[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-ckorhonen-babysit-pr-en":3,"guides-for-ckorhonen-babysit-pr":478,"similar-k179d3pmvdz1pwa0vmmshm136986n06n-en":479},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":241,"isFallback":233,"parentExtension":246,"providers":268,"relations":272,"repo":273,"tags":476,"workflow":477},1778683790179.779,"k179d3pmvdz1pwa0vmmshm136986n06n",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"claudeCode":12},"ckorhonen/swe-skills","babysit-pr","https://github.com/ckorhonen/swe-skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":225,"workflow":239},1778683839862.889,"kn7a7f8tzyfp9hyz1qbf9r1v6x86nw1c","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},[21,26,29,32,36,39,43,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,99,104,108,111,115,118,122,125,128,131,134,137,140,144,148,151,154,158,161,164,167,170,174,177,180,183,186,190],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly names the problem of babysitting an open pull request end-to-end and provides specific use cases and non-goals.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers significant value over a simple prompt by implementing a continuous watch loop, automated triage, and iteration based on specific feedback and CI states, going beyond basic PR review.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill is fully implemented and covers the complete lifecycle of monitoring a pull request until it is ready to merge or explicitly blocked, utilizing GitHub APIs and local Git commands.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses on a single, coherent workflow: monitoring and managing a single open pull request through its review process.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's functionality, including its purpose, use cases, and explicit non-goals, as detailed in the SKILL.md.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill primarily uses specific GitHub CLI commands like `gh pr view`, `gh pr checks`, `gh run view`, and `gh api` for reviews/comments, which are narrow verb-noun specialists.",{"category":44,"check":45,"severity":46,"summary":47},"Documentation","Configuration & parameter reference","not_applicable","No configurable parameters or environment variables are documented or referenced in the SKILL.md; the skill relies on inferred context or explicit user commands.",{"category":33,"check":49,"severity":24,"summary":50},"Tool naming","The skill's description implies usage of GitHub CLI commands, which follow descriptive verb-noun naming conventions.",{"category":33,"check":52,"severity":24,"summary":53},"Minimal I/O surface","The skill primarily interacts with GitHub APIs for PR metadata and actions, and local Git commands, which are expected to have well-defined and minimal I/O surfaces.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The extension is licensed under the MIT license, as indicated by the bundled LICENSE file, 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 3 months.",{"category":59,"check":63,"severity":46,"summary":64},"Dependency Management","The skill appears to rely on standard GitHub CLI tools and Git, with no explicit third-party dependencies mentioned that would require management.",{"category":66,"check":67,"severity":24,"summary":68},"Security","Secret Management","The skill relies on an authenticated `gh` CLI session, implying it uses standard GitHub authentication mechanisms which are typically handled securely and not exposed in output.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill operates on GitHub PRs and local Git, with instructions to use specific CLI tools and commands, suggesting data is treated as input to these tools rather than executable instructions.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill uses bundled GitHub CLI commands and local Git operations, with no indication of runtime downloads or remote script execution that could introduce supply-chain risks.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill interacts with GitHub APIs and the local Git repository, with instructions to work on a PR branch, implying operations are confined to the repository's scope and not writing to arbitrary user paths.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","No evidence of detached process spawns or deny-retry loops is present in the described workflow; operations are sequential and tool-driven.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill's purpose is to manage a PR within GitHub, and it does not appear to have instructions to read or submit confidential data to external third parties.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled SKILL.md and README.md files appear to be free of hidden steering tricks, control characters, or other obfuscation techniques.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The skill's implementation relies on standard CLI tools and Git commands, with no indication of obfuscated code, base64 payloads, or runtime script fetching.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The skill assumes access to a clean local checkout of the PR branch and GitHub authentication, which are standard preconditions for this type of operation and clearly stated.",{"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 either a new or very stable project with minimal current issue engagement.",{"category":100,"check":101,"severity":102,"summary":103},"Versioning","Release Management","warning","While the code is recent, there is no clear versioning indicated in the SKILL.md frontmatter, package.json, or CHANGELOG, and the README install instructions reference `npx skills install ckorhonen/swe-skills` which may imply installation from main.",{"category":105,"check":106,"severity":24,"summary":107},"Execution","Validation","The skill's instructions imply validation will occur through CI checks and review processes, and the user is prompted to confirm inputs, suggesting a controlled workflow.",{"category":66,"check":109,"severity":24,"summary":110},"Unguarded Destructive Operations","The skill can push commits and rerun checks, but these operations are tied to the PR workflow and guided by reviewer feedback, implying they are not blindly destructive.",{"category":112,"check":113,"severity":24,"summary":114},"Code Execution","Error Handling","The SKILL.md outlines handling for various states (ambiguous feedback, CI failures, blockers) and specifies reporting mechanisms, implying a structured error handling approach.",{"category":112,"check":116,"severity":24,"summary":117},"Logging","The skill's instructions specify reporting updates and a final summary, which implies a form of logging or transcript generation of its actions and outcomes.",{"category":119,"check":120,"severity":24,"summary":121},"Compliance","GDPR","The skill operates on GitHub PR data and local code changes. It does not appear to specifically handle or submit personal data to third parties beyond what is inherent in GitHub interactions.",{"category":119,"check":123,"severity":24,"summary":124},"Target market","The skill is generic to GitHub PR management and does not contain any regional or jurisdictional logic; it is globally applicable.",{"category":92,"check":126,"severity":24,"summary":127},"Runtime stability","The skill relies on the GitHub CLI and local Git, which are standard tools available across common development environments, with no specific OS or shell assumptions.",{"category":44,"check":129,"severity":24,"summary":130},"README","The README exists and provides a general overview of the SWE Skills project, including installation and development instructions. The SKILL.md provides the specific detail for this skill.",{"category":33,"check":132,"severity":46,"summary":133},"Tool surface size","This skill is described as using specific GitHub CLI commands and local Git operations rather than exposing a large number of its own tools.",{"category":40,"check":135,"severity":24,"summary":136},"Overlapping near-synonym tools","The skill orchestrates specific GitHub CLI commands, which are distinct in their function, avoiding overlapping synonyms.",{"category":44,"check":138,"severity":24,"summary":139},"Phantom features","All features described in the README and SKILL.md, such as monitoring comments, handling CI failures, and iterating on feedback, are directly supported by the described workflow and implied tool usage.",{"category":141,"check":142,"severity":102,"summary":143},"Install","Installation instruction","The README provides an installation command (`npx skills install ckorhonen/swe-skills`), but it lacks specific examples of how to invoke the `babysit-pr` skill or detailed authentication steps for the `gh` CLI beyond implying its use.",{"category":145,"check":146,"severity":24,"summary":147},"Errors","Actionable error messages","The SKILL.md outlines specific actions for handling various states like ambiguous feedback, CI failures, and blockers, including asking clarifying questions or reporting issues, which implies actionable error reporting.",{"category":105,"check":149,"severity":24,"summary":150},"Pinned dependencies","The skill relies on the `gh` CLI and Git, which are assumed to be installed and managed by the user's environment, and the README mentions `npm install` for development tooling, suggesting standard dependency management.",{"category":33,"check":152,"severity":46,"summary":153},"Dry-run preview","The skill's core function is to actively monitor and interact with a PR, which is inherently state-changing and does not lend itself to a dry-run mode without fundamentally altering its purpose.",{"category":155,"check":156,"severity":24,"summary":157},"Protocol","Idempotent retry & timeouts","While not explicitly stated as upsert-by-key, the described iterative loop and handling of retries per SHA suggest a careful approach to state management, and the 60-second poll loop implies a form of timeout.",{"category":119,"check":159,"severity":24,"summary":160},"Telemetry opt-in","There is no mention of telemetry collection within the SKILL.md or README, implying it is either not present or not a user-facing feature requiring opt-in.",{"category":40,"check":162,"severity":24,"summary":163},"Precise Purpose","The description clearly states the skill's purpose (babysitting a PR end-to-end) and provides explicit positive triggers and non-goals, making its scope and usage unambiguous.",{"category":40,"check":165,"severity":24,"summary":166},"Concise Frontmatter","The frontmatter in SKILL.md is concise, clearly stating the skill's core capability and providing trigger phrases within the first 160 characters.",{"category":44,"check":168,"severity":24,"summary":169},"Concise Body","The SKILL.md is well-structured and under approximately 500 lines, with detailed instructions and examples without excessive verbosity.",{"category":171,"check":172,"severity":24,"summary":173},"Context","Progressive Disclosure","The SKILL.md is structured logically with clear sections. While it contains detailed instructions, it does not embed large bulk third-party material, and its length is manageable.",{"category":171,"check":175,"severity":46,"summary":176},"Forked exploration","The skill performs a defined workflow rather than deep exploration or code review, so `context: fork` is not applicable.",{"category":22,"check":178,"severity":24,"summary":179},"Usage examples","Two clear examples are provided demonstrating user input, expected actions, and the observable outcome of the skill's execution.",{"category":22,"check":181,"severity":24,"summary":182},"Edge cases","The SKILL.md documents failure modes like missing GitHub auth, ambiguous requests, lack of reviewer input, and mergeability issues, along with recovery steps.",{"category":112,"check":184,"severity":46,"summary":185},"Tool Fallback","The skill relies on the GitHub CLI and local Git, which are standard tools and not optional external MCPs requiring fallback mechanisms.",{"category":187,"check":188,"severity":24,"summary":189},"Safety","Halt on unexpected state","The skill's instructions detail how to handle unexpected states like uncommitted changes, ambiguous feedback, and CI failures, by stopping and reporting or asking for clarification.",{"category":92,"check":191,"severity":24,"summary":192},"Cross-skill coupling","The skill focuses on a specific PR babysitting task and does not appear to implicitly rely on other skills being loaded in the same session.",1778683839741,"This skill actively monitors and manages a single open pull request, handling comments, reviews, CI failures, and iterating on feedback until the PR is ready to merge or becomes blocked. It uses GitHub CLI and Git commands for interaction.",[196,197,198,199,200],"End-to-end PR monitoring and management","Automated triage of comments and reviews","Handling of CI failures and reruns","Iterative feedback and score-based gatekeeping","Stopping only when PR is merge-ready or blocked",[202,203,204,205],"One-time risk review with no ongoing watch loop","Post-merge production impact checks","Repo-wide CI triage without a scoped PR","Ambiguous product or design decisions requiring user direction","3.0.0","4.4.0","To automate the process of shepherding a pull request from review to merge-ready status, reducing manual oversight and ensuring continuous progress.","The 'Release Management' check failed due to a lack of explicit versioning, and the 'Installation instruction' check received a warning for vague authentication and invocation examples. Despite these minor documentation points, the skill is well-defined, functional, and secure.",95,"A robust and secure skill for automating pull request management through review cycles.",[213,214,215,216,217],"github","pull-request","automation","ci-cd","code-review","global","community",[221,222,223,224],"Babysit an open PR until it is merge-ready","Watch for review comments, change requests, and CI failures continuously","Apply small follow-up fixes and push them automatically","Keep iterating until a reviewer or review bot gives the highest available score",{"codeQuality":226,"collectedAt":228,"documentation":229,"maintenance":232,"security":236,"testCoverage":238},{"hasLockfile":227},true,1778683822470,{"descriptionLength":230,"readmeSize":231},494,8683,{"closedIssues90d":8,"forks":8,"hasChangelog":233,"openIssues90d":8,"pushedAt":234,"stars":235},false,1778361321000,1,{"hasNpmPackage":233,"license":237,"smitheryVerified":233},"MIT",{"hasCi":227,"hasTests":233},{"updatedAt":240},1778683839862,{"basePath":242,"githubOwner":243,"githubRepo":244,"locale":18,"slug":13,"type":245},"skills/babysit-pr","ckorhonen","swe-skills","skill",{"_creationTime":247,"_id":248,"community":249,"display":250,"identity":253,"parentExtension":256,"providers":257,"relations":263,"tags":265,"workflow":266},1778683790179.7788,"k17d2yq229g61qvea0x8t60w1h86mgr8",{"reviewCount":8},{"description":251,"installMethods":252,"name":244,"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":244},{"basePath":254,"githubOwner":243,"githubRepo":244,"locale":18,"slug":244,"type":255},"","plugin",null,{"extract":258},{"commitSha":259,"plugin":260},"HEAD",{"mcpCount":8,"provider":261,"skillCount":262},"classify",17,{"repoId":264},"kd7b5kvzw3q7dgvym5bdx3m53986mann",[],{"extractAt":267,"updatedAt":267},1778683790179,{"evaluate":269,"extract":271},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":270,"targetMarket":218,"tier":219},[213,214,215,216,217],{"commitSha":259},{"parentExtensionId":248,"repoId":264},{"_creationTime":274,"_id":264,"identity":275,"providers":276,"workflow":472},1778683785537.182,{"githubOwner":243,"githubRepo":244,"sourceUrl":14},{"classify":277,"discover":461,"github":464},{"commitSha":259,"extensions":278},[279,327,333,341,349,357,365,373,381,389,397,405,413,421,429,437,445,453],{"basePath":254,"description":251,"displayName":244,"installMethods":280,"rationale":281,"selectedPaths":282,"source":326,"sourceLanguage":18,"type":255},{"claudeCode":244},"plugin manifest at .claude-plugin/plugin.json",[283,286,288,291,294,296,298,300,302,304,306,308,310,312,314,316,318,320,322,324],{"path":284,"priority":285},".claude-plugin/plugin.json","mandatory",{"path":287,"priority":285},"README.md",{"path":289,"priority":290},"LICENSE","high",{"path":292,"priority":293},"skills/babysit-pr/SKILL.md","medium",{"path":295,"priority":293},"skills/capture-knowledge/SKILL.md",{"path":297,"priority":293},"skills/change-validation-planner/SKILL.md",{"path":299,"priority":293},"skills/create-skill/SKILL.md",{"path":301,"priority":293},"skills/docs-drift-audit/SKILL.md",{"path":303,"priority":293},"skills/incident-followup-audit/SKILL.md",{"path":305,"priority":293},"skills/init/SKILL.md",{"path":307,"priority":293},"skills/merged-pr-monitoring/SKILL.md",{"path":309,"priority":293},"skills/observability-gap-hunt/SKILL.md",{"path":311,"priority":293},"skills/ownership-risk-map/SKILL.md",{"path":313,"priority":293},"skills/performance-hunt/SKILL.md",{"path":315,"priority":293},"skills/pr-risk-review/SKILL.md",{"path":317,"priority":293},"skills/recent-commit-bug-hunt/SKILL.md",{"path":319,"priority":293},"skills/refactor-opportunities/SKILL.md",{"path":321,"priority":293},"skills/repo-introspection/SKILL.md",{"path":323,"priority":293},"skills/security-audit/SKILL.md",{"path":325,"priority":293},"skills/test-gap-hunt/SKILL.md","rule",{"basePath":242,"description":10,"displayName":13,"installMethods":328,"rationale":329,"selectedPaths":330,"source":326,"sourceLanguage":18,"type":245},{"claudeCode":12},"SKILL.md frontmatter at skills/babysit-pr/SKILL.md",[331],{"path":332,"priority":285},"SKILL.md",{"basePath":334,"description":335,"displayName":336,"installMethods":337,"rationale":338,"selectedPaths":339,"source":326,"sourceLanguage":18,"type":245},"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",[340],{"path":332,"priority":285},{"basePath":342,"description":343,"displayName":344,"installMethods":345,"rationale":346,"selectedPaths":347,"source":326,"sourceLanguage":18,"type":245},"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",[348],{"path":332,"priority":285},{"basePath":350,"description":351,"displayName":352,"installMethods":353,"rationale":354,"selectedPaths":355,"source":326,"sourceLanguage":18,"type":245},"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",[356],{"path":332,"priority":285},{"basePath":358,"description":359,"displayName":360,"installMethods":361,"rationale":362,"selectedPaths":363,"source":326,"sourceLanguage":18,"type":245},"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",[364],{"path":332,"priority":285},{"basePath":366,"description":367,"displayName":368,"installMethods":369,"rationale":370,"selectedPaths":371,"source":326,"sourceLanguage":18,"type":245},"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",[372],{"path":332,"priority":285},{"basePath":374,"description":375,"displayName":376,"installMethods":377,"rationale":378,"selectedPaths":379,"source":326,"sourceLanguage":18,"type":245},"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",[380],{"path":332,"priority":285},{"basePath":382,"description":383,"displayName":384,"installMethods":385,"rationale":386,"selectedPaths":387,"source":326,"sourceLanguage":18,"type":245},"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",[388],{"path":332,"priority":285},{"basePath":390,"description":391,"displayName":392,"installMethods":393,"rationale":394,"selectedPaths":395,"source":326,"sourceLanguage":18,"type":245},"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",[396],{"path":332,"priority":285},{"basePath":398,"description":399,"displayName":400,"installMethods":401,"rationale":402,"selectedPaths":403,"source":326,"sourceLanguage":18,"type":245},"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",[404],{"path":332,"priority":285},{"basePath":406,"description":407,"displayName":408,"installMethods":409,"rationale":410,"selectedPaths":411,"source":326,"sourceLanguage":18,"type":245},"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",[412],{"path":332,"priority":285},{"basePath":414,"description":415,"displayName":416,"installMethods":417,"rationale":418,"selectedPaths":419,"source":326,"sourceLanguage":18,"type":245},"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",[420],{"path":332,"priority":285},{"basePath":422,"description":423,"displayName":424,"installMethods":425,"rationale":426,"selectedPaths":427,"source":326,"sourceLanguage":18,"type":245},"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",[428],{"path":332,"priority":285},{"basePath":430,"description":431,"displayName":432,"installMethods":433,"rationale":434,"selectedPaths":435,"source":326,"sourceLanguage":18,"type":245},"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",[436],{"path":332,"priority":285},{"basePath":438,"description":439,"displayName":440,"installMethods":441,"rationale":442,"selectedPaths":443,"source":326,"sourceLanguage":18,"type":245},"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",[444],{"path":332,"priority":285},{"basePath":446,"description":447,"displayName":448,"installMethods":449,"rationale":450,"selectedPaths":451,"source":326,"sourceLanguage":18,"type":245},"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",[452],{"path":332,"priority":285},{"basePath":454,"description":455,"displayName":456,"installMethods":457,"rationale":458,"selectedPaths":459,"source":326,"sourceLanguage":18,"type":245},"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",[460],{"path":332,"priority":285},{"sources":462},[463],"manual",{"closedIssues90d":8,"description":465,"forks":8,"homepage":466,"license":237,"openIssues90d":8,"pushedAt":234,"readmeSize":231,"stars":235,"topics":467},"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/",[468,469,470,217,471],"agent-skills","claude-code","claude-plugins","codex",{"classifiedAt":473,"discoverAt":474,"extractAt":475,"githubAt":475,"updatedAt":473},1778683789715,1778683785537,1778683787839,[215,216,217,213,214],{"evaluatedAt":240,"extractAt":267,"updatedAt":240},[],[480,508,537,563,583,612],{"_creationTime":481,"_id":482,"community":483,"display":484,"identity":490,"providers":495,"relations":502,"tags":504,"workflow":505},1778697652123.8804,"k173mjn1bp2a67v1h8qjkv7wn186met8",{"reviewCount":8},{"description":485,"installMethods":486,"name":488,"sourceUrl":489},"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":487},"steipete/clawdis","ClawSweeper Skill","https://github.com/steipete/clawdis",{"basePath":491,"githubOwner":492,"githubRepo":493,"locale":18,"slug":494,"type":245},".agents/skills/clawsweeper","steipete","clawdis","clawsweeper",{"evaluate":496,"extract":501},{"promptVersionExtension":206,"promptVersionScoring":207,"score":497,"tags":498,"targetMarket":218,"tier":500},100,[213,215,217,499,216],"maintenance","verified",{"commitSha":259,"license":237},{"repoId":503},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[215,216,217,213,499],{"evaluatedAt":506,"extractAt":507,"updatedAt":506},1778697688364,1778697652123,{"_creationTime":509,"_id":510,"community":511,"display":512,"identity":518,"providers":522,"relations":530,"tags":533,"workflow":534},1778695548458.3926,"k172f2ed2j5kxdq8hbw4nszcw186m5xj",{"reviewCount":8},{"description":513,"installMethods":514,"name":516,"sourceUrl":517},"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":515},"pjt222/agent-almanac","review-pull-request","https://github.com/pjt222/agent-almanac",{"basePath":519,"githubOwner":520,"githubRepo":521,"locale":18,"slug":516,"type":245},"skills/review-pull-request","pjt222","agent-almanac",{"evaluate":523,"extract":529},{"promptVersionExtension":206,"promptVersionScoring":207,"score":497,"tags":524,"targetMarket":218,"tier":500},[525,214,213,217,526,527,528],"review","gh-cli","feedback","pr",{"commitSha":259},{"parentExtensionId":531,"repoId":532},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[217,527,526,213,528,214,525],{"evaluatedAt":535,"extractAt":536,"updatedAt":535},1778700796502,1778695548458,{"_creationTime":538,"_id":539,"community":540,"display":541,"identity":547,"providers":551,"relations":557,"tags":559,"workflow":560},1778696691708.3008,"k17fayzd1zy2hnd48zygbrmd3586myqe",{"reviewCount":8},{"description":542,"installMethods":543,"name":545,"sourceUrl":546},"Comprehensive GitHub code review with AI-powered swarm coordination",{"claudeCode":544},"ruvnet/ruflo","github-code-review","https://github.com/ruvnet/ruflo",{"basePath":548,"githubOwner":549,"githubRepo":550,"locale":18,"slug":545,"type":245},".claude/skills/github-code-review","ruvnet","ruflo",{"evaluate":552,"extract":556},{"promptVersionExtension":206,"promptVersionScoring":207,"score":553,"tags":554,"targetMarket":218,"tier":500},99,[213,217,555,215,216],"ai",{"commitSha":259},{"repoId":558},"kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[555,215,216,217,213],{"evaluatedAt":561,"extractAt":562,"updatedAt":561},1778699000157,1778696691708,{"_creationTime":564,"_id":565,"community":566,"display":567,"identity":571,"providers":573,"relations":579,"tags":580,"workflow":581},1778695548458.3474,"k1730fbw3hyx274fzsesckx2bs86nqph",{"reviewCount":8},{"description":568,"installMethods":569,"name":570,"sourceUrl":517},"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":515},"create-pull-request",{"basePath":572,"githubOwner":520,"githubRepo":521,"locale":18,"slug":570,"type":245},"skills/create-pull-request",{"evaluate":574,"extract":578},{"promptVersionExtension":206,"promptVersionScoring":207,"score":553,"tags":575,"targetMarket":218,"tier":500},[213,214,576,577,217,215],"git","collaboration",{"commitSha":259},{"parentExtensionId":531,"repoId":532},[215,217,577,576,213,214],{"evaluatedAt":582,"extractAt":536,"updatedAt":582},1778697203799,{"_creationTime":584,"_id":585,"community":586,"display":587,"identity":593,"providers":597,"relations":605,"tags":608,"workflow":609},1778699234184.611,"k179b6dkc777g1rgyecze04wqn86m6y4",{"reviewCount":8},{"description":588,"installMethods":589,"name":591,"sourceUrl":592},"Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly",{"claudeCode":590},"Yeachan-Heo/oh-my-claudecode","oh-my-claudecode","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":594,"githubOwner":595,"githubRepo":591,"locale":18,"slug":596,"type":245},"skills/ask","Yeachan-Heo","ask",{"evaluate":598,"extract":604},{"promptVersionExtension":206,"promptVersionScoring":207,"score":497,"tags":599,"targetMarket":218,"tier":500},[600,215,601,602,217,603],"cli","llm","prompting","artifact-generation",{"commitSha":259,"license":237},{"parentExtensionId":606,"repoId":607},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[603,215,600,217,601,602],{"evaluatedAt":610,"extractAt":611,"updatedAt":610},1778699303045,1778699234184,{"_creationTime":613,"_id":614,"community":615,"display":616,"identity":619,"providers":621,"relations":627,"tags":628,"workflow":629},1778697652123.8928,"k171pew5empzzrfghyg9nqrk6n86nqa9",{"reviewCount":8},{"description":617,"installMethods":618,"name":213,"sourceUrl":489},"Use gh for GitHub issues, PR status, CI/logs, comments, reviews, releases, and API queries.",{"claudeCode":487},{"basePath":620,"githubOwner":492,"githubRepo":493,"locale":18,"slug":213,"type":245},"skills/github",{"evaluate":622,"extract":626},{"promptVersionExtension":206,"promptVersionScoring":207,"score":497,"tags":623,"targetMarket":218,"tier":500},[213,600,624,625,215],"api","developer-tools",{"commitSha":259},{"repoId":503},[624,215,600,625,213],{"evaluatedAt":630,"extractAt":507,"updatedAt":630},1778698569289]