[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-rohitg00-survey-generator-zh-CN":3,"guides-for-rohitg00-survey-generator":792,"similar-k175bsz86zj45n9h5xarvnjm6186n4qm-zh-CN":793},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":222,"isFallback":205,"parentExtension":227,"providers":290,"relations":294,"repo":295,"tags":790,"workflow":791},1778696595410.568,"k175bsz86zj45n9h5xarvnjm6186n4qm",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Compile a structured literature survey on any AI/ML topic. Agent curates a research bundle (taxonomy + sections + bibliography of real papers) from a public anchor resource, then a chosen LLM generates the survey artifact. Output target is a wiki page (markdown), not a one-off HTML — survey lands in `\u003Cwiki>/derived/surveys/\u003Cslug>.md` with full bibliography rows in `sources.md`. Provider-agnostic (Anthropic/OpenAI/OpenRouter/Fireworks/custom OpenAI-compat). Use when the user asks for a \"survey\", \"literature review\", \"lit review\", or \"deep dive\" on a technical topic.",{"claudeCode":12},"rohitg00/pro-workflow","survey-generator","https://github.com/rohitg00/pro-workflow",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":203,"workflow":220},1778697037612.5703,"kn79exzp6hzrt3zv3nq31ebs1d86ntyv","en",{"checks":20,"evaluatedAt":170,"extensionSummary":171,"features":172,"nonGoals":178,"promptVersionExtension":183,"promptVersionScoring":184,"purpose":185,"rationale":186,"score":187,"summary":188,"tags":189,"targetMarket":196,"tier":197,"useCases":198},[21,26,29,32,36,39,43,46,50,54,58,62,65,69,73,77,81,84,87,90,93,96,99,103,106,110,114,118,121,125,128,132,135,138,141,144,147,150,154,157,160,163,167],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of compiling literature surveys on AI/ML topics and identifies the output target (wiki page) and the use case for specific user requests.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers significant value over a basic prompt by curating a structured research bundle, generating a survey artifact, and integrating with a wiki and FTS5 index, going beyond simple LLM generation.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill provides a complete workflow from fetching an anchor resource to generating a survey and integrating it into a wiki, covering the full lifecycle and supporting multiple LLM providers.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses on generating literature surveys for a wiki, which is a coherent and single responsibility.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's functionality, including its output target, provider-agnostic nature, and use cases.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Precise Purpose","The description clearly defines the artifact (structured literature survey), the task (compile), the target (wiki page), and the triggers ('survey', 'literature review', 'lit review', 'deep dive').",{"category":40,"check":44,"severity":24,"summary":45},"Concise Frontmatter","The frontmatter effectively summarizes the skill's core capability and provides trigger phrases within a reasonable character limit.",{"category":47,"check":48,"severity":24,"summary":49},"Documentation","Concise Body","The SKILL.md body is concise, outlining the workflow and inputs, and delegates deeper material like templates to separate files.",{"category":51,"check":52,"severity":24,"summary":53},"Context","Progressive Disclosure","The SKILL.md outlines the main workflow and points to a template file for detailed structure, adhering to progressive disclosure.",{"category":51,"check":55,"severity":56,"summary":57},"Forked exploration","not_applicable","The skill's workflow does not involve deep exploration or inspection of external codebases that would necessitate 'context: fork'.",{"category":22,"check":59,"severity":60,"summary":61},"Usage examples","info","The SKILL.md provides detailed workflow steps and commands for generating surveys, but lacks end-to-end examples showing specific input, invocation, and claimed output.",{"category":22,"check":63,"severity":60,"summary":64},"Edge cases","The SKILL.md outlines hard rules and potential iteration steps but does not explicitly detail failure modes, their symptoms, or recovery steps.",{"category":66,"check":67,"severity":56,"summary":68},"Code Execution","Tool Fallback","The skill uses standard Node.js and potentially LLM provider APIs, not a custom MCP that would require a fallback.",{"category":70,"check":71,"severity":56,"summary":72},"Safety","Halt on unexpected state","The skill's workflow does not involve destructive operations or complex state management that would require explicit pre-condition checklists for halting.",{"category":74,"check":75,"severity":24,"summary":76},"Portability","Cross-skill coupling","The skill operates independently and mentions its integration with other pro-workflow components like `wiki-cli.js` explicitly without implicit reliance.",{"category":78,"check":79,"severity":24,"summary":80},"Security","Secret Management","The skill requires API keys via environment variables, and the script's usage of these keys is standard for LLM provider interaction, with no evidence of secrets being echoed.",{"category":78,"check":82,"severity":24,"summary":83},"Injection","The skill fetches data from a provided URL and uses it as input for an LLM, without any indication of executing external code or instructions within the fetched data.",{"category":78,"check":85,"severity":24,"summary":86},"Transitive Supply-Chain Grenades","The skill uses provided URLs and internal scripts; it does not download or execute external code at runtime.",{"category":78,"check":88,"severity":24,"summary":89},"Sandbox Isolation","The script operates on provided inputs and LLM APIs, writing to specified wiki directories; there's no indication of attempting to modify files outside its intended scope.",{"category":78,"check":91,"severity":24,"summary":92},"Sandbox escape primitives","The provided script does not contain any detached-process spawns or retry loops around denied tool calls.",{"category":78,"check":94,"severity":24,"summary":95},"Data Exfiltration","The skill requires API keys for LLM providers but does not instruct to submit confidential data to a third party or any undocumented outbound calls.",{"category":78,"check":97,"severity":24,"summary":98},"Hidden Text Tricks","The bundled files are clean and do not contain hidden-steering tricks, control characters, or invisible Unicode tag sequences.",{"category":100,"check":101,"severity":24,"summary":102},"Hooks","Opaque code execution","The provided script is plain JavaScript and does not use obfuscation techniques like base64 decoding or runtime fetching for execution.",{"category":74,"check":104,"severity":24,"summary":105},"Structural Assumption","The script assumes the existence of a wiki directory structure and `wiki-cli.js`, which are part of the pro-workflow ecosystem, but these are standard for the context.",{"category":107,"check":108,"severity":24,"summary":109},"Trust","Issues Attention","There are 0 open issues and 5 closed issues in the last 90 days, indicating active maintenance and responsiveness.",{"category":111,"check":112,"severity":24,"summary":113},"Versioning","Release Management","The project has a `package.json` with a version and the README shows an npm badge, indicating versioning is in place.",{"category":115,"check":116,"severity":60,"summary":117},"Execution","Validation","The script parses arguments and validates the bundle structure, but doesn't use a formal schema library for input validation beyond basic checks.",{"category":78,"check":119,"severity":56,"summary":120},"Unguarded Destructive Operations","The skill writes survey files and appends to sources.md, which are not destructive operations requiring a confirmation gate.",{"category":122,"check":123,"severity":60,"summary":124},"Errors","Error Handling","The script includes basic error handling with `die()` calls for critical failures, but lacks structured error reporting or specific recovery steps for LLM provider issues.",{"category":66,"check":126,"severity":60,"summary":127},"Logging","The script logs progress and errors to stderr using `console.error`, but does not append to a persistent audit log file.",{"category":129,"check":130,"severity":56,"summary":131},"Compliance","GDPR","The skill operates on a user-provided topic and URL, and generates text; it does not handle personal data.",{"category":129,"check":133,"severity":24,"summary":134},"Target market","The skill is provider-agnostic and its functionality is not tied to any specific geographic or legal jurisdiction; targetMarket is global.",{"category":74,"check":136,"severity":24,"summary":137},"Runtime stability","The script is a standard Node.js script and relies on common modules and LLM APIs, making it portable across POSIX-compliant systems with Node.js installed.",{"category":47,"check":139,"severity":24,"summary":140},"README","The README provides a comprehensive overview of the pro-workflow project, including install instructions and feature comparisons, which is relevant context.",{"category":33,"check":142,"severity":56,"summary":143},"Tool surface size","This is a single script with one primary command-line interface, not a collection of tools.",{"category":40,"check":145,"severity":56,"summary":146},"Overlapping near-synonym tools","The skill has a single entry point (`build-survey.js`) and does not expose multiple tools with overlapping functionalities.",{"category":47,"check":148,"severity":24,"summary":149},"Phantom features","All features mentioned in the SKILL.md and README (survey generation, wiki integration, provider-agnosticism) are implemented in the provided script and its associated commands.",{"category":151,"check":152,"severity":24,"summary":153},"Install","Installation instruction","The README includes clear installation instructions via `/plugin marketplace add` and `/plugin install`, as well as command-line usage examples for the script.",{"category":122,"check":155,"severity":60,"summary":156},"Actionable error messages","Error messages are provided for critical failures like missing arguments or files, but lack detailed remediation steps beyond suggesting checking usage.",{"category":115,"check":158,"severity":24,"summary":159},"Pinned dependencies","The project uses npm and likely has pinned dependencies via `package-lock.json` (implied by `hasLockfile: true`), and the script has a shebang and uses standard Node.js modules.",{"category":33,"check":161,"severity":56,"summary":162},"Dry-run preview","The skill's primary function is to generate and write files, which is not a destructive operation that requires a dry-run mode. The output is previewable by inspecting the generated markdown before committing.",{"category":164,"check":165,"severity":60,"summary":166},"Protocol","Idempotent retry & timeouts","The script includes a timeout for the LLM provider call, but mutations like writing files are not inherently idempotent, and error handling for retries is basic.",{"category":129,"check":168,"severity":24,"summary":169},"Telemetry opt-in","The script itself does not emit telemetry. Any telemetry would be handled by the underlying LLM providers or the pro-workflow framework, which are assumed to follow opt-in principles.",1778697037435,"This skill generates structured literature surveys on AI/ML topics by curating research bundles from anchor resources and using LLMs. It outputs markdown survey pages to a specified wiki and appends bibliography entries to `sources.md`, supporting multiple LLM providers and integrating with the pro-workflow ecosystem.",[173,174,175,176,177],"Generates structured literature surveys from a URL","Creates research bundles (taxonomy, sections, bibliography)","Outputs to wiki markdown pages and updates `sources.md`","Provider-agnostic LLM integration (Anthropic, OpenAI, etc.)","Integrates with pro-workflow's wiki and FTS5 indexing",[179,180,181,182],"Generating standalone HTML survey files","Inventing bibliography entries","Performing deep analysis beyond survey compilation","Directly editing wiki content outside of the generated survey and bibliography","3.0.0","4.4.0","To automate the creation of comprehensive literature surveys, serving as a knowledge base within a wiki for easy access and future research.","The skill is well-documented, functional, and adheres to best practices with a clear purpose and robust implementation. Minor areas for improvement include more explicit error handling and end-to-end usage examples.",88,"A well-implemented skill for generating structured literature surveys with wiki integration.",[190,191,192,193,194,195],"documentation","ai","llm","research","wiki","survey","global","verified",[199,200,201,202],"Generating an initial overview of a new technical topic","Creating a structured knowledge base for a research area","Compiling survey artifacts for technical documentation","Seeding the wiki for further automated research",{"codeQuality":204,"collectedAt":206,"documentation":207,"maintenance":210,"popularity":216,"security":218,"testCoverage":219},{"hasLockfile":205},true,1778697021446,{"descriptionLength":208,"readmeSize":209},571,22012,{"closedIssues90d":211,"forks":212,"hasChangelog":213,"openIssues90d":8,"pushedAt":214,"stars":215},5,203,false,1778554780000,2113,{"npmDownloads":217},611,{"hasNpmPackage":205,"smitheryVerified":213},{"hasCi":205,"hasTests":213},{"updatedAt":221},1778697037612,{"basePath":223,"githubOwner":224,"githubRepo":225,"locale":18,"slug":13,"type":226},"skills/survey-generator","rohitg00","pro-workflow","skill",{"_creationTime":228,"_id":229,"community":230,"display":231,"identity":237,"parentExtension":240,"providers":272,"relations":286,"tags":287,"workflow":288},1778696595410.5615,"k17fxtjcfh5gvxdrhv2dmgn1t986mdhv",{"reviewCount":8},{"description":232,"installMethods":233,"name":236,"sourceUrl":14},"Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.",{"claudeCode":225,"cursor":234,"npm":225,"skillkit":235},"/add-plugin pro-workflow","npx skillkit install pro-workflow","Pro Workflow",{"basePath":238,"githubOwner":224,"githubRepo":225,"locale":18,"slug":225,"type":239},"","plugin",{"_creationTime":241,"_id":242,"community":243,"display":244,"identity":247,"providers":249,"relations":266,"tags":268,"workflow":269},1778696595410.5613,"k1741gyqaf0tj1ffq65gjpsm6x86mfhx",{"reviewCount":8},{"description":245,"installMethods":246,"name":236,"sourceUrl":14},"Battle-tested Claude Code workflows from power users",{"claudeCode":12},{"basePath":238,"githubOwner":224,"githubRepo":225,"locale":18,"slug":225,"type":248},"marketplace",{"evaluate":250,"extract":259},{"promptVersionExtension":251,"promptVersionScoring":184,"score":252,"tags":253,"targetMarket":196,"tier":197},"3.1.0",99,[254,255,256,257,258],"workflow","productivity","ai-assistance","developer-tools","knowledge-management",{"commitSha":260,"license":261,"marketplace":262,"plugin":264},"HEAD","MIT",{"name":225,"pluginCount":263},1,{"mcpCount":8,"provider":265,"skillCount":8},"classify",{"repoId":267},"kd7am4e918eq98hrd9s31jm4vs86nn0b",[256,257,258,255,254],{"evaluatedAt":270,"extractAt":271,"updatedAt":270},1778696611346,1778696595410,{"evaluate":273,"extract":283},{"promptVersionExtension":183,"promptVersionScoring":184,"score":274,"tags":275,"targetMarket":196,"tier":282},96,[254,255,276,277,278,279,280,281],"ai-coding","self-correction","knowledge-base","sqlite","hooks","agents","community",{"commitSha":260,"license":261,"plugin":284},{"mcpCount":8,"provider":265,"skillCount":285},34,{"parentExtensionId":242,"repoId":267},[281,276,280,278,255,277,279,254],{"evaluatedAt":289,"extractAt":271,"updatedAt":289},1778696621396,{"evaluate":291,"extract":293},{"promptVersionExtension":183,"promptVersionScoring":184,"score":187,"tags":292,"targetMarket":196,"tier":197},[190,191,192,193,194,195],{"commitSha":260},{"parentExtensionId":229,"repoId":267},{"_creationTime":296,"_id":267,"identity":297,"providers":298,"workflow":785},1778696588306.821,{"githubOwner":224,"githubRepo":225,"sourceUrl":14},{"classify":299,"discover":764,"extract":767,"github":768,"npm":784},{"commitSha":260,"extensions":300},[301,311,452,461,469,477,485,493,501,509,517,525,533,541,549,560,568,576,584,592,600,608,616,623,631,639,647,655,663,672,680,688,720,730,746,756],{"basePath":238,"description":245,"displayName":225,"installMethods":302,"rationale":303,"selectedPaths":304,"source":310,"sourceLanguage":18,"type":248},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[305,308],{"path":306,"priority":307},".claude-plugin/marketplace.json","mandatory",{"path":309,"priority":307},"README.md","rule",{"basePath":238,"description":232,"displayName":225,"installMethods":312,"license":261,"rationale":313,"selectedPaths":314,"source":310,"sourceLanguage":18,"type":239},{"claudeCode":225},"plugin manifest at .claude-plugin/plugin.json",[315,317,318,321,323,325,327,329,331,333,335,337,339,341,343,345,347,349,351,353,355,357,359,361,363,365,367,369,371,373,375,377,379,381,383,385,387,390,392,394,396,398,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,450],{"path":316,"priority":307},".claude-plugin/plugin.json",{"path":309,"priority":307},{"path":319,"priority":320},"skills/agent-teams/SKILL.md","medium",{"path":322,"priority":320},"skills/auto-setup/SKILL.md",{"path":324,"priority":320},"skills/batch-orchestration/SKILL.md",{"path":326,"priority":320},"skills/bug-capture/SKILL.md",{"path":328,"priority":320},"skills/compact-guard/SKILL.md",{"path":330,"priority":320},"skills/context-engineering/SKILL.md",{"path":332,"priority":320},"skills/context-optimizer/SKILL.md",{"path":334,"priority":320},"skills/cost-tracker/SKILL.md",{"path":336,"priority":320},"skills/deslop/SKILL.md",{"path":338,"priority":320},"skills/file-watcher/SKILL.md",{"path":340,"priority":320},"skills/insights/SKILL.md",{"path":342,"priority":320},"skills/learn-rule/SKILL.md",{"path":344,"priority":320},"skills/llm-council/SKILL.md",{"path":346,"priority":320},"skills/llm-gate/SKILL.md",{"path":348,"priority":320},"skills/mcp-audit/SKILL.md",{"path":350,"priority":320},"skills/module-map/SKILL.md",{"path":352,"priority":320},"skills/orchestrate/SKILL.md",{"path":354,"priority":320},"skills/parallel-worktrees/SKILL.md",{"path":356,"priority":320},"skills/permission-tuner/SKILL.md",{"path":358,"priority":320},"skills/plan-interrogate/SKILL.md",{"path":360,"priority":320},"skills/pro-workflow/SKILL.md",{"path":362,"priority":320},"skills/replay-learnings/SKILL.md",{"path":364,"priority":320},"skills/safe-mode/SKILL.md",{"path":366,"priority":320},"skills/session-handoff/SKILL.md",{"path":368,"priority":320},"skills/smart-commit/SKILL.md",{"path":370,"priority":320},"skills/sprint-status/SKILL.md",{"path":372,"priority":320},"skills/survey-generator/SKILL.md",{"path":374,"priority":320},"skills/thoroughness-scoring/SKILL.md",{"path":376,"priority":320},"skills/token-efficiency/SKILL.md",{"path":378,"priority":320},"skills/wiki-builder/SKILL.md",{"path":380,"priority":320},"skills/wiki-query/SKILL.md",{"path":382,"priority":320},"skills/wiki-research-loop/SKILL.md",{"path":384,"priority":320},"skills/wiki-viewer/SKILL.md",{"path":386,"priority":320},"skills/wrap-up/SKILL.md",{"path":388,"priority":389},"agents/context-engineer.md","high",{"path":391,"priority":389},"agents/cost-analyst.md",{"path":393,"priority":389},"agents/debugger.md",{"path":395,"priority":389},"agents/orchestrator.md",{"path":397,"priority":389},"agents/permission-analyst.md",{"path":399,"priority":389},"agents/planner.md",{"path":401,"priority":389},"agents/reviewer.md",{"path":403,"priority":389},"agents/scout.md",{"path":405,"priority":389},"commands/auto-setup.md",{"path":407,"priority":389},"commands/commit.md",{"path":409,"priority":389},"commands/compact-guard.md",{"path":411,"priority":389},"commands/context-optimizer.md",{"path":413,"priority":389},"commands/cost-tracker.md",{"path":415,"priority":389},"commands/deslop.md",{"path":417,"priority":389},"commands/develop.md",{"path":419,"priority":389},"commands/doctor.md",{"path":421,"priority":389},"commands/handoff.md",{"path":423,"priority":389},"commands/insights.md",{"path":425,"priority":389},"commands/learn-rule.md",{"path":427,"priority":389},"commands/learn.md",{"path":429,"priority":389},"commands/list.md",{"path":431,"priority":389},"commands/mcp-audit.md",{"path":433,"priority":389},"commands/parallel.md",{"path":435,"priority":389},"commands/permission-tuner.md",{"path":437,"priority":389},"commands/replay.md",{"path":439,"priority":389},"commands/safe-mode.md",{"path":441,"priority":389},"commands/search.md",{"path":443,"priority":389},"commands/sprint-status.md",{"path":445,"priority":389},"commands/wiki.md",{"path":447,"priority":389},"commands/wrap-up.md",{"path":449,"priority":389},"hooks/hooks.json",{"path":451,"priority":389},".cursor-plugin/plugin.json",{"basePath":453,"description":454,"displayName":455,"installMethods":456,"rationale":457,"selectedPaths":458,"source":310,"sourceLanguage":18,"type":226},"skills/agent-teams","Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.","agent-teams",{"claudeCode":12},"SKILL.md frontmatter at skills/agent-teams/SKILL.md",[459],{"path":460,"priority":307},"SKILL.md",{"basePath":462,"description":463,"displayName":464,"installMethods":465,"rationale":466,"selectedPaths":467,"source":310,"sourceLanguage":18,"type":226},"skills/auto-setup","Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.","auto-setup",{"claudeCode":12},"SKILL.md frontmatter at skills/auto-setup/SKILL.md",[468],{"path":460,"priority":307},{"basePath":470,"description":471,"displayName":472,"installMethods":473,"rationale":474,"selectedPaths":475,"source":310,"sourceLanguage":18,"type":226},"skills/batch-orchestration","Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.","batch-orchestration",{"claudeCode":12},"SKILL.md frontmatter at skills/batch-orchestration/SKILL.md",[476],{"path":460,"priority":307},{"basePath":478,"description":479,"displayName":480,"installMethods":481,"rationale":482,"selectedPaths":483,"source":310,"sourceLanguage":18,"type":226},"skills/bug-capture","Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never leaks file paths or line numbers into the issue. Use when the user reports a bug conversationally, runs a QA pass, or says \"file an issue\", \"log this as a bug\", \"capture this\".","bug-capture",{"claudeCode":12},"SKILL.md frontmatter at skills/bug-capture/SKILL.md",[484],{"path":460,"priority":307},{"basePath":486,"description":487,"displayName":488,"installMethods":489,"rationale":490,"selectedPaths":491,"source":310,"sourceLanguage":18,"type":226},"skills/compact-guard","Smart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after. Use before manual compact or when auto-compact triggers.","compact-guard",{"claudeCode":12},"SKILL.md frontmatter at skills/compact-guard/SKILL.md",[492],{"path":460,"priority":307},{"basePath":494,"description":495,"displayName":496,"installMethods":497,"rationale":498,"selectedPaths":499,"source":310,"sourceLanguage":18,"type":226},"skills/context-engineering","Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.","context-engineering",{"claudeCode":12},"SKILL.md frontmatter at skills/context-engineering/SKILL.md",[500],{"path":460,"priority":307},{"basePath":502,"description":503,"displayName":504,"installMethods":505,"rationale":506,"selectedPaths":507,"source":310,"sourceLanguage":18,"type":226},"skills/context-optimizer","Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.","context-optimizer",{"claudeCode":12},"SKILL.md frontmatter at skills/context-optimizer/SKILL.md",[508],{"path":460,"priority":307},{"basePath":510,"description":511,"displayName":512,"installMethods":513,"rationale":514,"selectedPaths":515,"source":310,"sourceLanguage":18,"type":226},"skills/cost-tracker","Track session costs, set budget alerts, and optimize token spend. Use to check costs mid-session or set spending limits.","cost-tracker",{"claudeCode":12},"SKILL.md frontmatter at skills/cost-tracker/SKILL.md",[516],{"path":460,"priority":307},{"basePath":518,"description":519,"displayName":520,"installMethods":521,"rationale":522,"selectedPaths":523,"source":310,"sourceLanguage":18,"type":226},"skills/deslop","Remove AI-generated code slop, unnecessary comments, and over-engineering from the current branch diff. Cleans up boilerplate, simplifies abstractions, and strips defensive code. Use when cleaning up code, simplifying, removing boilerplate, or before committing.","deslop",{"claudeCode":12},"SKILL.md frontmatter at skills/deslop/SKILL.md",[524],{"path":460,"priority":307},{"basePath":526,"description":527,"displayName":528,"installMethods":529,"rationale":530,"selectedPaths":531,"source":310,"sourceLanguage":18,"type":226},"skills/file-watcher","Configure file watching hooks to auto-react to config changes, env file updates, and dependency modifications. Use to set up reactive workflows.","file-watcher",{"claudeCode":12},"SKILL.md frontmatter at skills/file-watcher/SKILL.md",[532],{"path":460,"priority":307},{"basePath":534,"description":535,"displayName":536,"installMethods":537,"rationale":538,"selectedPaths":539,"source":310,"sourceLanguage":18,"type":226},"skills/insights","Show session analytics, learning patterns, correction trends, heatmaps, and productivity metrics. Computes stats from project memory and session history. Use when asking for stats, statistics, progress, how am I doing, coding history, or dashboard.","insights",{"claudeCode":12},"SKILL.md frontmatter at skills/insights/SKILL.md",[540],{"path":460,"priority":307},{"basePath":542,"description":543,"displayName":544,"installMethods":545,"rationale":546,"selectedPaths":547,"source":310,"sourceLanguage":18,"type":226},"skills/learn-rule","Capture a correction or lesson as a persistent learning rule with category, mistake, and correction. Stores, categorises, and retrieves rules for future sessions. Use after mistakes or when the user says \"remember this\", \"don't forget\", \"note this\", or \"learn from this\".","learn-rule",{"claudeCode":12},"SKILL.md frontmatter at skills/learn-rule/SKILL.md",[548],{"path":460,"priority":307},{"basePath":550,"description":551,"displayName":552,"installMethods":553,"rationale":554,"selectedPaths":555,"source":310,"sourceLanguage":18,"type":226},"skills/llm-council","Provider-agnostic multi-LLM deliberation. Three phases — independent responses, cross-model anonymized ranking, chairman synthesis. Provider config from env (OPENAI/ANTHROPIC/FIREWORKS/OPENROUTER/custom OpenAI-compatible base URL). Persists transcript to a wiki page when --wiki \u003Cslug> is passed. Use when the user wants multiple AI perspectives, consensus-building, or the \"LLM Council\" approach for high-stakes reviews, plan critique, or contested learning rules.","llm-council",{"claudeCode":12},"SKILL.md frontmatter at skills/llm-council/SKILL.md",[556,557],{"path":460,"priority":307},{"path":558,"priority":559},"scripts/council.js","low",{"basePath":561,"description":562,"displayName":563,"installMethods":564,"rationale":565,"selectedPaths":566,"source":310,"sourceLanguage":18,"type":226},"skills/llm-gate","LLM-powered quality verification using prompt hooks. Validates commit messages, code patterns, and conventions using AI before allowing operations. Use to set up intelligent guardrails.","llm-gate",{"claudeCode":12},"SKILL.md frontmatter at skills/llm-gate/SKILL.md",[567],{"path":460,"priority":307},{"basePath":569,"description":570,"displayName":571,"installMethods":572,"rationale":573,"selectedPaths":574,"source":310,"sourceLanguage":18,"type":226},"skills/mcp-audit","Audit connected MCP servers for token overhead, redundancy, and security. Use when sessions feel slow or before adding new MCPs.","mcp-audit",{"claudeCode":12},"SKILL.md frontmatter at skills/mcp-audit/SKILL.md",[575],{"path":460,"priority":307},{"basePath":577,"description":578,"displayName":579,"installMethods":580,"rationale":581,"selectedPaths":582,"source":310,"sourceLanguage":18,"type":226},"skills/module-map","Produce a one-screen map of an unfamiliar area of the codebase: entry points, modules, data flow, callers. Designed to be read in fifteen seconds. Use when the user says \"I do not know this area\", \"give me the map\", \"zoom out\", \"orient me\".","module-map",{"claudeCode":12},"SKILL.md frontmatter at skills/module-map/SKILL.md",[583],{"path":460,"priority":307},{"basePath":585,"description":586,"displayName":587,"installMethods":588,"rationale":589,"selectedPaths":590,"source":310,"sourceLanguage":18,"type":226},"skills/orchestrate","Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.","orchestrate",{"claudeCode":12},"SKILL.md frontmatter at skills/orchestrate/SKILL.md",[591],{"path":460,"priority":307},{"basePath":593,"description":594,"displayName":595,"installMethods":596,"rationale":597,"selectedPaths":598,"source":310,"sourceLanguage":18,"type":226},"skills/parallel-worktrees","Create and manage git worktrees for parallel coding sessions with zero dead time. Use when blocked on tests, builds, wanting to work on multiple branches, context switching, or exploring multiple approaches simultaneously.","parallel-worktrees",{"claudeCode":12},"SKILL.md frontmatter at skills/parallel-worktrees/SKILL.md",[599],{"path":460,"priority":307},{"basePath":601,"description":602,"displayName":603,"installMethods":604,"rationale":605,"selectedPaths":606,"source":310,"sourceLanguage":18,"type":226},"skills/permission-tuner","Analyze permission denial patterns and generate optimized alwaysAllow and alwaysDeny rules. Use when permission prompts are slowing you down or after sessions with many denials.","permission-tuner",{"claudeCode":12},"SKILL.md frontmatter at skills/permission-tuner/SKILL.md",[607],{"path":460,"priority":307},{"basePath":609,"description":610,"displayName":611,"installMethods":612,"rationale":613,"selectedPaths":614,"source":310,"sourceLanguage":18,"type":226},"skills/plan-interrogate","Stress-test a plan by walking its decision tree one question at a time. Use when the user wants to pressure-test a design before implementation.","plan-interrogate",{"claudeCode":12},"SKILL.md frontmatter at skills/plan-interrogate/SKILL.md",[615],{"path":460,"priority":307},{"basePath":617,"description":618,"displayName":225,"installMethods":619,"rationale":620,"selectedPaths":621,"source":310,"sourceLanguage":18,"type":226},"skills/pro-workflow","Complete AI coding workflow system. Orchestration patterns, 18 hook events, 5 agents, cross-agent support, reference guides, and searchable learnings. Works with Claude Code, Cursor, and 32+ agents.",{"claudeCode":12},"SKILL.md frontmatter at skills/pro-workflow/SKILL.md",[622],{"path":460,"priority":307},{"basePath":624,"description":625,"displayName":626,"installMethods":627,"rationale":628,"selectedPaths":629,"source":310,"sourceLanguage":18,"type":226},"skills/replay-learnings","Surface past learnings relevant to the current task before starting work. Searches correction history, recalls past mistakes, and applies prior patterns. Use when starting a task, saying \"what do I know about\", \"previous mistakes\", \"lessons learned\", or \"remind me about\".","replay-learnings",{"claudeCode":12},"SKILL.md frontmatter at skills/replay-learnings/SKILL.md",[630],{"path":460,"priority":307},{"basePath":632,"description":633,"displayName":634,"installMethods":635,"rationale":636,"selectedPaths":637,"source":310,"sourceLanguage":18,"type":226},"skills/safe-mode","Prevent destructive operations using Claude Code hooks. Three modes — cautious (warn on dangerous commands), lockdown (restrict edits to one directory), and clear (remove restrictions). Uses PreToolUse matchers for Bash, Edit, and Write.","safe-mode",{"claudeCode":12},"SKILL.md frontmatter at skills/safe-mode/SKILL.md",[638],{"path":460,"priority":307},{"basePath":640,"description":641,"displayName":642,"installMethods":643,"rationale":644,"selectedPaths":645,"source":310,"sourceLanguage":18,"type":226},"skills/session-handoff","Generate a structured handoff document capturing current progress, open tasks, key decisions, and context needed to resume work. Use when ending a session, saying \"continue later\", \"save progress\", \"session summary\", or \"pick up where I left off\".","session-handoff",{"claudeCode":12},"SKILL.md frontmatter at skills/session-handoff/SKILL.md",[646],{"path":460,"priority":307},{"basePath":648,"description":649,"displayName":650,"installMethods":651,"rationale":652,"selectedPaths":653,"source":310,"sourceLanguage":18,"type":226},"skills/smart-commit","Run quality gates, review staged changes for issues, and create a well-crafted conventional commit. Use when saying \"commit\", \"git commit\", \"save my changes\", or ready to commit after making changes.","smart-commit",{"claudeCode":12},"SKILL.md frontmatter at skills/smart-commit/SKILL.md",[654],{"path":460,"priority":307},{"basePath":656,"description":657,"displayName":658,"installMethods":659,"rationale":660,"selectedPaths":661,"source":310,"sourceLanguage":18,"type":226},"skills/sprint-status","Track parallel work sessions and prevent confusion across multiple Claude Code instances. Every major step ends with a status line. Every question re-states project, branch, and task.","sprint-status",{"claudeCode":12},"SKILL.md frontmatter at skills/sprint-status/SKILL.md",[662],{"path":460,"priority":307},{"basePath":223,"description":10,"displayName":13,"installMethods":664,"rationale":665,"selectedPaths":666,"source":310,"sourceLanguage":18,"type":226},{"claudeCode":12},"SKILL.md frontmatter at skills/survey-generator/SKILL.md",[667,668,670],{"path":460,"priority":307},{"path":669,"priority":559},"scripts/build-survey.js",{"path":671,"priority":559},"templates/research_bundle.template.json",{"basePath":673,"description":674,"displayName":675,"installMethods":676,"rationale":677,"selectedPaths":678,"source":310,"sourceLanguage":18,"type":226},"skills/thoroughness-scoring","Score every decision point with a Thoroughness Rating (1-10). AI makes the marginal cost of doing things properly near-zero — pick the higher-rated option every time. Includes scope checks to distinguish contained vs unbounded work.","thoroughness-scoring",{"claudeCode":12},"SKILL.md frontmatter at skills/thoroughness-scoring/SKILL.md",[679],{"path":460,"priority":307},{"basePath":681,"description":682,"displayName":683,"installMethods":684,"rationale":685,"selectedPaths":686,"source":310,"sourceLanguage":18,"type":226},"skills/token-efficiency","Reduce token waste by 40-60% through anti-sycophancy rules, tool-call budgets, one-pass coding, task profiles, and read-before-write enforcement. Inspired by drona23/claude-token-efficient.","token-efficiency",{"claudeCode":12},"SKILL.md frontmatter at skills/token-efficiency/SKILL.md",[687],{"path":460,"priority":307},{"basePath":689,"description":690,"displayName":691,"installMethods":692,"rationale":693,"selectedPaths":694,"source":310,"sourceLanguage":18,"type":226},"skills/wiki-builder","Start, structure, and grow a persistent research wiki indexed in pro-workflow's SQLite knowledge base. Each wiki is a folder of markdown pages with provenance, plus a shadow FTS5 index so any session can recall it. Use when the user says \"start a wiki\", \"add to wiki\", \"compile a page\", \"wiki on X\", or wants a long-lived knowledge base on a topic, paper, product, person, project, or codebase.","wiki-builder",{"claudeCode":12},"SKILL.md frontmatter at skills/wiki-builder/SKILL.md",[695,696,698,700,702,704,706,708,710,712,714,716,718],{"path":460,"priority":307},{"path":697,"priority":320},"references/wiki-flavors.md",{"path":699,"priority":559},"scripts/init_wiki.sh",{"path":701,"priority":559},"scripts/wiki-cli.js",{"path":703,"priority":559},"templates/index.md",{"path":705,"priority":559},"templates/maintenance-log.md",{"path":707,"priority":559},"templates/prompts/compile-concept-page.md",{"path":709,"priority":559},"templates/prompts/compile-index.md",{"path":711,"priority":559},"templates/prompts/compile-source-page.md",{"path":713,"priority":559},"templates/prompts/lint-wiki.md",{"path":715,"priority":559},"templates/prompts/query-and-file.md",{"path":717,"priority":559},"templates/sources.md",{"path":719,"priority":559},"templates/wiki.config.md",{"basePath":721,"description":722,"displayName":723,"installMethods":724,"rationale":725,"selectedPaths":726,"source":310,"sourceLanguage":18,"type":226},"skills/wiki-query","Query pro-workflow wikis via SQLite FTS5 BM25 retrieval. Returns top-K passages with citations. Use when answering a question that any of the user's wikis already covers, when the user says \"what does the wiki say about X\", \"ask wiki\", \"search wikis\", or before drafting a new wiki page (to avoid duplication).","wiki-query",{"claudeCode":12},"SKILL.md frontmatter at skills/wiki-query/SKILL.md",[727,728],{"path":460,"priority":307},{"path":729,"priority":559},"scripts/query.js",{"basePath":731,"description":732,"displayName":733,"installMethods":734,"rationale":735,"selectedPaths":736,"source":310,"sourceLanguage":18,"type":226},"skills/wiki-research-loop","Auto-grow a pro-workflow wiki by running a budget-capped BFS research loop over pluggable source fetchers (web, arXiv, GitHub). Each iteration pops a seed from the queue, fetches sources, drafts a wiki page, dedupes claims against existing pages, enqueues follow-up seeds. Halts on budget cap, depth cap, or convergence. Use when the user says \"research \u003Ctopic>\", \"grow the \u003Cslug> wiki\", \"auto-research\", or wants a knowledge base that builds itself overnight.","wiki-research-loop",{"claudeCode":12},"SKILL.md frontmatter at skills/wiki-research-loop/SKILL.md",[737,738,740,742,744],{"path":460,"priority":307},{"path":739,"priority":559},"scripts/research-loop.js",{"path":741,"priority":559},"scripts/source-fetchers/arxiv.js",{"path":743,"priority":559},"scripts/source-fetchers/github.js",{"path":745,"priority":559},"scripts/source-fetchers/web.js",{"basePath":747,"description":748,"displayName":749,"installMethods":750,"rationale":751,"selectedPaths":752,"source":310,"sourceLanguage":18,"type":226},"skills/wiki-viewer","Render a self-contained HTML viewer for a pro-workflow wiki. Pages, sources, claims, seed queue, page-link graph and full-text search all in one file. No external dependencies, no JS framework, S3-uploadable. Use when the user wants to browse a wiki visually, share its current state with someone, audit research progress, or hand off a knowledge base. Inspired by Thariq Shihipar's \"Unreasonable Effectiveness of HTML\" — favors information density and shareability over markdown-only outputs.","wiki-viewer",{"claudeCode":12},"SKILL.md frontmatter at skills/wiki-viewer/SKILL.md",[753,754],{"path":460,"priority":307},{"path":755,"priority":559},"scripts/render.js",{"basePath":757,"description":758,"displayName":759,"installMethods":760,"rationale":761,"selectedPaths":762,"source":310,"sourceLanguage":18,"type":226},"skills/wrap-up","End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use when saying \"wrap up\", \"done for the day\", \"finish coding\", or ending a coding session.","wrap-up",{"claudeCode":12},"SKILL.md frontmatter at skills/wrap-up/SKILL.md",[763],{"path":460,"priority":307},{"sources":765},[766],"manual",{"npmPackage":225},{"closedIssues90d":211,"description":769,"forks":212,"homepage":770,"openIssues90d":8,"pushedAt":214,"readmeSize":209,"stars":215,"topics":771},"Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.","https://rohitg00.github.io/pro-workflow/infographic.html",[772,773,774,254,775,776,276,777,778,779,780,781,496,257,782,280,255,277,783],"claude","claude-code","cursor","agent-orchestration","ai-agents","ai-workflow","claude-code-plugin","claude-code-skills","claude-skills","codex","gemini-cli","worktrees",{"downloads":217},{"classifiedAt":786,"discoverAt":787,"extractAt":788,"githubAt":788,"npmAt":789,"updatedAt":786},1778696594915,1778696588306,1778696590961,1778696593284,[191,190,192,193,195,194],{"evaluatedAt":221,"extractAt":271,"updatedAt":221},[],[794,828,856,887,914,944],{"_creationTime":795,"_id":796,"community":797,"display":798,"identity":804,"providers":810,"relations":819,"tags":823,"workflow":824},1778693805112.8403,"k177f7s31ysk6nw1qw3sak1r3186n795",{"reviewCount":8},{"description":799,"installMethods":800,"name":802,"sourceUrl":803},"Evolution Engine 的领域知识 — 支持 LLM 从原始 OHLCV 数据中自主发现策略。涵盖生成-回测-选择-进化循环、向量化回测、样本外验证和策略梯度。在发现交易模式、运行回测、进化策略或审查进化日志时使用。由“evolve”、“discover patterns”、“backtest”、“evolution”、“strategy generation”、“candidate strategy”触发。",{"claudeCode":801},"mnemox-ai/tradememory-protocol","TradeMemory Protocol","https://github.com/mnemox-ai/tradememory-protocol",{"basePath":805,"githubOwner":806,"githubRepo":807,"locale":808,"slug":809,"type":226},"tradememory-plugin/skills/evolution-engine","mnemox-ai","tradememory-protocol","zh-CN","evolution-engine",{"evaluate":811,"extract":818},{"promptVersionExtension":183,"promptVersionScoring":184,"score":812,"tags":813,"targetMarket":196,"tier":197},100,[814,191,815,816,817,192],"trading","memory","audit","compliance",{"commitSha":260,"license":261},{"parentExtensionId":820,"repoId":821,"translatedFrom":822},"k170vxkqee48k2xq1v55a025nh86nzn7","kd73z11kfekksxyrs8ds0snacs86ncdy","k171p5pgbfbm5g4k5sa3y4cj9s86m6hk",[191,816,817,192,815,814],{"evaluatedAt":825,"extractAt":826,"updatedAt":827},1778693678813,1778693539593,1778693805112,{"_creationTime":829,"_id":830,"community":831,"display":832,"identity":838,"providers":842,"relations":849,"tags":852,"workflow":853},1778699234184.6135,"k175frmf44tn80mcd6gvw1c1th86ngq9",{"reviewCount":8},{"description":833,"installMethods":834,"name":836,"sourceUrl":837},"Invoke parallel document-specialist agents for external web searches and documentation lookup",{"claudeCode":835},"Yeachan-Heo/oh-my-claudecode","external-context","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":839,"githubOwner":840,"githubRepo":841,"locale":18,"slug":836,"type":226},"skills/external-context","Yeachan-Heo","oh-my-claudecode",{"evaluate":843,"extract":848},{"promptVersionExtension":183,"promptVersionScoring":184,"score":812,"tags":844,"targetMarket":196,"tier":197},[845,190,193,846,847],"search","information-retrieval","multi-agent",{"commitSha":260},{"parentExtensionId":850,"repoId":851},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[190,846,847,193,845],{"evaluatedAt":854,"extractAt":855,"updatedAt":854},1778699449790,1778699234184,{"_creationTime":857,"_id":858,"community":859,"display":860,"identity":866,"providers":871,"relations":879,"tags":882,"workflow":883},1778692818788.4202,"k17ambp6v3xcg52bx2sbp8fj9x86nvmv",{"reviewCount":8},{"description":861,"installMethods":862,"name":864,"sourceUrl":865},"分析 Karpathy 模式的 LLM Wiki 知识库，并生成一个交互式知识图谱，包含实体提取、隐含规则和主题聚类。",{"claudeCode":863},"Lum1104/Understand-Anything","Understand Knowledge","https://github.com/Lum1104/Understand-Anything",{"basePath":867,"githubOwner":868,"githubRepo":869,"locale":808,"slug":870,"type":226},"understand-anything-plugin/skills/understand-knowledge","Lum1104","Understand-Anything","understand-knowledge",{"evaluate":872,"extract":878},{"promptVersionExtension":183,"promptVersionScoring":184,"score":812,"tags":873,"targetMarket":196,"tier":197},[874,192,194,875,876,877],"knowledge-graph","entity-extraction","topic-clustering","python",{"commitSha":260,"license":261},{"repoId":880,"translatedFrom":881},"kd78egfytykkxxbpr6k3t7wsph86n83x","k174cf2tsjpdqmm0p10s8ybq5h86ngnx",[875,874,192,877,876,194],{"evaluatedAt":884,"extractAt":885,"updatedAt":886},1778692723004,1778692549705,1778692818788,{"_creationTime":888,"_id":889,"community":890,"display":891,"identity":897,"providers":900,"relations":905,"tags":909,"workflow":910},1778675389065.5505,"k17efbbhbjt47j1pr8as1ck3d586npx0",{"reviewCount":8},{"description":892,"installMethods":893,"name":895,"sourceUrl":896},"深入的递归研究，具有自我调节的循环，可达博士级别。适用于任何领域（科学、技术、商业、艺术、人文学科）。使用 WDM + Munger 反演进行自主决策、可靠来源分级和磁盘检查点以克服上下文限制。",{"claudeCode":894},"Anjos2/recursive-research","recursive-research","https://github.com/Anjos2/recursive-research",{"basePath":898,"githubOwner":899,"githubRepo":895,"locale":808,"slug":895,"type":226},"plugins/recursive-research/skills/recursive-research","Anjos2",{"evaluate":901,"extract":904},{"promptVersionExtension":183,"promptVersionScoring":184,"score":812,"tags":902,"targetMarket":196,"tier":197},[193,258,192,903,190],"decision-making",{"commitSha":260},{"parentExtensionId":906,"repoId":907,"translatedFrom":908},"k178rg6vs234c409g28ca6arbd86n5a1","kd753d1f20n4nwaapq6yp8vhd186nzxp","k17agpm4ma1bjqydbc6e6w2sr186m0k8",[903,190,258,192,193],{"evaluatedAt":911,"extractAt":912,"updatedAt":913},1778675358883,1778675291492,1778675389065,{"_creationTime":915,"_id":916,"community":917,"display":918,"identity":924,"providers":929,"relations":937,"tags":940,"workflow":941},1778696691708.3274,"k170az7r02e9e2v47mpy80kx6n86nff3",{"reviewCount":8},{"description":919,"installMethods":920,"name":922,"sourceUrl":923},"Detect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy",{"claudeCode":921},"ruvnet/ruflo","Trader Regime","https://github.com/ruvnet/ruflo",{"basePath":925,"githubOwner":926,"githubRepo":927,"locale":18,"slug":928,"type":226},"plugins/ruflo-neural-trader/skills/trader-regime","ruvnet","ruflo","trader-regime",{"evaluate":930,"extract":936},{"promptVersionExtension":183,"promptVersionScoring":184,"score":812,"tags":931,"targetMarket":196,"tier":197},[932,814,933,191,934,935],"finance","market-analysis","typescript","cli",{"commitSha":260,"license":261},{"parentExtensionId":938,"repoId":939},"k17drge8h1fgzchr0p4jaeg33n86mwmy","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[191,935,932,933,814,934],{"evaluatedAt":942,"extractAt":943,"updatedAt":942},1778701108877,1778696691708,{"_creationTime":945,"_id":946,"community":947,"display":948,"identity":952,"providers":954,"relations":958,"tags":960,"workflow":961},1778693819389.531,"k174n8dznk7k8dr9drb7fwx01586nm5t",{"reviewCount":8},{"description":949,"installMethods":950,"name":951,"sourceUrl":803},"AI交易记忆的领域知识 — 结果加权记忆 (OWM) 架构、5种记忆类型、回忆评分和行为分析。用于记录交易、回忆相似的上下文、分析性能或检查行为漂移。在 \"record trade\"、\"remember trade\"、\"recall\"、\"similar trades\"、\"performance\"、\"behavioral\"、\"disposition\"、\"affective state\"、\"confidence\" 时触发。",{"claudeCode":801},"trading-memory",{"basePath":953,"githubOwner":806,"githubRepo":807,"locale":808,"slug":951,"type":226},"tradememory-plugin/skills/trading-memory",{"evaluate":955,"extract":957},{"promptVersionExtension":183,"promptVersionScoring":184,"score":812,"tags":956,"targetMarket":196,"tier":197},[814,191,815,932,877],{"commitSha":260},{"parentExtensionId":820,"repoId":821,"translatedFrom":959},"k173a67a16bpq0e29wjd85v71986nx03",[191,932,815,877,814],{"evaluatedAt":962,"extractAt":826,"updatedAt":963},1778693719816,1778693819389]