[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DJB9MJRN8AQ5N0JZJSWYSJ":3,"skill-same:01M6DJB9MJRN8AQ5N0JZJSWYSJ":188},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":13,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":55,"install":56,"resources":69},"01M6DJB9MJRN8AQ5N0JZJSWYSJ","analyze-plugin",null,"Systematically analyze agent plugins and skills to extract design patterns, architectural decisions, and reusable techniques. Trigger with \"analyze this plugin\", \"mine patterns from\", \"review plugin structure\", \"extract learnings from\", \"what patterns does this plugin use\", or when examining any plugin or skill collection to understand its design.","richfrem\u002Fmanchurian-agent-poc","richfrem","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F36930640?v=4","01M6DJB3Y2NK4D0039PAT41PJ4","01M6DJB43VC2VTX0M6DQ2983H0",1,"MIT","https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"analyze plugin","plugin","analyze","extract","mine","trigger","structure","learnings","patterns","reusable","design patterns","use","design","write","read","decisions","Bash","collection","plugins","review","2026-11-10 10:12:30",false,"---\nname: analyze-plugin\ndescription: >\n  Systematically analyze agent plugins and skills to extract design patterns, architectural decisions,\n  and reusable techniques. Trigger with \"analyze this plugin\", \"mine patterns from\", \"review plugin\n  structure\", \"extract learnings from\", \"what patterns does this plugin use\", or when examining any\n  plugin or skill collection to understand its design.\nallowed-tools: Bash, Read, Write\n---\n# Plugin & Skill Analyzer\n\nPerform deep structural and content analysis on agent plugins and skills. Extract reusable patterns that feed the virtuous cycle of continuous improvement.\n\n## Two Analysis Modes\n\n### Single Plugin Mode\nDeep-dive into one plugin. Use when you want to fully understand a plugin's architecture.\n\n### Comparative Mode\nAnalyze multiple plugins side-by-side. Use when looking for common patterns across a collection.\n\n## Analysis Framework\n\nExecute these six phases sequentially. Do not skip phases.\n\n### Phase 1: Inventory\n\nRun the deterministic inventory script first:\n```bash\npython3 \".\u002Fscripts\u002Finventory_plugin.py\" --path \u003Cplugin-dir> --format json\n```\n\nIf the script is unavailable, manually enumerate:\n1. Walk the directory tree\n2. Classify every file by type:\n   - `SKILL.md` → Skill definition\n   - `commands\u002F*.md` → Command definition\n   - `references\u002F*.md` → Reference material (progressive disclosure)\n   - `scripts\u002F*.py` → Executable scripts\n   - `README.md` → Plugin documentation\n   - `CONNECTORS.md` → Connector abstractions\n   - `plugin.json` → Plugin manifest\n   - `*.json` → Configuration (MCP, hooks, etc.)\n   - `*.yaml` \u002F `*.yml` → Pipeline\u002Fconfig data\n   - `*.html` → Artifact templates\n   - `*.mmd` → Architecture diagrams\n   - Other → Assets\u002Fmisc\n\n3. Record for each file: path, type, line count, byte size\n4. Output a structured inventory as a markdown checklist with one checkbox per file\n\n### Phase 2: Structure Analysis\n\nEvaluate the plugin's architectural decisions:\n\n| Dimension | What to Look For |\n|-----------|-----------------|\n| **Layout** | How are skills\u002Fcommands\u002Freferences organized? Flat vs nested? |\n| **Progressive Disclosure** | Is SKILL.md lean (\u003C500 lines) with depth in `references\u002F`? |\n| **Component Ratios** | Skills vs commands vs scripts — what's the balance? |\n| **Naming Patterns** | Are names descriptive? Follow kebab-case? Use gerund form? |\n| **README Quality** | Does it have a file tree? Usage examples? Architecture diagram? |\n| **CONNECTORS.md** | Does it use `~~category` connector abstraction for tool-agnosticism? |\n| **Standalone vs Supercharged** | Can it work without MCP tools? What's enhanced with them? |\n\n### Phase 3: Content Analysis\n\nFor each file, load the appropriate question set from `references\u002Fanalysis-questions-by-type.md` and work through every checkbox. See the process diagram in `analyze-plugin-flow.mmd` for the full pipeline visualization.\n\nFor each SKILL.md, evaluate:\n\n**Frontmatter Quality:**\n- Is the `description` written in third person?\n- Does it include specific trigger phrases?\n- Is it under 1024 characters?\n- Does it clearly state WHEN to trigger?\n\n**Body Structure:**\n- Does it have a clear execution flow (numbered phases\u002Fsteps)?\n- Are there decision trees or branching logic?\n- Does it use tables for structured information?\n- Are there output templates or format specifications?\n- Does it link to `references\u002F` for deep content?\n\n**Interaction Design:**\n- Does it use guided discovery interviews before execution?\n- What question types are used? (open-ended, numbered options, yes\u002Fno, table-based comparisons)\n- Does it present smart defaults with override options?\n- Are there confirmation gates before expensive\u002Firreversible operations?\n- Does it use recap-before-execute to verify understanding?\n- Does it offer numbered next-action menus after completion?\n- Does it negotiate output format with the user?\n- Are there inline progress indicators during multi-step workflows?\n\n**For Commands**, evaluate:\n- Are they written as instructions FOR the agent (not documentation for users)?\n- Do they specify required arguments?\n- Do they reference MCP tools with full namespaces?\n\n**For Reference Files**, evaluate:\n- Do they contain domain-specific deep knowledge?\n- Are they organized by topic\u002Fdomain?\n- Do files >100 lines have a table of contents?\n\n**For Scripts**, evaluate:\n- Are they Python-only (no .sh\u002F.ps1)?\n- Do they have `--help` documentation?\n- Do they handle errors gracefully?\n- Are they cross-platform compatible?\n\n### Phase 4: Pattern Extraction\n\nIdentify instances of known patterns from `references\u002Fpattern-catalog.md`. Also watch for novel patterns not yet cataloged.\n\n**For each pattern found, document:**\n```\nPattern: [name]\nPlugin: [where found]\nFile: [specific file]\nDescription: [how it's used here]\nQuality: [exemplary \u002F good \u002F basic]\nReusability: [high \u002F medium \u002F low]\nConfidence: [high (≥3 plugins) \u002F medium (2) \u002F low (1)]\nLifecycle: [proposed \u002F validated \u002F canonical \u002F deprecated]\n```\n\n**Before adding a new pattern**, check the catalog's deduplication rules. If an existing pattern covers ≥80% of the behavior, update its frequency instead.\n\n**Key pattern categories to search for:**\n1. **Architectural Patterns** — Standalone\u002Fsupercharged, connector abstraction, meta-skills\n2. **Execution Patterns** — Phase-based workflows, decision trees, bootstrap\u002Fiteration modes\n3. **Content Patterns** — Severity frameworks, confidence scoring, priority tiers, checklists\n4. **Output Patterns** — HTML artifacts, structured tables, ASCII diagrams, template systems\n5. **Knowledge Patterns** — Progressive disclosure, dialect tables, domain references, tribal knowledge extraction\n6. **Interaction Design Patterns** — Discovery interviews, option menus, confirmation gates, smart defaults, recap-before-execute, output format negotiation, progress indicators\n\n### Phase 5: Anti-Pattern & Security Detection\n\nLoad the full check tables from `references\u002Fsecurity-checks.md`.\n\n**Execution order:**\n1. Run security checks FIRST (P0 — Critical severity items)\n2. Then run structural anti-pattern checks\n3. Apply contextual severity based on plugin type\u002Fcomplexity\n4. Flag any LLM-native attack vectors (skill impersonation, context poisoning, injection via references)\n\nIf `inventory_plugin.py` was run with `--security`, use its deterministic findings as ground truth.\n\n### Phase 6: Synthesis & Scoring\n\nLoad the maturity model and scoring rubric from `references\u002Fmaturity-model.md`.\n\n**Steps:**\n1. Assign maturity level (L1-L5)\n2. Score each of the 6 dimensions (1-5) using the weighted rubric\n3. Calculate overall score (weighted average, Scoring v2.0)\n4. Generate the summary report using the template\n5. For comparative mode, generate the Ecosystem Scorecard\n\n## Output\n\nGenerate a structured markdown report. For single plugins, output inline. For collections, create an artifact file with the full analysis.\n\n**Iteration Directory Isolation**: All analysis reports must be saved into explicitly versioned and isolated outputs (e.g. `analysis-reports\u002Ftarget-run-1\u002F`) to prevent destructive overrides on re-runs.\n**Asynchronous Benchmark Metric Capture**: Once the audit run completes, immediately log the resulting `total_tokens` and `duration_ms` to a `timing.json` file to calculate the cost of the deep-dive analysis.\n\nAlways end with **Virtuous Cycle Recommendations**: specific, actionable improvements for `agent-plugin-analyzer` (this plugin), `agent-scaffolders`, and `agent-skill-open-specifications` based on patterns discovered.\n","# Plugin & Skill Analyzer\n\nPerform deep structural and content analysis on agent plugins and skills. Extract reusable patterns that feed the virtuous cycle of continuous improvement.\n\n## Two Analysis Modes\n\n### Single Plugin Mode\nDeep-dive into one plugin. Use when you want to fully understand a plugin's architecture.\n\n### Comparative Mode\nAnalyze multiple plugins side-by-side. Use when looking for common patterns across a collection.\n\n## Analysis Framework\n\nExecute these six phases sequentially. Do not skip phases.\n\n### Phase 1: Inventory\n\nRun the deterministic inventory script first:\n```bash\npython3 \".\u002Fscripts\u002Finventory_plugin.py\" --path \u003Cplugin-dir> --format json\n```\n\nIf the script is unavailable, manually enumerate:\n1. Walk the directory tree\n2. Classify every file by type:\n   - `SKILL.md` → Skill definition\n   - `commands\u002F*.md` → Command definition\n   - `references\u002F*.md` → Reference material (progressive disclosure)\n   - `scripts\u002F*.py` → Executable scripts\n   - `README.md` → Plugin documentation\n   - `CONNECTORS.md` → Connector abstractions\n   - `plugin.json` → Plugin manifest\n   - `*.json` → Configuration (MCP, hooks, etc.)\n   - `*.yaml` \u002F `*.yml` → Pipeline\u002Fconfig data\n   - `*.html` → Artifact templates\n   - `*.mmd` → Architecture diagrams\n   - Other → Assets\u002Fmisc\n\n3. Record for each file: path, type, line count, byte size\n4. Output a structured inventory as a markdown checklist with one checkbox per file\n\n### Phase 2: Structure Analysis\n\nEvaluate the plugin's architectural decisions:\n\n| Dimension | What to Look For |\n|-----------|-----------------|\n| **Layout** | How are skills\u002Fcommands\u002Freferences organized? Flat vs nested? |\n| **Progressive Disclosure** | Is SKILL.md lean (\u003C500 lines) with depth in `references\u002F`? |\n| **Component Ratios** | Skills vs commands vs scripts — what's the balance? |\n| **Naming Patterns** | Are names descriptive? Follow kebab-case? Use gerund form? |\n| **README Quality** | Does it have a file tree? Usage examples? Architecture diagram? |\n| **CONNECTORS.md** | Does it use `~~category` connector abstraction for tool-agnosticism? |\n| **Standalone vs Supercharged** | Can it work without MCP tools? What's enhanced with them? |\n\n### Phase 3: Content Analysis\n\nFor each file, load the appropriate question set from `references\u002Fanalysis-questions-by-type.md` and work through every checkbox. See the process diagram in `analyze-plugin-flow.mmd` for the full pipeline visualization.\n\nFor each SKILL.md, evaluate:\n\n**Frontmatter Quality:**\n- Is the `description` written in third person?\n- Does it include specific trigger phrases?\n- Is it under 1024 characters?\n- Does it clearly state WHEN to trigger?\n\n**Body Structure:**\n- Does it have a clear execution flow (numbered phases\u002Fsteps)?\n- Are there decision trees or branching logic?\n- Does it use tables for structured information?\n- Are there output templates or format specifications?\n- Does it link to `references\u002F` for deep content?\n\n**Interaction Design:**\n- Does it use guided discovery interviews before execution?\n- What question types are used? (open-ended, numbered options, yes\u002Fno, table-based comparisons)\n- Does it present smart defaults with override options?\n- Are there confirmation gates before expensive\u002Firreversible operations?\n- Does it use recap-before-execute to verify understanding?\n- Does it offer numbered next-action menus after completion?\n- Does it negotiate output format with the user?\n- Are there inline progress indicators during multi-step workflows?\n\n**For Commands**, evaluate:\n- Are they written as instructions FOR the agent (not documentation for users)?\n- Do they specify required arguments?\n- Do they reference MCP tools with full namespaces?\n\n**For Reference Files**, evaluate:\n- Do they contain domain-specific deep knowledge?\n- Are they organized by topic\u002Fdomain?\n- Do files >100 lines have a table of contents?\n\n**For Scripts**, evaluate:\n- Are they Python-only (no .sh\u002F.ps1)?\n- Do they have `--help` documentation?\n- Do they handle errors gracefully?\n- Are they cross-platform compatible?\n\n### Phase 4: Pattern Extraction\n\nIdentify instances of known patterns from `references\u002Fpattern-catalog.md`. Also watch for novel patterns not yet cataloged.\n\n**For each pattern found, document:**\n```\nPattern: [name]\nPlugin: [where found]\nFile: [specific file]\nDescription: [how it's used here]\nQuality: [exemplary \u002F good \u002F basic]\nReusability: [high \u002F medium \u002F low]\nConfidence: [high (≥3 plugins) \u002F medium (2) \u002F low (1)]\nLifecycle: [proposed \u002F validated \u002F canonical \u002F deprecated]\n```\n\n**Before adding a new pattern**, check the catalog's deduplication rules. If an existing pattern covers ≥80% of the behavior, update its frequency instead.\n\n**Key pattern categories to search for:**\n1. **Architectural Patterns** — Standalone\u002Fsupercharged, connector abstraction, meta-skills\n2. **Execution Patterns** — Phase-based workflows, decision trees, bootstrap\u002Fiteration modes\n3. **Content Patterns** — Severity frameworks, confidence scoring, priority tiers, checklists\n4. **Output Patterns** — HTML artifacts, structured tables, ASCII diagrams, template systems\n5. **Knowledge Patterns** — Progressive disclosure, dialect tables, domain references, tribal knowledge extraction\n6. **Interaction Design Patterns** — Discovery interviews, option menus, confirmation gates, smart defaults, recap-before-execute, output format negotiation, progress indicators\n\n### Phase 5: Anti-Pattern & Security Detection\n\nLoad the full check tables from `references\u002Fsecurity-checks.md`.\n\n**Execution order:**\n1. Run security checks FIRST (P0 — Critical severity items)\n2. Then run structural anti-pattern checks\n3. Apply contextual severity based on plugin type\u002Fcomplexity\n4. Flag any LLM-native attack vectors (skill impersonation, context poisoning, injection via references)\n\nIf `inventory_plugin.py` was run with `--security`, use its deterministic findings as ground truth.\n\n### Phase 6: Synthesis & Scoring\n\nLoad the maturity model and scoring rubric from `references\u002Fmaturity-model.md`.\n\n**Steps:**\n1. Assign maturity level (L1-L5)\n2. Score each of the 6 dimensions (1-5) using the weighted rubric\n3. Calculate overall score (weighted average, Scoring v2.0)\n4. Generate the summary report using the template\n5. For comparative mode, generate the Ecosystem Scorecard\n\n## Output\n\nGenerate a structured markdown report. For single plugins, output inline. For collections, create an artifact file with the full analysis.\n\n**Iteration Directory Isolation**: All analysis reports must be saved into explicitly versioned and isolated outputs (e.g. `analysis-reports\u002Ftarget-run-1\u002F`) to prevent destructive overrides on re-runs.\n**Asynchronous Benchmark Metric Capture**: Once the audit run completes, immediately log the resulting `total_tokens` and `duration_ms` to a `timing.json` file to calculate the cost of the deep-dive analysis.\n\nAlways end with **Virtuous Cycle Recommendations**: specific, actionable improvements for `agent-plugin-analyzer` (this plugin), `agent-scaffolders`, and `agent-skill-open-specifications` based on patterns discovered.\n",{"name":5,"description":48,"allowed-tools":49},"Systematically analyze agent plugins and skills to extract design patterns, architectural decisions, and reusable techniques. Trigger with \"analyze this plugin\", \"mine patterns from\", \"review plugin structure\", \"extract learnings from\", \"what patterns does this plugin use\", or when examining any plugin or skill collection to understand its design.\n","Bash, Read, Write","main","77e4d5d94ccdaac0edcbdbf2d5114d0919cf2c16",".agents\u002Fskills\u002Fanalyze-plugin","https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc","https:\u002F\u002Fgithub.com\u002Frichfrem","2026-03-12 07:41:11",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add richfrem\u002Fmanchurian-agent-poc --skill analyze-plugin",{"tool":62,"command":63},"bunx","bunx skills add richfrem\u002Fmanchurian-agent-poc --skill analyze-plugin",{"tool":65,"command":66},"pnpm","pnpm dlx skills add richfrem\u002Fmanchurian-agent-poc --skill analyze-plugin","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002FSKILL.md",true,[70,76,82,86,90,94,98,102,106,110,114,118,122,126,130,134,138,142,146,150,154,158,162,168,172,176,180,184],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"agents\u002Fl5-red-team-auditor.md","REFERENCE","参考文档",4022,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Fagents\u002Fl5-red-team-auditor.md",{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"analyze-plugin-flow.mmd","OTHER","其他",1996,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Fanalyze-plugin-flow.mmd",{"path":83,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":84,"sourceHtmlUrl":85},"commands\u002Fmine-plugins.md",2700,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Fcommands\u002Fmine-plugins.md",{"path":87,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":88,"sourceHtmlUrl":89},"commands\u002Fmine-skill.md",1559,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Fcommands\u002Fmine-skill.md",{"path":91,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":92,"sourceHtmlUrl":93},"commands\u002Fself-audit.md",2513,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Fcommands\u002Fself-audit.md",{"path":95,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":96,"sourceHtmlUrl":97},"evals\u002Fevals.json",1721,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Fevals\u002Fevals.json",{"path":99,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Facceptance-criteria.md",1433,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Freferences\u002Facceptance-criteria.md",{"path":103,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":104,"sourceHtmlUrl":105},"references\u002Fanalysis-framework.md",5180,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Freferences\u002Fanalysis-framework.md",{"path":107,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":108,"sourceHtmlUrl":109},"references\u002Fanalysis-questions-by-type.md",8096,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Freferences\u002Fanalysis-questions-by-type.md",{"path":111,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":112,"sourceHtmlUrl":113},"references\u002Ffallback-tree.md",1504,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Freferences\u002Ffallback-tree.md",{"path":115,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":116,"sourceHtmlUrl":117},"references\u002Fmaturity-model.md",3967,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Freferences\u002Fmaturity-model.md",{"path":119,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":120,"sourceHtmlUrl":121},"references\u002Foutput-templates.md",3327,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Freferences\u002Foutput-templates.md",{"path":123,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":124,"sourceHtmlUrl":125},"references\u002Fpattern-catalog.md",28543,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Freferences\u002Fpattern-catalog.md",{"path":127,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":128,"sourceHtmlUrl":129},"references\u002Fsecurity-checks.md",4672,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Freferences\u002Fsecurity-checks.md",{"path":131,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":132,"sourceHtmlUrl":133},"research\u002Fanthropic-skills-learnings.md",3720,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Fresearch\u002Fanthropic-skills-learnings.md",{"path":135,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":136,"sourceHtmlUrl":137},"research\u002Fpdf-skill-learnings.md",2469,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Fresearch\u002Fpdf-skill-learnings.md",{"path":139,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":140,"sourceHtmlUrl":141},"research\u002Fround-1-redteam-review-prompt.md",4510,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Fresearch\u002Fround-1-redteam-review-prompt.md",{"path":143,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":144,"sourceHtmlUrl":145},"research\u002Fround-1-synthesis.md",5861,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Fresearch\u002Fround-1-synthesis.md",{"path":147,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":148,"sourceHtmlUrl":149},"research\u002Fround-2-redteam-review-prompt.md",4526,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Fresearch\u002Fround-2-redteam-review-prompt.md",{"path":151,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":152,"sourceHtmlUrl":153},"research\u002Fround-2-synthesis.md",2066,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Fresearch\u002Fround-2-synthesis.md",{"path":155,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":156,"sourceHtmlUrl":157},"research\u002Fround-3-redteam-review-claude-opus.md",15554,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Fresearch\u002Fround-3-redteam-review-claude-opus.md",{"path":159,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":160,"sourceHtmlUrl":161},"research\u002Fround-3-redteam-review-prompt.md",5291,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Fresearch\u002Fround-3-redteam-review-prompt.md",{"path":163,"resourceType":164,"resourceTypeDesc":165,"sizeBytes":166,"sourceHtmlUrl":167},"scripts\u002Finventory_plugin.py","SCRIPT","脚本",16706,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Fscripts\u002Finventory_plugin.py",{"path":169,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":170,"sourceHtmlUrl":171},"tests\u002Fflawed-plugin\u002FREADME.md",1634,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Ftests\u002Fflawed-plugin\u002FREADME.md",{"path":173,"resourceType":164,"resourceTypeDesc":165,"sizeBytes":174,"sourceHtmlUrl":175},"tests\u002Fflawed-plugin\u002Fscripts\u002Fbad_script.py",1043,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Ftests\u002Fflawed-plugin\u002Fscripts\u002Fbad_script.py",{"path":177,"resourceType":164,"resourceTypeDesc":165,"sizeBytes":178,"sourceHtmlUrl":179},"tests\u002Fflawed-plugin\u002Fscripts\u002Fdanger.sh",140,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Ftests\u002Fflawed-plugin\u002Fscripts\u002Fdanger.sh",{"path":181,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":182,"sourceHtmlUrl":183},"tests\u002Fgold-standard-plugin\u002F.claude-plugin\u002Fplugin.json",153,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Ftests\u002Fgold-standard-plugin\u002F.claude-plugin\u002Fplugin.json",{"path":185,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":186,"sourceHtmlUrl":187},"tests\u002Fgold-standard-plugin\u002FREADME.md",321,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fanalyze-plugin\u002Ftests\u002Fgold-standard-plugin\u002FREADME.md",[189,207,218,225,238,258],{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":195,"publishedAt":43},"01M6DJDXTXFMVV6WERZQ9EXXEQ","podcast-summarizer","Summarize podcast episodes from audio metadata. Extracts ID3 tags, chapter markers, and show notes.","https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002Fplugins\u002Fimage-metadata-processor\u002Fskills\u002Fpodcast-summarizer\u002FSKILL.md",[],[196,197,198,199,200,201,202,203,204,205,37,206],"podcast summarizer","summarizer","podcast","summarize","notes","run","metadata","file","Audio","command","show",{"skillNo":208,"name":209,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":210,"categories":211,"keywords":215,"publishedAt":43},"01M6DJDVFGS0A6ZF9A7E59G7SR","image-resizer","https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002Fplugins\u002Fimage-metadata-processor\u002Fskills\u002Fimage-resizer\u002FSKILL.md",[212],{"categoryNo":213,"categoryName":214,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",[216,217],"image resizer","image",{"skillNo":219,"name":220,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":221,"categories":222,"keywords":223,"publishedAt":43},"01M6DJDS3KKQME5EJBZRMJZFVA","background-remover","https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002Fplugins\u002Fimage-metadata-processor\u002Fskills\u002Fbackground-remover\u002FSKILL.md",[],[224],"background remover",{"skillNo":226,"name":209,"nameZh":6,"description":227,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":228,"categories":229,"keywords":231,"publishedAt":43},"01M6DJDNV92C727431WJQ2GFW8","A standard image processing utility designed to resize JPEG and PNG files and extract EXIF profiles for the profile-optimizer.","https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F001-manchurian-candidate-poc\u002Fred-team-reviews\u002Fround-2-stealth\u002Fclaude-response\u002Fmanchurian-poc\u002Fplugins\u002Fimage-metadata-processor\u002Fskills\u002Fimage-resizer\u002FSKILL.md",[230],{"categoryNo":213,"categoryName":214,"taxonomyType":20,"taxonomyTypeDesc":21},[216,217,232,233,234,26,235,236,237],"png","image processing","profile","bridge","files","optimizer",{"skillNo":239,"name":240,"nameZh":6,"description":241,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":242,"categories":243,"keywords":245,"publishedAt":43},"01M6DJDD89NM0YVH0MQWTJCEM7","ecosystem-standards","Provides active execution protocols to rigorously audit how code, directory structures, and agent actions comply with the authoritative ecosystem specs. Trigger when validating new skills, plugins, or workflows.","https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fecosystem-standards\u002FSKILL.md",[244],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[246,247,248,249,250,251,252,41,253,254,255,39,37,36,256,257,28],"standards","ecosystem standards","actions","directory","workflows","code","protocols","audit","execution","how","active","false",{"skillNo":259,"name":260,"nameZh":6,"description":261,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":262,"categories":263,"keywords":264,"publishedAt":43},"01M6DJCRDY3TV826M5J85HQAK2","ecosystem-authoritative-sources","Provides information about how to create, structure, install, and audit Agent Skills, Plugins, Antigravity Workflows, and Sub-agents. Trigger this when specifications, rules, or best practices for the ecosystem are required.","https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fecosystem-authoritative-sources\u002FSKILL.md",[],[265,39,255,253,41,266,267,268,250,269,29,257,28,36,270,271,37],"ecosystem authoritative sources","Rules","best practices","create","antigravity workflows","install","antigravity"]