[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-j4rk0r-skill-learner-en":3,"guides-for-j4rk0r-skill-learner":422,"similar-k17b92m937rpcpsdzk2tpkbx1186n7d4-en":423},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":242,"isFallback":229,"parentExtension":247,"providers":248,"relations":253,"repo":255,"tags":418,"workflow":419},1778691193352.519,"k17b92m937rpcpsdzk2tpkbx1186n7d4",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Persistent correction system that captures mistakes from skills or Claude behavior and ensures they never repeat across sessions. Use whenever the user indicates something went wrong — \"that's wrong\", \"fix this\", \"not what I wanted\", \"learn from this\", \"don't do that again\", \"esto está mal\", \"aprende de esto\", \"no hagas eso otra vez\", or any correction, complaint, or teaching moment about Claude's output or a skill's behavior. Also use when the user asks to review, list, delete, or manage past corrections, or wants to create an improvement proposal for a skill author. Covers installed skills, general Claude behavior, and cross-session learning persistence.\n",{"claudeCode":12},"j4rk0r/claude-skills","skill-learner","https://github.com/j4rk0r/claude-skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":227,"workflow":240},1778691334993.0925,"kn7a67v7c3m2330acqvt1cfrk186m2n8","en",{"checks":20,"evaluatedAt":193,"extensionSummary":194,"features":195,"nonGoals":201,"promptVersionExtension":207,"promptVersionScoring":208,"purpose":209,"rationale":210,"score":211,"summary":212,"tags":213,"targetMarket":220,"tier":221,"useCases":222},[21,26,29,32,36,39,43,47,50,53,57,61,65,69,72,75,78,81,84,87,91,95,99,104,108,111,115,118,122,125,128,131,134,137,140,144,148,151,154,158,161,164,167,170,174,177,180,183,186,190],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly identifies the problem of persistent mistakes from skills or Claude behavior that repeat across sessions, and specifies trigger phrases for corrections.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers significant value beyond default behavior by capturing and persisting corrections, reducing future errors and optionally generating improvement proposals.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill covers the complete lifecycle of capturing, storing, and applying corrections across sessions, with clear documentation and management commands.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill has a clear, singular focus on managing persistent corrections for skills and general Claude behavior.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's functionality as detailed in the SKILL.md, including its scope and trigger conditions.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill utilizes specific tools like Read, Edit, Write, and Glob, which are narrowly scoped for managing correction files.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","The SKILL.md details the file structure, storage locations, and workflow steps, providing sufficient reference for usage.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","The tools implied by the SKILL.md, such as file operations (Read, Edit, Write, Glob) and management commands, are descriptive.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","The skill interacts with a defined set of files and directories within its scope and uses management commands for specific actions, avoiding excessive I/O.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The extension is licensed under the MIT license, which is permissive and widely usable.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The last commit was on April 13, 2026, indicating recent maintenance.",{"category":58,"check":62,"severity":63,"summary":64},"Dependency Management","not_applicable","The skill does not appear to use third-party dependencies beyond standard file operations and potential Claude internal tools.",{"category":66,"check":67,"severity":24,"summary":68},"Security","Secret Management","The skill operates on local files within its designated directory and does not handle or expose secrets.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill interacts with local files based on explicit commands and user input, with no indication of loading or executing untrusted external data as instructions.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill operates on local files and does not fetch external content or execute remote scripts.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill manages corrections within the `~/.claude/skill-corrections/` directory and does not appear to modify files outside its designated scope.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","There are no indications of detached processes or retry loops around denied tool calls in the provided documentation.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill operates locally and does not submit any user data or confidential information to third parties.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled content and documentation do not exhibit hidden steering tricks, Unicode tags, or control characters.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The skill's logic appears to be directly interpretable from the SKILL.md and file management descriptions, with no evidence of obfuscation like base64 payloads or runtime script fetching.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The skill operates within its own designated directory structure, avoiding assumptions about user-specific project organization.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","There are 0 issues opened and 0 issues closed in the last 90 days, indicating either a new skill or inactive maintenance, which is acceptable given the score.",{"category":100,"check":101,"severity":102,"summary":103},"Versioning","Release Management","info","No explicit versioning is declared in the SKILL.md frontmatter or manifest, and installation instructions reference main, but this is a common pattern for Claude skills.",{"category":105,"check":106,"severity":24,"summary":107},"Execution","Validation","The skill's operations involve file management based on user-provided commands and paths within a controlled directory, implying validation of these inputs.",{"category":66,"check":109,"severity":24,"summary":110},"Unguarded Destructive Operations","File operations like delete and archive are managed through explicit commands and occur within the skill's dedicated directory, with user confirmation implied for management actions.",{"category":112,"check":113,"severity":24,"summary":114},"Code Execution","Error Handling","The documentation implies that operations are categorized and reported, with clear directives for user interaction, suggesting robust error handling.",{"category":112,"check":116,"severity":63,"summary":117},"Logging","The skill's primary function is managing local correction files, and extensive logging is not a typical requirement for such a utility.",{"category":119,"check":120,"severity":24,"summary":121},"Compliance","GDPR","The skill operates on local files and does not process personal data beyond what is necessary for managing corrections.",{"category":119,"check":123,"severity":24,"summary":124},"Target market","The skill operates locally and does not have any regional or jurisdictional limitations.",{"category":92,"check":126,"severity":24,"summary":127},"Runtime stability","The skill relies on standard file operations and commands, making it portable across POSIX-compliant systems.",{"category":44,"check":129,"severity":24,"summary":130},"README","The README file clearly describes the skill's purpose, features, and installation instructions.",{"category":33,"check":132,"severity":63,"summary":133},"Tool surface size","This is a single-function skill, not a collection of distinct tools.",{"category":40,"check":135,"severity":24,"summary":136},"Overlapping near-synonym tools","The skill's operations are distinct and do not present overlapping near-synonym commands.",{"category":44,"check":138,"severity":24,"summary":139},"Phantom features","All features described in the README and SKILL.md have corresponding functionality outlined in the documentation and workflow.",{"category":141,"check":142,"severity":24,"summary":143},"Install","Installation instruction","The README provides clear installation instructions and an example invocation.",{"category":145,"check":146,"severity":24,"summary":147},"Errors","Actionable error messages","The SKILL.md emphasizes the importance of clear error reporting and user feedback, suggesting actionable error messages are implemented.",{"category":105,"check":149,"severity":63,"summary":150},"Pinned dependencies","The skill does not appear to rely on external dependencies that would require pinning.",{"category":33,"check":152,"severity":63,"summary":153},"Dry-run preview","The skill's operations are primarily file management within a dedicated directory, and destructive operations are guarded by explicit commands and user interaction, making a dry-run less applicable.",{"category":155,"check":156,"severity":63,"summary":157},"Protocol","Idempotent retry & timeouts","The skill operates locally with file system interactions and does not involve remote calls or state-changing operations that would require idempotency or timeouts.",{"category":66,"check":159,"severity":24,"summary":160},"Telemetry opt-in","There is no mention of telemetry being emitted by this skill.",{"category":40,"check":162,"severity":24,"summary":163},"Precise Purpose","The description clearly states the skill's purpose (persistent correction system) and when to use it (user indicates mistakes or complaints), with explicit non-goals.",{"category":40,"check":165,"severity":24,"summary":166},"Concise Frontmatter","The frontmatter is concise and effectively summarizes the core capability and trigger phrases.",{"category":44,"check":168,"severity":24,"summary":169},"Concise Body","The SKILL.md is well-structured with clear sections and delegates deeper material to references, keeping the main body concise.",{"category":171,"check":172,"severity":24,"summary":173},"Context","Progressive Disclosure","The SKILL.md outlines the workflow and links to `references/correction-patterns.md` for detailed procedures.",{"category":171,"check":175,"severity":63,"summary":176},"Forked exploration","The skill does not involve deep exploration or code review that would necessitate forked context.",{"category":22,"check":178,"severity":24,"summary":179},"Usage examples","The SKILL.md provides clear examples for correction file templates, severity decision trees, and scope calibration, enabling practical application.",{"category":22,"check":181,"severity":24,"summary":182},"Edge cases","The SKILL.md addresses edge cases like user correction errors, multiple skill applications, and behavior correction, with recovery steps.",{"category":112,"check":184,"severity":63,"summary":185},"Tool Fallback","This skill does not rely on external tools like MCP servers, operating on local file system functions.",{"category":187,"check":188,"severity":24,"summary":189},"Safety","Halt on unexpected state","The documentation emphasizes the importance of clear pre-state conditions and meticulous saving of corrections, implying a halt on unexpected states.",{"category":92,"check":191,"severity":24,"summary":192},"Cross-skill coupling","The skill is self-contained and does not implicitly rely on other skills; coordination with other skills is explicit when needed (e.g., generating proposals).",1778691334814,"This skill acts as a persistent correction system, capturing mistakes made by skills or general Claude behavior to prevent repetition across sessions. It allows users to teach the AI by providing specific feedback, managing past corrections, and optionally creating improvement proposals for skill authors.",[196,197,198,199,200],"Captures and persists skill and general AI behavior mistakes","Supports user corrections via specific feedback and trigger phrases","Manages past corrections (review, delete, list)","Optionally generates improvement proposals for skill authors","Operates across sessions and conversational contexts",[202,203,204,205,206],"Saving vague corrections without specific alternatives.","Creating duplicate corrections for the same issue.","Saving one-time preferences as universal rules without scope clarification.","Exceeding a defined limit of active corrections to maintain performance.","Saving corrections that bypass safety measures like input validation or authorization checks.","3.0.0","4.4.0","To ensure that mistakes made by AI skills or general AI behavior are captured, understood, and prevented from recurring in future sessions, leading to a more reliable and personalized AI experience.","The skill is exceptionally well-documented, robust, and addresses a clear user need with a well-defined workflow and safety mechanisms. All checks passed with high severity ratings.",99,"A robust skill for capturing and persisting corrections to improve AI behavior across sessions.",[214,215,216,217,218,219],"learning","corrections","persistence","skills","behavioral-tuning","auditing","global","verified",[223,224,225,226],"When the user indicates something went wrong with a skill's output.","When the user provides feedback on general Claude behavior that should be remembered.","When the user wants to review or manage past corrections made to the AI's behavior.","When the user wants to suggest improvements to a skill author based on observed mistakes.",{"codeQuality":228,"collectedAt":230,"documentation":231,"maintenance":234,"security":237,"testCoverage":239},{"hasLockfile":229},false,1778691315556,{"descriptionLength":232,"readmeSize":233},665,26542,{"closedIssues90d":8,"forks":8,"hasChangelog":229,"openIssues90d":8,"pushedAt":235,"stars":236},1776088077000,2,{"hasNpmPackage":229,"license":238,"smitheryVerified":229},"MIT",{"hasCi":229,"hasTests":229},{"updatedAt":241},1778691334993,{"basePath":243,"githubOwner":244,"githubRepo":245,"locale":18,"slug":13,"type":246},"skills/skill-learner","j4rk0r","claude-skills","skill",null,{"evaluate":249,"extract":251},{"promptVersionExtension":207,"promptVersionScoring":208,"score":211,"tags":250,"targetMarket":220,"tier":221},[214,215,216,217,218,219],{"commitSha":252},"HEAD",{"repoId":254},"kd79shaph0e07035621cxd7x1n86m944",{"_creationTime":256,"_id":254,"identity":257,"providers":258,"workflow":414},1778689957073.3262,{"githubOwner":244,"githubRepo":245,"sourceUrl":14},{"classify":259,"discover":401,"github":404},{"commitSha":252,"extensions":260},[261,293,310,331,356,369,380,387],{"basePath":262,"description":263,"displayName":264,"installMethods":265,"rationale":266,"selectedPaths":267,"source":291,"sourceLanguage":292,"type":246},"skills/codex-diff-develop","Revisa el diff de la rama actual frente a develop en proyectos Drupal 11 siguiendo la metodología Codex (lógica de negocio, edge cases de hooks/queries, seguridad, performance, completitud). Genera un informe .md en la carpeta del IDE detectado (.antigravity/, .cursor/, .vscode/ o docs/) con hallazgos por severidad y soluciones accionables. Usar cuando el usuario pida \"Revisión diff develop\", \"revisión diff develop\", \"diff develop\", \"revisar diff\", \"codex diff\" o expresiones similares con intención de auditar cambios contra develop. Triggers: diff develop, codex diff, revisión diff, lint diff develop, auditar diff.","codex-diff-develop",{"claudeCode":12},"SKILL.md frontmatter at skills/codex-diff-develop/SKILL.md",[268,271,274,277,279,281,283,285,287,289],{"path":269,"priority":270},"SKILL.md","mandatory",{"path":272,"priority":273},"README.md","high",{"path":275,"priority":276},"README.de.md","medium",{"path":278,"priority":276},"README.es.md",{"path":280,"priority":276},"README.fr.md",{"path":282,"priority":276},"README.ja.md",{"path":284,"priority":276},"README.pt.md",{"path":286,"priority":276},"README.zh.md",{"path":288,"priority":276},"references/metodologia-codex-completa.md",{"path":290,"priority":276},"references/plantillas-hallazgos.md","rule","es",{"basePath":294,"description":295,"displayName":296,"installMethods":297,"rationale":298,"selectedPaths":299,"source":291,"sourceLanguage":292,"type":246},"skills/codex-pr-review","Revisa pull requests en proyectos Drupal 11 (u otro) siguiendo la metodología Codex (lógica de negocio, edge cases de hooks/queries, seguridad, performance, completitud). Genera un informe .md en la carpeta del IDE detectado (.antigravity/, .cursor/, .vscode/ o docs/) con hallazgos por severidad y soluciones accionables. Usar cuando el usuario pida \"revisión Codex\", \"revisión de PR\", \"revisar PR\", \"revisar PR","codex-pr-review",{"claudeCode":12},"SKILL.md frontmatter at skills/codex-pr-review/SKILL.md",[300,301,302,303,304,305,306,307,308,309],{"path":269,"priority":270},{"path":272,"priority":273},{"path":275,"priority":276},{"path":278,"priority":276},{"path":280,"priority":276},{"path":282,"priority":276},{"path":284,"priority":276},{"path":286,"priority":276},{"path":288,"priority":276},{"path":290,"priority":276},{"basePath":311,"description":312,"displayName":313,"installMethods":314,"rationale":315,"selectedPaths":316,"source":291,"sourceLanguage":292,"type":246},"skills/lint-drupal-module","Lint review completo de un módulo Drupal 11 combinando 4 fuentes en paralelo — PHPStan level 5 + phpstan-drupal, PHPCS Drupal/DrupalPractice, agente drupal-qa (estándares) y agente drupal-security (OWASP). Dos modos — completo (todo el módulo) y diff (solo archivos cambiados vs develop). Genera informe markdown estructurado en la carpeta del IDE con resumen ejecutivo, hallazgos clasificados por severidad, acciones P0/P1/P2 y comandos de verificación. Úsalo siempre que el usuario quiera auditar calidad o seguridad de un módulo Drupal custom, aunque no diga \"lint\". Triggers — \"lint review\", \"lint del módulo\", \"auditar módulo Drupal\", \"revisar módulo custom\", \"phpstan del módulo\", \"validar módulo\", \"qa del módulo\", o cuando el usuario pregunta \"¿está bien este módulo?\", \"¿hay errores?\", \"¿es seguro?\". También antes de un release, antes de un PR a develop, o al validar un módulo recién creado.","lint-drupal-module",{"claudeCode":12},"SKILL.md frontmatter at skills/lint-drupal-module/SKILL.md",[317,318,319,320,321,322,323,324,325,327,329],{"path":269,"priority":270},{"path":272,"priority":273},{"path":275,"priority":276},{"path":278,"priority":276},{"path":280,"priority":276},{"path":282,"priority":276},{"path":284,"priority":276},{"path":286,"priority":276},{"path":326,"priority":276},"references/edge-cases.md",{"path":328,"priority":276},"references/plantilla-informe.md",{"path":330,"priority":276},"references/prompts-agentes.md",{"basePath":332,"description":333,"displayName":334,"installMethods":335,"rationale":336,"selectedPaths":337,"source":291,"sourceLanguage":292,"type":246},"skills/milestone","Persistent development milestone tracker with full context across conversations. Use when: tracking multi-session features, resuming work from a previous conversation, asking 'what's left to do on X' or 'what's pending', breaking work into trackable subtasks, planning complex implementations, updating progress after coding, checking project status, completing a subtask with QA validation, auditing what's missing in the project, syncing milestones with actual code state, or closing/archiving a finished milestone. Also trigger when user references a milestone by name, says 'what did we do last time', 'resume where we left off', 'how far along is X', 'mark this as done', 'milestone done', 'close this milestone', 'what's missing', 'audit the project', 'sync milestones', or wants to plan a feature with subtasks. Commands: /milestone, /milestone \u003Cname>, /milestone init, /milestone sync, /milestone start, /milestone done, /milestone update.","milestone",{"claudeCode":12},"SKILL.md frontmatter at skills/milestone/SKILL.md",[338,339,340,341,342,343,344,345,346,348,350,352,354],{"path":269,"priority":270},{"path":272,"priority":273},{"path":275,"priority":276},{"path":278,"priority":276},{"path":280,"priority":276},{"path":282,"priority":276},{"path":284,"priority":276},{"path":286,"priority":276},{"path":347,"priority":276},"references/errors.md",{"path":349,"priority":276},"references/milestone-new-session.sh",{"path":351,"priority":276},"references/project-audit.md",{"path":353,"priority":276},"references/qa-validation.md",{"path":355,"priority":276},"references/templates.md",{"basePath":357,"description":358,"displayName":359,"installMethods":360,"rationale":361,"selectedPaths":362,"source":291,"sourceLanguage":18,"type":246},"skills/skill-advisor","Pre-execution assistant that builds a full execution plan with installed skills (✅) AND uninstalled gaps (❌) the task needs, then offers to install missing skills one by one. Use BEFORE starting any multi-step task. Triggers: 'recommend skills', 'what skill should I use', 'advise', 'suggest', 'help me with', or any work instruction involving code, design, planning, debugging, docs, testing, commits, PRs, strategy.","skill-advisor",{"claudeCode":12},"SKILL.md frontmatter at skills/skill-advisor/SKILL.md",[363,364,365,367],{"path":269,"priority":270},{"path":272,"priority":273},{"path":366,"priority":276},"references/gap-maps.md",{"path":368,"priority":276},"references/pipelines.md",{"basePath":370,"description":371,"displayName":372,"installMethods":373,"rationale":374,"selectedPaths":375,"source":291,"sourceLanguage":18,"type":246},"skills/skill-guard","Security auditor for Claude Code skills. Analyzes skills BEFORE installation using a 9-layer threat detection engine (permissions, static patterns, LLM semantic analysis, bundled scripts, data flow, MCP abuse, supply chain, reputation, anti-evasion) with scoring 0-100 and community audit registry. MUST be used whenever the user is about to install a skill — via npx skills add, /find-skills recommendation, /skill-advisor suggestion, or manual request. Also use when user says 'is this skill safe', 'audit this skill', 'check this skill', 'security scan', 'review before installing', or any mention of skill safety/trust/security. Intercept ALL skill installations proactively.","skill-guard",{"claudeCode":12},"SKILL.md frontmatter at skills/skill-guard/SKILL.md",[376,377,378],{"path":269,"priority":270},{"path":272,"priority":273},{"path":379,"priority":276},"references/patterns.md",{"basePath":243,"description":10,"displayName":13,"installMethods":381,"rationale":382,"selectedPaths":383,"source":291,"sourceLanguage":18,"type":246},{"claudeCode":12},"SKILL.md frontmatter at skills/skill-learner/SKILL.md",[384,385],{"path":269,"priority":270},{"path":386,"priority":276},"references/correction-patterns.md",{"basePath":388,"description":389,"displayName":390,"installMethods":391,"rationale":392,"selectedPaths":393,"source":291,"sourceLanguage":292,"type":246},"skills/usage-tracker","Track and report local Claude Code usage per request: tokens consumed, estimated cost in €, sessions, projects, and tool breakdown. Use when the user asks about consumption, credits, usage, cost per request, wants to see a report, asks why a specific request was expensive, suspects a process is consuming tokens, wants to optimize their Claude Code usage, or wants to audit tool usage by request. Also triggers on Spanish phrases: 'cuánto me está costando', 'cuántos tokens', 'consumo de hoy', 'qué petición fue cara', 'está consumiendo mucho', 'optimizar consumo', 'reporte de uso', 'ver uso', 'instalar tracker', 'hook no registra'. Commands: /usage-tracker report [hoy|semana|mes|all] [proyecto], /usage-tracker top-requests [hoy|semana], /usage-tracker install, /usage-tracker status","usage-tracker",{"claudeCode":12},"SKILL.md frontmatter at skills/usage-tracker/SKILL.md",[394,395,397,399],{"path":269,"priority":270},{"path":396,"priority":276},"references/log-usage.sh",{"path":398,"priority":276},"references/pricing.md",{"path":400,"priority":276},"references/usage-report.sh",{"sources":402},[403],"manual",{"closedIssues90d":8,"description":405,"forks":8,"homepage":406,"license":238,"openIssues90d":8,"pushedAt":235,"readmeSize":233,"stars":236,"topics":407},"Curated high-quality skills for Claude Code — skill-advisor and more","https://claude-skills-omega.vercel.app",[408,409,410,411,412,245,413,359],"agent-skills","ai-tools","anthropic","claude","claude-code","developer-tools",{"classifiedAt":415,"discoverAt":416,"extractAt":417,"githubAt":417,"updatedAt":415},1778691193146,1778689957073,1778691191083,[219,218,215,214,216,217],{"evaluatedAt":241,"extractAt":420,"updatedAt":421},1778691193352,1778691485659,[],[424,453,472,501,531,559],{"_creationTime":425,"_id":426,"community":427,"display":428,"identity":434,"providers":438,"relations":445,"tags":448,"workflow":449},1778691884319.067,"k177wxk7zzyaycd3t6ads36e7586mkcw",{"reviewCount":8},{"description":429,"installMethods":430,"name":432,"sourceUrl":433},"Full health check of all your skills in one report. Use when the user wants to check for errors, find duplicates, detect broken skills, or get a complete overview of skill health.",{"claudeCode":431},"khendzel/skills-janitor","janitor-report","https://github.com/khendzel/skills-janitor",{"basePath":435,"githubOwner":436,"githubRepo":437,"locale":18,"slug":432,"type":246},"skills/janitor-report","khendzel","skills-janitor",{"evaluate":439,"extract":444},{"promptVersionExtension":207,"promptVersionScoring":208,"score":440,"tags":441,"targetMarket":220,"tier":221},100,[217,442,219,443,413],"management","maintenance",{"commitSha":252},{"parentExtensionId":446,"repoId":447},"k173y287h96a0x42zvrvymzvgn86nq38","kd722xn3d2v8ze2vwgebvzgpv986mj48",[219,413,443,442,217],{"evaluatedAt":450,"extractAt":451,"updatedAt":452},1778692022779,1778691884319,1778692172820,{"_creationTime":454,"_id":455,"community":456,"display":457,"identity":461,"providers":463,"relations":467,"tags":468,"workflow":469},1778691884319.0662,"k17enbaydwffjeah1ncmnkn5y586ned0",{"reviewCount":8},{"description":458,"installMethods":459,"name":460,"sourceUrl":433},"Show all your installed skills",{"claudeCode":431},"janitor-audit",{"basePath":462,"githubOwner":436,"githubRepo":437,"locale":18,"slug":460,"type":246},"skills/janitor-audit",{"evaluate":464,"extract":466},{"promptVersionExtension":207,"promptVersionScoring":208,"score":440,"tags":465,"targetMarket":220,"tier":221},[217,442,219,443,413],{"commitSha":252},{"parentExtensionId":446,"repoId":447},[219,413,443,442,217],{"evaluatedAt":470,"extractAt":451,"updatedAt":471},1778691945236,1778692172117,{"_creationTime":473,"_id":474,"community":475,"display":476,"identity":482,"providers":487,"relations":495,"tags":497,"workflow":498},1778698371743.7043,"k179rk9j081qefqrd7ebwnx9yx86msv2",{"reviewCount":8},{"description":477,"installMethods":478,"name":480,"sourceUrl":481},"Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user)",{"claudeCode":479},"vectorize-io/hindsight","Hindsight Memory Skill","https://github.com/vectorize-io/hindsight",{"basePath":483,"githubOwner":484,"githubRepo":485,"locale":18,"slug":486,"type":246},"skills/hindsight-local","vectorize-io","hindsight","hindsight-local",{"evaluate":488,"extract":494},{"promptVersionExtension":207,"promptVersionScoring":208,"score":489,"tags":490,"targetMarket":220,"tier":221},98,[491,492,214,216,493],"memory","agent","llm",{"commitSha":252,"license":238},{"repoId":496},"kd7etqyey7pjacrkp7wzfh4vts86nq1z",[492,214,493,491,216],{"evaluatedAt":499,"extractAt":500,"updatedAt":499},1778698529103,1778698371743,{"_creationTime":502,"_id":503,"community":504,"display":505,"identity":511,"providers":515,"relations":524,"tags":527,"workflow":528},1778695548458.3718,"k175vfqr247swcyt62e6v08a4x86mtf1",{"reviewCount":8},{"description":506,"installMethods":507,"name":509,"sourceUrl":510},"Investigate root causes and manage CAPAs (Corrective and Preventive Actions) for compliance deviations. Covers investigation method selection (5-Why, fishbone, fault tree), structured root cause analysis, corrective vs preventive action design, effectiveness verification, and trend analysis. Use when an audit finding requires a CAPA, when a deviation or incident occurs in a validated system, when a regulatory observation needs a formal response, when a data integrity anomaly requires investigation, or when recurring issues suggest a systemic root cause.\n",{"claudeCode":508},"pjt222/agent-almanac","investigate-capa-root-cause","https://github.com/pjt222/agent-almanac",{"basePath":512,"githubOwner":513,"githubRepo":514,"locale":18,"slug":509,"type":246},"skills/investigate-capa-root-cause","pjt222","agent-almanac",{"evaluate":516,"extract":523},{"promptVersionExtension":207,"promptVersionScoring":208,"score":440,"tags":517,"targetMarket":220,"tier":221},[518,519,520,521,522,219],"compliance","capa","investigation","root-cause-analysis","gxp",{"commitSha":252},{"parentExtensionId":525,"repoId":526},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[219,519,518,522,520,521],{"evaluatedAt":529,"extractAt":530,"updatedAt":529},1778699030088,1778695548458,{"_creationTime":532,"_id":533,"community":534,"display":535,"identity":541,"providers":545,"relations":553,"tags":555,"workflow":556},1778695753353.633,"k17fxb9fnez7bhk0sy8znxzx8n86m48r",{"reviewCount":8},{"description":536,"installMethods":537,"name":539,"sourceUrl":540},"Drift detection + baseline integrity guard for agent workspace files with automatic alerting support",{"claudeCode":538},"prompt-security/clawsec","soul-guardian","https://github.com/prompt-security/clawsec",{"basePath":542,"githubOwner":543,"githubRepo":544,"locale":18,"slug":539,"type":246},"skills/soul-guardian","prompt-security","clawsec",{"evaluate":546,"extract":552},{"promptVersionExtension":207,"promptVersionScoring":208,"score":440,"tags":547,"targetMarket":220,"tier":221},[548,549,219,550,551],"security","integrity","file-guard","workspace",{"commitSha":252},{"repoId":554},"kd72phsqkbk8w57ctvf7ac9nqs86n9t4",[219,550,549,548,551],{"evaluatedAt":557,"extractAt":558,"updatedAt":557},1778696065248,1778695753353,{"_creationTime":560,"_id":561,"community":562,"display":563,"identity":567,"providers":569,"relations":576,"tags":577,"workflow":578},1778695548458.3328,"k17cyw0d6mk1vdgew2xmncx1f186npdm",{"reviewCount":8},{"description":564,"installMethods":565,"name":566,"sourceUrl":510},"Audit project dependencies for version staleness, security vulnerabilities, and compatibility issues. Covers lock file analysis, upgrade path planning, and breaking change assessment. Use before a release to ensure dependencies are current and secure, during periodic maintenance reviews, after receiving a security advisory, when upgrading to a new language version, before submitting to CRAN or npm, or when inheriting a project to assess its dependency health.\n",{"claudeCode":508},"audit-dependency-versions",{"basePath":568,"githubOwner":513,"githubRepo":514,"locale":18,"slug":566,"type":246},"skills/audit-dependency-versions",{"evaluate":570,"extract":575},{"promptVersionExtension":207,"promptVersionScoring":208,"score":440,"tags":571,"targetMarket":220,"tier":221},[572,219,548,573,574,443],"dependencies","upgrades","versioning",{"commitSha":252},{"parentExtensionId":525,"repoId":526},[219,572,443,548,573,574],{"evaluatedAt":579,"extractAt":530,"updatedAt":579},1778696062378]