[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-mksglu-ctx-purge-en":3,"guides-for-mksglu-ctx-purge":586,"similar-k176tc1tv0m0nkcdcm07fy4vx186mcpz-en":587},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":249,"isFallback":238,"parentExtension":255,"providers":291,"relations":295,"repo":296,"tags":583,"workflow":584},1778693511416.366,"k176tc1tv0m0nkcdcm07fy4vx186mcpz",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Purge the context-mode knowledge base. Permanently deletes all indexed content\nand resets session stats. This is destructive and cannot be undone.\nTrigger: /context-mode:ctx-purge\n",{"claudeCode":12},"mksglu/context-mode","Context Mode Purge","https://github.com/mksglu/context-mode",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":228,"workflow":247},1778693659975.197,"kn72qmxpvht8chr0tht3xrhs7s86mndf","en",{"checks":20,"evaluatedAt":191,"extensionSummary":192,"features":193,"nonGoals":198,"practices":202,"prerequisites":203,"promptVersionExtension":204,"promptVersionScoring":205,"purpose":206,"rationale":207,"score":208,"summary":209,"tags":210,"targetMarket":216,"tier":217,"useCases":218,"workflow":223},[21,26,29,32,36,39,43,47,50,53,57,61,64,69,72,75,78,81,84,87,90,94,98,102,106,109,112,115,119,122,125,128,131,134,137,141,145,149,152,156,159,162,165,168,172,175,178,181,184,188],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of purging the context-mode knowledge base and resetting session stats, identifying it as a destructive and irreversible action.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","This skill offers a critical utility for managing context data by providing a permanent deletion mechanism, which is a distinct and necessary function beyond simple LLM capabilities.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill is fully implemented and provides a crucial destructive operation, with clear instructions and scope definitions for project-wide or session-specific purges.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill is narrowly focused on purging context-mode knowledge base and session data, with well-defined scopes (project vs. session) and no unrelated capabilities.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's destructive and irreversible nature, clearly stating its purpose and trigger.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill exposes a single, well-scoped tool (`mcp__context-mode__ctx_purge`) with clear parameters for confirmation and scope selection.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","The SKILL.md clearly documents the required `confirm: true` parameter and the `sessionId` and `scope` options, along with their valid combinations and rejections.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","The tool name `mcp__context-mode__ctx_purge` is descriptive and follows the expected MCP naming convention.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","The tool's input schema is minimal, requiring only confirmation and scope/session identifiers, and its output lists deleted items, focusing solely on the purge operation's outcome.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The extension is licensed under Elastic License 2.0, which is a source-available license allowing use, modification, and distribution with specific limitations.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The repository shows recent commits, indicating active maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The project uses npm and appears to manage dependencies appropriately with lockfiles, as indicated by the presence of `package-lock.json` and `node_modules` in `.gitignore`.",{"category":65,"check":66,"severity":67,"summary":68},"Security","Secret Management","not_applicable","This skill does not handle or expose any secrets.",{"category":65,"check":70,"severity":24,"summary":71},"Injection","The skill operates on well-defined parameters and does not load external, untrusted data that could be subject to injection attacks.",{"category":65,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill does not fetch remote content or execute arbitrary code from external sources at runtime.",{"category":65,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill's operation is confined to managing internal data and does not involve file system modifications outside its defined scope.",{"category":65,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","No detached process spawns or retry loops around denied operations were detected in the skill's implementation.",{"category":65,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill's function is purely local and does not involve any outbound network calls or submission of data to third parties.",{"category":65,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled content is free of hidden steering tricks, control characters, or obfuscated instructions.",{"category":65,"check":88,"severity":24,"summary":89},"Opaque code execution","The skill's code is plain and readable, with no obfuscation, base64 payloads, or runtime script fetching.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The skill operates on internal data structures and does not make assumptions about the user's project file layout.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","The repository shows a healthy ratio of closed to open issues, indicating active maintenance and responsiveness to user reports.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","The project has a meaningful version declared in its `package.json` and uses Git tags, allowing for clear release tracking.",{"category":103,"check":104,"severity":24,"summary":105},"Code Execution","Validation","The tool's inputs are strictly validated parameters (`confirm`, `sessionId`, `scope`), preventing unexpected values.",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","The destructive operation is guarded by a mandatory `confirm: true` parameter and clear user prompts, with explicit scope selection preventing accidental data loss.",{"category":103,"check":110,"severity":24,"summary":111},"Error Handling","The skill handles errors by reporting specific outcomes, and the required `confirm: true` parameter ensures operations are not performed without explicit user consent.",{"category":103,"check":113,"severity":67,"summary":114},"Logging","This skill is a utility command and does not perform actions that require logging to a local audit file.",{"category":116,"check":117,"severity":67,"summary":118},"Compliance","GDPR","The skill operates solely on internal session and knowledge base data and does not handle personal data.",{"category":116,"check":120,"severity":24,"summary":121},"Target market","The skill is a local utility and has no regional or jurisdictional dependencies, making it globally applicable.",{"category":91,"check":123,"severity":24,"summary":124},"Runtime stability","The skill's installation and runtime requirements are standard Node.js, with clear build prerequisites documented for older systems.",{"category":44,"check":126,"severity":24,"summary":127},"README","The README provides a comprehensive overview of the context-mode project, its purpose, installation, and utility commands.",{"category":33,"check":129,"severity":67,"summary":130},"Tool surface size","This extension exposes only a single tool, which is within the acceptable range.",{"category":40,"check":132,"severity":67,"summary":133},"Overlapping near-synonym tools","The extension exposes only one tool, so there are no overlapping near-synonyms.",{"category":44,"check":135,"severity":24,"summary":136},"Phantom features","All advertised features, particularly the `ctx_purge` functionality, are directly implemented and accessible via the MCP tool.",{"category":138,"check":139,"severity":24,"summary":140},"Install","Installation instruction","The README provides detailed, copy-pasteable installation instructions for various platforms (Claude Code, Gemini CLI, VS Code Copilot, etc.) including verification steps.",{"category":142,"check":143,"severity":24,"summary":144},"Errors","Actionable error messages","The skill clearly communicates errors, such as invalid parameter combinations or the irreversible nature of the purge operation, prompting user confirmation.",{"category":146,"check":147,"severity":24,"summary":148},"Execution","Pinned dependencies","Dependencies are managed via npm lockfiles, ensuring reproducible builds.",{"category":33,"check":150,"severity":24,"summary":151},"Dry-run preview","The purge operation requires explicit confirmation via a parameter and user interaction, effectively serving as a 'dry-run preview' for this destructive action.",{"category":153,"check":154,"severity":24,"summary":155},"Protocol","Idempotent retry & timeouts","The purge operation is idempotent by nature as it's a destructive command; it does not involve remote calls requiring timeouts or retries.",{"category":116,"check":157,"severity":24,"summary":158},"Telemetry opt-in","The extension explicitly states that no telemetry is collected, aligning with a privacy-first philosophy.",{"category":40,"check":160,"severity":24,"summary":161},"Precise Purpose","The skill's purpose is precisely defined as purging context-mode knowledge base and session data, with clear triggers and scopes provided.",{"category":40,"check":163,"severity":24,"summary":164},"Concise Frontmatter","The frontmatter in SKILL.md is concise, clearly stating the name, description, and trigger for the `ctx-purge` tool.",{"category":44,"check":166,"severity":24,"summary":167},"Concise Body","The SKILL.md is well-structured, under 500 lines, and effectively delegates detailed information to other sections like 'Instructions' and 'Schema rules'.",{"category":169,"check":170,"severity":24,"summary":171},"Context","Progressive Disclosure","Detailed instructions and schema rules are presented inline within SKILL.md, with no need for external files for this specific tool's operation.",{"category":169,"check":173,"severity":67,"summary":174},"Forked exploration","This skill is a utility command and does not involve deep exploration or code review that would necessitate forked context.",{"category":22,"check":176,"severity":24,"summary":177},"Usage examples","The SKILL.md provides clear instructions on how to use the `ctx_purge` tool with specific parameters and scope selections.",{"category":22,"check":179,"severity":24,"summary":180},"Edge cases","The skill explicitly documents failure modes such as ambiguous parameter combinations and the irreversible nature of the operation, with recovery being user confirmation.",{"category":103,"check":182,"severity":67,"summary":183},"Tool Fallback","This skill is a self-contained tool and does not rely on external MCP servers or tools that would require fallbacks.",{"category":185,"check":186,"severity":24,"summary":187},"Safety","Halt on unexpected state","The operation requires explicit confirmation and parameter specification, inherently halting if the expected state (user confirmation) is not met.",{"category":91,"check":189,"severity":24,"summary":190},"Cross-skill coupling","The `ctx_purge` skill is standalone and does not implicitly rely on other skills being loaded in the same session.",1778693659554,"This skill provides a tool to permanently delete all indexed content and reset session statistics within the context-mode knowledge base, supporting both project-wide and session-specific purges.",[194,195,196,197],"Permanently deletes indexed content and session data","Supports project-wide scope for complete reset","Supports session-specific scope for targeted deletion","Requires explicit confirmation for destructive actions",[199,200,201],"Recovering deleted data after a purge","Modifying session statistics or knowledge base content","Deleting data via other mechanisms like /clear or /compact",[],[],"3.0.0","4.4.0","To provide a safe and controlled method for users to permanently clear their context-mode knowledge base and session data, ensuring a clean slate when needed.","The extension is well-documented, secure, and has a clear, single responsibility. The worst finding is 'not_applicable' for several checks that do not apply to a utility command, and 'pass' for all others.",99,"A robust and secure utility for purging context-mode knowledge bases, with excellent documentation and adherence to best practices.",[211,212,213,214,215],"context","knowledge-base","cleanup","data-management","utility","global","verified",[219,220,221,222],"When the knowledge base contains stale or incorrect content","To start fresh on a project without losing session statistics","To isolate a polluted session without affecting other sessions or project stats","To revert to a clean state before starting new, unrelated work",[224,225,226,227],"Decide the scope (project or session)","Warn the user about the irreversible nature of project scope purge","Call the `mcp__context-mode__ctx_purge` MCP tool with appropriate parameters","Report the result to the user, listing deleted items",{"codeQuality":229,"collectedAt":231,"documentation":232,"maintenance":235,"popularity":242,"security":244,"testCoverage":246},{"hasLockfile":230},true,1778693634423,{"descriptionLength":233,"readmeSize":234},180,76711,{"closedIssues90d":236,"forks":237,"hasChangelog":238,"openIssues90d":239,"pushedAt":240,"stars":241},240,1027,false,5,1778685749000,14607,{"npmDownloads":243},73627,{"hasNpmPackage":230,"license":245,"smitheryVerified":238},"NOASSERTION",{"hasCi":230,"hasTests":230},{"updatedAt":248},1778693659975,{"basePath":250,"githubOwner":251,"githubRepo":252,"locale":18,"slug":253,"type":254},"skills/ctx-purge","mksglu","context-mode","ctx-purge","skill",{"_creationTime":256,"_id":257,"community":258,"display":259,"identity":262,"parentExtension":265,"providers":266,"relations":284,"tags":286,"workflow":287},1778693511416.3647,"k17ezy748es7sfnbnp9phht43h86m53y",{"reviewCount":8},{"description":260,"installMethods":261,"name":252,"sourceUrl":14},"MCP server that saves 98% of your context window with session continuity. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and automatic state restore across compactions.",{"claudeCode":252},{"basePath":263,"githubOwner":251,"githubRepo":252,"locale":18,"slug":252,"type":264},"","plugin",null,{"evaluate":267,"extract":278},{"promptVersionExtension":204,"promptVersionScoring":205,"score":268,"tags":269,"targetMarket":216,"tier":217},98,[270,271,272,273,274,275,276,277],"mcp","context-window","sandbox","code-execution","fts5","bm25","session-continuity","typescript",{"commitSha":279,"license":280,"plugin":281},"HEAD","Elastic-2.0",{"mcpCount":8,"provider":282,"skillCount":283},"classify",6,{"repoId":285},"kd764b2fctbqg4b8j8y6xvmkvs86m29m",[275,273,271,274,270,272,276,277],{"evaluatedAt":288,"extractAt":289,"updatedAt":290},1778693549024,1778693511416,1778693816974,{"evaluate":292,"extract":294},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":293,"targetMarket":216,"tier":217},[211,212,213,214,215],{"commitSha":279,"license":245},{"parentExtensionId":257,"repoId":285},{"_creationTime":297,"_id":285,"identity":298,"providers":299,"workflow":578},1778693503750.4844,{"githubOwner":251,"githubRepo":252,"sourceUrl":14},{"classify":300,"discover":551,"extract":554,"github":555,"npm":577},{"commitSha":279,"extensions":301},[302,312,461,486,501,509,517,522,530,538],{"basePath":303,"displayName":252,"installMethods":304,"rationale":305,"selectedPaths":306,"source":310,"sourceLanguage":18,"type":311},".agents/plugins",{"claudeCode":12},"marketplace.json at .agents/plugins/marketplace.json (coalesced with duplicate marketplace at /)",[307],{"path":308,"priority":309},"marketplace.json","mandatory","rule","marketplace",{"basePath":263,"description":260,"displayName":252,"installMethods":313,"license":280,"rationale":314,"selectedPaths":315,"source":310,"sourceLanguage":18,"type":264},{"claudeCode":252},"plugin manifest at .claude-plugin/plugin.json",[316,318,320,323,326,328,330,332,334,336,339,341,343,345,347,349,351,353,355,357,359,361,363,365,367,369,371,373,375,377,379,381,383,385,387,389,391,393,395,397,399,401,403,405,407,409,411,413,415,417,419,421,423,425,427,429,431,433,435,437,439,441,443,445,447,449,451,453,455,457,459],{"path":317,"priority":309},".claude-plugin/plugin.json",{"path":319,"priority":309},"README.md",{"path":321,"priority":322},"LICENSE","high",{"path":324,"priority":325},"skills/context-mode/SKILL.md","medium",{"path":327,"priority":325},"skills/ctx-doctor/SKILL.md",{"path":329,"priority":325},"skills/ctx-insight/SKILL.md",{"path":331,"priority":325},"skills/ctx-purge/SKILL.md",{"path":333,"priority":325},"skills/ctx-stats/SKILL.md",{"path":335,"priority":325},"skills/ctx-upgrade/SKILL.md",{"path":337,"priority":338},"bin/statusline.mjs","low",{"path":340,"priority":322},"hooks/auto-injection.mjs",{"path":342,"priority":322},"hooks/cache-heal-utils.mjs",{"path":344,"priority":322},"hooks/codex/posttooluse.mjs",{"path":346,"priority":322},"hooks/codex/precompact.mjs",{"path":348,"priority":322},"hooks/codex/pretooluse.mjs",{"path":350,"priority":322},"hooks/codex/sessionstart.mjs",{"path":352,"priority":322},"hooks/codex/stop.mjs",{"path":354,"priority":322},"hooks/codex/userpromptsubmit.mjs",{"path":356,"priority":322},"hooks/core/formatters.mjs",{"path":358,"priority":322},"hooks/core/mcp-ready.mjs",{"path":360,"priority":322},"hooks/core/platform-detect.mjs",{"path":362,"priority":322},"hooks/core/routing.mjs",{"path":364,"priority":322},"hooks/core/stdin.mjs",{"path":366,"priority":322},"hooks/core/tool-naming.mjs",{"path":368,"priority":322},"hooks/cursor/afteragentresponse.mjs",{"path":370,"priority":322},"hooks/cursor/hooks.json",{"path":372,"priority":322},"hooks/cursor/posttooluse.mjs",{"path":374,"priority":322},"hooks/cursor/pretooluse.mjs",{"path":376,"priority":322},"hooks/cursor/sessionstart.mjs",{"path":378,"priority":322},"hooks/cursor/stop.mjs",{"path":380,"priority":322},"hooks/ensure-deps.mjs",{"path":382,"priority":322},"hooks/formatters/claude-code.mjs",{"path":384,"priority":322},"hooks/formatters/cursor.mjs",{"path":386,"priority":322},"hooks/formatters/gemini-cli.mjs",{"path":388,"priority":322},"hooks/formatters/vscode-copilot.mjs",{"path":390,"priority":322},"hooks/gemini-cli/aftertool.mjs",{"path":392,"priority":322},"hooks/gemini-cli/beforeagent.mjs",{"path":394,"priority":322},"hooks/gemini-cli/beforetool.mjs",{"path":396,"priority":322},"hooks/gemini-cli/precompress.mjs",{"path":398,"priority":322},"hooks/gemini-cli/sessionstart.mjs",{"path":400,"priority":322},"hooks/hooks.json",{"path":402,"priority":322},"hooks/jetbrains-copilot/posttooluse.mjs",{"path":404,"priority":322},"hooks/jetbrains-copilot/precompact.mjs",{"path":406,"priority":322},"hooks/jetbrains-copilot/pretooluse.mjs",{"path":408,"priority":322},"hooks/jetbrains-copilot/sessionstart.mjs",{"path":410,"priority":322},"hooks/kiro/agentspawn.mjs",{"path":412,"priority":322},"hooks/kiro/posttooluse.mjs",{"path":414,"priority":322},"hooks/kiro/pretooluse.mjs",{"path":416,"priority":322},"hooks/kiro/userpromptsubmit.mjs",{"path":418,"priority":322},"hooks/normalize-hooks.mjs",{"path":420,"priority":322},"hooks/posttooluse.mjs",{"path":422,"priority":322},"hooks/precompact.mjs",{"path":424,"priority":322},"hooks/pretooluse.mjs",{"path":426,"priority":322},"hooks/routing-block.mjs",{"path":428,"priority":322},"hooks/run-hook.mjs",{"path":430,"priority":322},"hooks/session-attribution.bundle.mjs",{"path":432,"priority":322},"hooks/session-db.bundle.mjs",{"path":434,"priority":322},"hooks/session-directive.mjs",{"path":436,"priority":322},"hooks/session-extract.bundle.mjs",{"path":438,"priority":322},"hooks/session-helpers.mjs",{"path":440,"priority":322},"hooks/session-loaders.mjs",{"path":442,"priority":322},"hooks/session-snapshot.bundle.mjs",{"path":444,"priority":322},"hooks/sessionstart.mjs",{"path":446,"priority":322},"hooks/suppress-stderr.mjs",{"path":448,"priority":322},"hooks/userpromptsubmit.mjs",{"path":450,"priority":322},"hooks/vscode-copilot/posttooluse.mjs",{"path":452,"priority":322},"hooks/vscode-copilot/precompact.mjs",{"path":454,"priority":322},"hooks/vscode-copilot/pretooluse.mjs",{"path":456,"priority":322},"hooks/vscode-copilot/sessionstart.mjs",{"path":458,"priority":322},".codex-plugin/plugin.json",{"path":460,"priority":322},".cursor-plugin/plugin.json",{"basePath":462,"description":463,"displayName":464,"installMethods":465,"rationale":466,"selectedPaths":467,"source":310,"sourceLanguage":18,"type":254},".claude/skills/context-mode-ops","Manage context-mode GitHub issues, PRs, releases, and marketing with parallel subagent army. Orchestrates 10-20 dynamic agents per task. Use when triaging issues, reviewing PRs, releasing versions, writing LinkedIn posts, announcing releases, fixing bugs, merging contributions, validating ENV vars, testing adapters, or syncing branches.","context-mode-ops",{"claudeCode":12},"SKILL.md frontmatter at .claude/skills/context-mode-ops/SKILL.md",[468,470,472,474,476,478,480,482,484],{"path":469,"priority":309},"SKILL.md",{"path":471,"priority":325},"agent-teams.md",{"path":473,"priority":325},"communication.md",{"path":475,"priority":325},"marketing.md",{"path":477,"priority":325},"release.md",{"path":479,"priority":325},"review-pr.md",{"path":481,"priority":325},"tdd.md",{"path":483,"priority":325},"triage-issue.md",{"path":485,"priority":325},"validation.md",{"basePath":487,"description":488,"displayName":252,"installMethods":489,"rationale":490,"selectedPaths":491,"source":310,"sourceLanguage":18,"type":254},"skills/context-mode","Use context-mode tools (ctx_execute, ctx_execute_file) instead of Bash/cat when processing\nlarge outputs. Triggers: \"analyze logs\", \"summarize output\", \"process data\",\n\"parse JSON\", \"filter results\", \"extract errors\", \"check build output\",\n\"analyze dependencies\", \"process API response\", \"large file analysis\",\n\"page snapshot\", \"browser snapshot\", \"DOM structure\", \"inspect page\",\n\"accessibility tree\", \"Playwright snapshot\",\n\"run tests\", \"test output\", \"coverage report\", \"git log\", \"recent commits\",\n\"diff between branches\", \"list containers\", \"pod status\", \"disk usage\",\n\"fetch docs\", \"API reference\", \"index documentation\",\n\"call API\", \"check response\", \"query results\",\n\"find TODOs\", \"count lines\", \"codebase statistics\", \"security audit\",\n\"outdated packages\", \"dependency tree\", \"cloud resources\", \"CI/CD output\".\nAlso triggers on ANY MCP tool output that may exceed 20 lines.\nSubagent routing is handled automatically via PreToolUse hook.\n",{"claudeCode":12},"SKILL.md frontmatter at skills/context-mode/SKILL.md",[492,493,495,497,499],{"path":469,"priority":309},{"path":494,"priority":325},"references/anti-patterns.md",{"path":496,"priority":325},"references/patterns-javascript.md",{"path":498,"priority":325},"references/patterns-python.md",{"path":500,"priority":325},"references/patterns-shell.md",{"basePath":502,"description":503,"displayName":504,"installMethods":505,"rationale":506,"selectedPaths":507,"source":310,"sourceLanguage":18,"type":254},"skills/ctx-doctor","Run context-mode diagnostics. Checks runtimes, hooks, FTS5,\nplugin registration, npm and marketplace versions.\nTrigger: /context-mode:ctx-doctor\n","ctx-doctor",{"claudeCode":12},"SKILL.md frontmatter at skills/ctx-doctor/SKILL.md",[508],{"path":469,"priority":309},{"basePath":510,"description":511,"displayName":512,"installMethods":513,"rationale":514,"selectedPaths":515,"source":310,"sourceLanguage":18,"type":254},"skills/ctx-insight","Open the context-mode Insight analytics dashboard in the browser.\nShows personal metrics: session activity, tool usage, error rate,\nparallel work patterns, project focus, and actionable insights.\nFirst run installs dependencies (~30s). Subsequent runs open instantly.\nTrigger: /context-mode:ctx-insight\n","ctx-insight",{"claudeCode":12},"SKILL.md frontmatter at skills/ctx-insight/SKILL.md",[516],{"path":469,"priority":309},{"basePath":250,"description":10,"displayName":253,"installMethods":518,"rationale":519,"selectedPaths":520,"source":310,"sourceLanguage":18,"type":254},{"claudeCode":12},"SKILL.md frontmatter at skills/ctx-purge/SKILL.md",[521],{"path":469,"priority":309},{"basePath":523,"description":524,"displayName":525,"installMethods":526,"rationale":527,"selectedPaths":528,"source":310,"sourceLanguage":18,"type":254},"skills/ctx-stats","Show how much context window context-mode saved this session.\nDisplays token consumption, context savings ratio, and per-tool breakdown.\nRead-only — shows stats only, no reset capability.\nTo wipe the knowledge base entirely, use ctx_purge instead.\nTrigger: /context-mode:ctx-stats\n","ctx-stats",{"claudeCode":12},"SKILL.md frontmatter at skills/ctx-stats/SKILL.md",[529],{"path":469,"priority":309},{"basePath":531,"description":532,"displayName":533,"installMethods":534,"rationale":535,"selectedPaths":536,"source":310,"sourceLanguage":18,"type":254},"skills/ctx-upgrade","Update context-mode from GitHub and fix hooks/settings.\nPulls latest, builds, installs, updates npm global, configures hooks.\nTrigger: /context-mode:ctx-upgrade\n","ctx-upgrade",{"claudeCode":12},"SKILL.md frontmatter at skills/ctx-upgrade/SKILL.md",[537],{"path":469,"priority":309},{"basePath":263,"description":539,"displayName":252,"installMethods":540,"license":280,"rationale":541,"selectedPaths":542,"source":310,"sourceLanguage":18,"type":270},"MCP plugin that saves 98% of your context window. Works with Claude Code, Gemini CLI, VS Code Copilot, OpenCode, and Codex CLI. Sandboxed code execution, FTS5 knowledge base, and intent-driven search.",{"npm":252},"package.json @modelcontextprotocol/sdk dep + bin at package.json",[543,545,546,547,549],{"path":544,"priority":309},"package.json",{"path":319,"priority":309},{"path":321,"priority":322},{"path":548,"priority":325},"cli.bundle.mjs",{"path":550,"priority":338},"src/server.ts",{"sources":552},[553],"manual",{"npmPackage":252},{"closedIssues90d":236,"description":556,"forks":237,"homepage":557,"license":245,"openIssues90d":239,"pushedAt":240,"readmeSize":234,"stars":241,"topics":558},"Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 15 platforms","https://context-mode.com",[559,560,561,270,562,563,564,565,566,567,568,569,570,571,572,573,574,575,576,252],"claude","claude-code","claude-code-plugins","skills","codex","copilot","opencode","antigravity","kiro","openclaw","claude-code-hooks","claude-code-skill","codex-cli","cursor-plugin","mcp-server","mcp-tools","pi-agent","zed-extension",{"downloads":243},{"classifiedAt":579,"discoverAt":580,"extractAt":581,"githubAt":581,"npmAt":582,"updatedAt":579},1778693511234,1778693503750,1778693507197,1778693509704,[213,211,214,212,215],{"evaluatedAt":248,"extractAt":289,"updatedAt":585},1778693818053,[],[588,618,647,678,707,737],{"_creationTime":589,"_id":590,"community":591,"display":592,"identity":598,"providers":602,"relations":611,"tags":614,"workflow":615},1778698144006.2202,"k172517ana4f5vj79mb22xzwsx86mksv",{"reviewCount":8},{"description":593,"installMethods":594,"name":596,"sourceUrl":597},"Audit and consolidate HubSpot reporting dashboards. Identifies unused, duplicate, or outdated dashboards. Must be performed manually — no dashboard API is available.",{"claudeCode":595},"TomGranot/hubspot-admin-skills","cleanup-dashboards","https://github.com/TomGranot/hubspot-admin-skills",{"basePath":599,"githubOwner":600,"githubRepo":601,"locale":18,"slug":596,"type":254},"skills/cleanup-dashboards","TomGranot","hubspot-admin-skills",{"evaluate":603,"extract":610},{"promptVersionExtension":204,"promptVersionScoring":205,"score":604,"tags":605,"targetMarket":216,"tier":217},100,[606,607,608,609,213],"hubspot","crm","maintenance","reporting",{"commitSha":279},{"parentExtensionId":612,"repoId":613},"k17c3p8t0thc73pbc8egtz31y986mwr0","kd75kpec7arn6z2wz641vfaj8n86nab6",[213,607,606,608,609],{"evaluatedAt":616,"extractAt":617,"updatedAt":616},1778698268281,1778698144006,{"_creationTime":619,"_id":620,"community":621,"display":622,"identity":628,"providers":632,"relations":639,"tags":642,"workflow":643},1778691884319.0664,"k172gnk14qpj28ndayqyr7y56186n1ys",{"reviewCount":8},{"description":623,"installMethods":624,"name":626,"sourceUrl":627},"Automatically fix skill problems (safe preview first). Also use with --prune to find and remove broken symlinks, empty directories, and orphaned skills.",{"claudeCode":625},"khendzel/skills-janitor","janitor-fix","https://github.com/khendzel/skills-janitor",{"basePath":629,"githubOwner":630,"githubRepo":631,"locale":18,"slug":626,"type":254},"skills/janitor-fix","khendzel","skills-janitor",{"evaluate":633,"extract":638},{"promptVersionExtension":204,"promptVersionScoring":205,"score":604,"tags":634,"targetMarket":216,"tier":217},[562,608,213,635,636,637],"automation","bash","python",{"commitSha":279},{"parentExtensionId":640,"repoId":641},"k173y287h96a0x42zvrvymzvgn86nq38","kd722xn3d2v8ze2vwgebvzgpv986mj48",[635,636,213,608,637,562],{"evaluatedAt":644,"extractAt":645,"updatedAt":646},1778691964565,1778691884319,1778692172300,{"_creationTime":648,"_id":649,"community":650,"display":651,"identity":657,"providers":662,"relations":671,"tags":673,"workflow":674},1778696473190.3645,"k175pwr78zcnem11h4am251frn86mh2m",{"reviewCount":8},{"description":652,"installMethods":653,"name":655,"sourceUrl":656},"Run /handoff to capture session data, then write a phased implementation plan that references it. Creates beads for tracking.",{"claudeCode":654},"REMvisual/claude-handoff","Claude Handoff","https://github.com/REMvisual/claude-handoff",{"basePath":658,"githubOwner":659,"githubRepo":660,"locale":18,"slug":661,"type":254},"skills/handoffplan","REMvisual","claude-handoff","handoffplan",{"evaluate":663,"extract":669},{"promptVersionExtension":204,"promptVersionScoring":205,"score":604,"tags":664,"targetMarket":216,"tier":217},[211,665,666,667,668],"planning","session-management","code-review","developer-tools",{"commitSha":279,"license":670},"MIT",{"repoId":672},"kd751dv4xqaztg0deehhxazcjn86mynf",[667,211,668,665,666],{"evaluatedAt":675,"extractAt":676,"updatedAt":677},1778696514353,1778696473190,1778696537692,{"_creationTime":679,"_id":680,"community":681,"display":682,"identity":688,"providers":692,"relations":700,"tags":703,"workflow":704},1778675056600.2158,"k177e3yxwkd9wwbpxgv09a7kdn86mx62",{"reviewCount":8},{"description":683,"installMethods":684,"name":686,"sourceUrl":687},"/cs:onboard — Founder interview that populates ~/.claude/company-context.md. The first command to run when starting with c-level-agents.",{"claudeCode":685},"alirezarezvani/claude-skills","onboard","https://github.com/alirezarezvani/claude-skills",{"basePath":689,"githubOwner":690,"githubRepo":691,"locale":18,"slug":686,"type":254},"c-level-advisor/c-level-agents/skills/onboard","alirezarezvani","claude-skills",{"evaluate":693,"extract":699},{"promptVersionExtension":204,"promptVersionScoring":205,"score":604,"tags":694,"targetMarket":216,"tier":217},[695,211,696,697,698],"onboarding","founder-interview","configuration","startup",{"commitSha":279},{"parentExtensionId":701,"repoId":702},"k172bm0n7hp1thk5xp6n6rwyj986mym4","kd7ff9s1w43mfyy1n7hf87816186m6px",[697,211,696,695,698],{"evaluatedAt":705,"extractAt":706,"updatedAt":705},1778676843992,1778675056600,{"_creationTime":708,"_id":709,"community":710,"display":711,"identity":717,"providers":722,"relations":731,"tags":733,"workflow":734},1778692098392.718,"k17akm3fqmcvhdq0nmaxcgh2h586mcef",{"reviewCount":8},{"description":712,"installMethods":713,"name":715,"sourceUrl":716},"当需要用 lark-cli 操作飞书多维表格（Base）时调用：搜索 Base、建表、字段管理、记录读写、记录分享链接、视图配置、历史查询，以及角色/表单/仪表盘管理/工作流；也适用于把旧的 +table / +field / +record 写法改成当前命令写法。涉及字段设计、公式字段、查找引用、跨表计算、行级派生指标、数据分析需求时也必须使用本 skill。",{"claudeCode":714},"larksuite/cli","lark-base","https://github.com/larksuite/cli",{"basePath":718,"githubOwner":719,"githubRepo":720,"locale":721,"slug":715,"type":254},"skills/lark-base","larksuite","cli","zh-CN",{"evaluate":723,"extract":730},{"promptVersionExtension":204,"promptVersionScoring":205,"score":604,"tags":724,"targetMarket":216,"tier":217},[725,726,720,635,727,728,214,729],"lark","feishu","api","workflow","base",{"commitSha":279},{"repoId":732},"kd7akv5cxs7vx53ys6jsrv85v186mha4",[727,635,729,720,214,726,725,728],{"evaluatedAt":735,"extractAt":736,"updatedAt":735},1778692233385,1778692098392,{"_creationTime":738,"_id":739,"community":740,"display":741,"identity":747,"providers":750,"relations":756,"tags":759,"workflow":760},1778690773482.4866,"k17a3mmgvm5hj49twj487hp64186n2qa",{"reviewCount":8},{"description":742,"installMethods":743,"name":745,"sourceUrl":746},"Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to use this skill whenever the user mentions 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or 'hugging face cli', or wants to do anything related to the Hugging Face ecosystem and to AI and ML in general. Also use for cloud storage needs like training checkpoints, data pipelines, or agent traces. Use even if the user doesn't explicitly ask for a CLI command. Replaces the deprecated `huggingface-cli`.",{"claudeCode":744},"huggingface/skills","hf-cli","https://github.com/huggingface/skills",{"basePath":748,"githubOwner":749,"githubRepo":562,"locale":18,"slug":745,"type":254},"skills/hf-cli","huggingface",{"evaluate":751,"extract":755},{"promptVersionExtension":204,"promptVersionScoring":205,"score":604,"tags":752,"targetMarket":216,"tier":217},[720,749,753,214,754],"mlops","model-management",{"commitSha":279},{"parentExtensionId":757,"repoId":758},"k175g1spb5757qt4tnj9cktcn986mshy","kd72xwt5xnc0ktc4p7smzfcp3986m959",[720,214,749,753,754],{"evaluatedAt":761,"extractAt":762,"updatedAt":761},1778691223210,1778690773482]