL.md",{"path":308,"priority":294},"skills/merged-pr-monitoring/SKILL.md",{"path":310,"priority":294},"skills/observability-gap-hunt/SKILL.md",{"path":312,"priority":294},"skills/ownership-risk-map/SKILL.md",{"path":314,"priority":294},"skills/performance-hunt/SKILL.md",{"path":316,"priority":294},"skills/pr-risk-review/SKILL.md",{"path":318,"priority":294},"skills/recent-commit-bug-hunt/SKILL.md",{"path":320,"priority":294},"skills/refactor-opportunities/SKILL.md",{"path":322,"priority":294},"skills/repo-introspection/SKILL.md",{"path":324,"priority":294},"skills/security-audit/SKILL.md",{"path":326,"priority":294},"skills/test-gap-hunt/SKILL.md","rule",{"basePath":329,"description":330,"displayName":331,"installMethods":332,"rationale":333,"selectedPaths":334,"source":327,"sourceLanguage":18,"type":246},"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",[335],{"path":336,"priority":286},"SKILL.md",{"basePath":338,"description":339,"displayName":340,"installMethods":341,"rationale":342,"selectedPaths":343,"source":327,"sourceLanguage":18,"type":246},"skills/capture-knowledge","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.","capture-knowledge",{"claudeCode":12},"SKILL.md frontmatter at skills/capture-knowledge/SKILL.md",[344],{"path":336,"priority":286},{"basePath":346,"description":347,"displayName":348,"installMethods":349,"rationale":350,"selectedPaths":351,"source":327,"sourceLanguage":18,"type":246},"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",[352],{"path":336,"priority":286},{"basePath":354,"description":355,"displayName":356,"installMethods":357,"rationale":358,"selectedPaths":359,"source":327,"sourceLanguage":18,"type":246},"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",[360],{"path":336,"priority":286},{"basePath":362,"description":363,"displayName":364,"installMethods":365,"rationale":366,"selectedPaths":367,"source":327,"sourceLanguage":18,"type":246},"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",[368],{"path":336,"priority":286},{"basePath":370,"description":371,"displayName":372,"installMethods":373,"rationale":374,"selectedPaths":375,"source":327,"sourceLanguage":18,"type":246},"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",[376],{"path":336,"priority":286},{"basePath":378,"description":379,"displayName":380,"installMethods":381,"rationale":382,"selectedPaths":383,"source":327,"sourceLanguage":18,"type":246},"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",[384],{"path":336,"priority":286},{"basePath":386,"description":387,"displayName":388,"installMethods":389,"rationale":390,"selectedPaths":391,"source":327,"sourceLanguage":18,"type":246},"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",[392],{"path":336,"priority":286},{"basePath":394,"description":395,"displayName":396,"installMethods":397,"rationale":398,"selectedPaths":399,"source":327,"sourceLanguage":18,"type":246},"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",[400],{"path":336,"priority":286},{"basePath":402,"description":403,"displayName":404,"installMethods":405,"rationale":406,"selectedPaths":407,"source":327,"sourceLanguage":18,"type":246},"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",[408],{"path":336,"priority":286},{"basePath":410,"description":411,"displayName":412,"installMethods":413,"rationale":414,"selectedPaths":415,"source":327,"sourceLanguage":18,"type":246},"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",[416],{"path":336,"priority":286},{"basePath":243,"description":10,"displayName":13,"installMethods":418,"rationale":419,"selectedPaths":420,"source":327,"sourceLanguage":18,"type":246},{"claudeCode":12},"SKILL.md frontmatter at skills/pr-risk-review/SKILL.md",[421],{"path":336,"priority":286},{"basePath":423,"description":424,"displayName":425,"installMethods":426,"rationale":427,"selectedPaths":428,"source":327,"sourceLanguage":18,"type":246},"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",[429],{"path":336,"priority":286},{"basePath":431,"description":432,"displayName":433,"installMethods":434,"rationale":435,"selectedPaths":436,"source":327,"sourceLanguage":18,"type":246},"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",[437],{"path":336,"priority":286},{"basePath":439,"description":440,"displayName":441,"installMethods":442,"rationale":443,"selectedPaths":444,"source":327,"sourceLanguage":18,"type":246},"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",[445],{"path":336,"priority":286},{"basePath":447,"description":448,"displayName":449,"installMethods":450,"rationale":451,"selectedPaths":452,"source":327,"sourceLanguage":18,"type":246},"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",[453],{"path":336,"priority":286},{"basePath":455,"description":456,"displayName":457,"installMethods":458,"rationale":459,"selectedPaths":460,"source":327,"sourceLanguage":18,"type":246},"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",[461],{"path":336,"priority":286},{"sources":463},[464],"manual",{"closedIssues90d":8,"description":466,"forks":8,"homepage":467,"license":238,"openIssues90d":8,"pushedAt":235,"readmeSize":232,"stars":236,"topics":468},"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/",[469,470,471,215,472],"agent-skills","claude-code","claude-plugins","codex",{"classifiedAt":474,"discoverAt":475,"extractAt":476,"githubAt":476,"updatedAt":474},1778683789715,1778683785537,1778683787839,[218,215,217,214,216],{"evaluatedAt":241,"extractAt":268,"updatedAt":241},[],[481,511,539,568,599,620],{"_creationTime":482,"_id":483,"community":484,"display":485,"identity":491,"providers":495,"relations":504,"tags":507,"workflow":508},1778699234184.611,"k179b6dkc777g1rgyecze04wqn86m6y4",{"reviewCount":8},{"description":486,"installMethods":487,"name":489,"sourceUrl":490},"Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly",{"claudeCode":488},"Yeachan-Heo/oh-my-claudecode","oh-my-claudecode","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":492,"githubOwner":493,"githubRepo":489,"locale":18,"slug":494,"type":246},"skills/ask","Yeachan-Heo","ask",{"evaluate":496,"extract":503},{"promptVersionExtension":207,"promptVersionScoring":208,"score":497,"tags":498,"targetMarket":219,"tier":220},100,[499,218,500,501,215,502],"cli","llm","prompting","artifact-generation",{"commitSha":260,"license":238},{"parentExtensionId":505,"repoId":506},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[502,218,499,215,500,501],{"evaluatedAt":509,"extractAt":510,"updatedAt":509},1778699303045,1778699234184,{"_creationTime":512,"_id":513,"community":514,"display":515,"identity":521,"providers":526,"relations":533,"tags":535,"workflow":536},1778697652123.8804,"k173mjn1bp2a67v1h8qjkv7wn186met8",{"reviewCount":8},{"description":516,"installMethods":517,"name":519,"sourceUrl":520},"Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, commit-review reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions monitoring, permissions, gates, and manual backfills.",{"claudeCode":518},"steipete/clawdis","ClawSweeper Skill","https://github.com/steipete/clawdis",{"basePath":522,"githubOwner":523,"githubRepo":524,"locale":18,"slug":525,"type":246},".agents/skills/clawsweeper","steipete","clawdis","clawsweeper",{"evaluate":527,"extract":532},{"promptVersionExtension":207,"promptVersionScoring":208,"score":497,"tags":528,"targetMarket":219,"tier":220},[529,218,215,530,531],"github","maintenance","ci-cd",{"commitSha":260,"license":238},{"repoId":534},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[218,531,215,529,530],{"evaluatedAt":537,"extractAt":538,"updatedAt":537},1778697688364,1778697652123,{"_creationTime":540,"_id":541,"community":542,"display":543,"identity":549,"providers":553,"relations":561,"tags":564,"workflow":565},1778695548458.3926,"k172f2ed2j5kxdq8hbw4nszcw186m5xj",{"reviewCount":8},{"description":544,"installMethods":545,"name":547,"sourceUrl":548},"Review a pull request end-to-end using GitHub CLI. Covers diff analysis, commit history review, CI/CD check verification, severity-leveled feedback (blocking/suggestion/nit/praise), and gh pr review submission. Use when a pull request is assigned for review, performing a self-review before requesting others' input, conducting a second review after feedback is addressed, or auditing a merged PR for post-merge quality assessment.\n",{"claudeCode":546},"pjt222/agent-almanac","review-pull-request","https://github.com/pjt222/agent-almanac",{"basePath":550,"githubOwner":551,"githubRepo":552,"locale":18,"slug":547,"type":246},"skills/review-pull-request","pjt222","agent-almanac",{"evaluate":554,"extract":560},{"promptVersionExtension":207,"promptVersionScoring":208,"score":497,"tags":555,"targetMarket":219,"tier":220},[556,214,529,215,557,558,559],"review","gh-cli","feedback","pr",{"commitSha":260},{"parentExtensionId":562,"repoId":563},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[215,558,557,529,559,214,556],{"evaluatedAt":566,"extractAt":567,"updatedAt":566},1778700796502,1778695548458,{"_creationTime":569,"_id":570,"community":571,"display":572,"identity":578,"providers":584,"relations":591,"tags":594,"workflow":595},1778691370980.6204,"k175r5wzz8n1wk65qfwqv70vkn86n2kg",{"reviewCount":8},{"description":573,"installMethods":574,"name":576,"sourceUrl":577},"Überprüft Pull Requests in Drupal 11 (oder anderen) Projekten gemäß der Codex-Methodik (Geschäftslogik, Edge Cases von Hooks/Queries, Sicherheit, Performance, Vollständigkeit). Generiert einen .md-Bericht im erkannten IDE-Ordner (.antigravity/, .cursor/, .vscode/ oder docs/) mit Befunden nach Schweregrad und umsetzbaren Lösungen. Verwenden Sie dies, wenn der Benutzer \"Codex-Überprüfung\", \"PR-Überprüfung\", \"PR überprüfen\", \"PR überprüfen\" anfordert.",{"claudeCode":575},"j4rk0r/claude-skills","Codex PR Review","https://github.com/j4rk0r/claude-skills",{"basePath":579,"githubOwner":580,"githubRepo":581,"locale":582,"slug":583,"type":246},"skills/codex-pr-review","j4rk0r","claude-skills","de","codex-pr-review",{"evaluate":585,"extract":590},{"promptVersionExtension":207,"promptVersionScoring":208,"score":497,"tags":586,"targetMarket":219,"tier":220},[587,215,214,472,588,589],"drupal","security","quality-assurance",{"commitSha":260,"license":238},{"repoId":592,"translatedFrom":593},"kd79shaph0e07035621cxd7x1n86m944","k175cj68ewyej64segk2xnppss86n5ad",[215,472,587,214,589,588],{"evaluatedAt":596,"extractAt":597,"updatedAt":598},1778691239127,1778691193352,1778691370980,{"_creationTime":600,"_id":601,"community":602,"display":603,"identity":607,"providers":609,"relations":616,"tags":617,"workflow":618},1778695548458.3474,"k1730fbw3hyx274fzsesckx2bs86nqph",{"reviewCount":8},{"description":604,"installMethods":605,"name":606,"sourceUrl":548},"Create and manage pull requests using GitHub CLI. Covers branch preparation, writing PR titles and descriptions, creating PRs, handling review feedback, and merge/cleanup workflows. Use when proposing changes from a feature or fix branch for review, merging completed work into the main branch, requesting code review from collaborators, or documenting the purpose and scope of a set of changes.\n",{"claudeCode":546},"create-pull-request",{"basePath":608,"githubOwner":551,"githubRepo":552,"locale":18,"slug":606,"type":246},"skills/create-pull-request",{"evaluate":610,"extract":615},{"promptVersionExtension":207,"promptVersionScoring":208,"score":611,"tags":612,"targetMarket":219,"tier":220},99,[529,214,613,614,215,218],"git","collaboration",{"commitSha":260},{"parentExtensionId":562,"repoId":563},[218,215,614,613,529,214],{"evaluatedAt":619,"extractAt":567,"updatedAt":619},1778697203799,{"_creationTime":621,"_id":622,"community":623,"display":624,"identity":628,"providers":631,"relations":639,"tags":640,"workflow":641},1778699234184.6157,"k177tdbfgqmwhtaqv771f2ych586nne9",{"reviewCount":8},{"description":625,"installMethods":626,"name":627,"sourceUrl":490},"Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions",{"claudeCode":488},"Project Session Manager",{"basePath":629,"githubOwner":493,"githubRepo":489,"locale":18,"slug":630,"type":246},"skills/project-session-manager","project-session-manager",{"evaluate":632,"extract":638},{"promptVersionExtension":207,"promptVersionScoring":208,"score":497,"tags":633,"targetMarket":219,"tier":220},[613,634,635,636,218,499,637],"development-environment","workflow","tmux","developer-tool",{"commitSha":260,"license":238},{"parentExtensionId":505,"repoId":506},[218,499,637,634,613,636,635],{"evaluatedAt":642,"extractAt":510,"updatedAt":642},1778699613343]