[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75FZ2ZFHJD9B0D6B2854G6M":3,"skill-same:01M75FZ2ZFHJD9B0D6B2854G6M":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M75FZ2ZFHJD9B0D6B2854G6M","feature-gap-bottleneck-analysis",null,"Triggered when the agent needs to audit, discover, and resolve missing features, architectural or functional gaps, performance\u002Fprocess bottlenecks, and structural complexity liabilities across a codebase, delivering lean and pragmatic improvement blueprints.","RudyCity\u002Fsuperagent","RudyCity","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F82188919?v=4","01M75FP5X8AW8ACBH0SH34WS7M","01M75FP5YAHJK8M1Q52BWXB82K",70,"MIT","https:\u002F\u002Fgithub.com\u002FRudyCity\u002Fsuperagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ffeature-gap-bottleneck-analysis\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: feature-gap-bottleneck-analysis\ndescription: >-\n  Triggered when the agent needs to audit, discover, and resolve missing features, architectural or functional gaps,\n  performance\u002Fprocess bottlenecks, and structural complexity liabilities across a codebase, delivering lean and pragmatic improvement blueprints.\n---\n\n# Feature, Gap & Bottleneck Analysis (`feature-gap-bottleneck-analysis`)\n\nCombines **Single-Agent Cognitive Scale-Up** (high-density batch scanning, symbolic indexing, fractal clustering) with **Pragmatic Minimalism** (lean solutions, liability reduction, zero unnecessary abstractions) to audit codebases for missing capabilities, structural gaps, performance bottlenecks, and system friction—followed by concrete, high-ROI improvement blueprints.\n\n---\n\n## When to Use This Skill\n\n- Triggered by keywords or user intent:\n  - **English**: \"missing feature\", \"feature gap\", \"gap analysis\", \"find bottlenecks\", \"system bottleneck\", \"performance gap\", \"architectural gap\", \"audit codebase gaps\", \"system audit\", \"improvement suggestions\".\n  - **Indonesian**: \"missing fitur\", \"fitur hilang\", \"fitur terlewat\", \"analisis gap\", \"analisis bottleneck\", \"temukan bottleneck\", \"saran perbaikan\", \"penambahan fitur\", \"peningkatan sistem\".\n- When conducting system health checks, pre-refactor audits, or technical debt assessments.\n- When reviewing a module\u002Fworkspace for missing edge-case handling, incomplete user flows, or latent performance limiters.\n\n---\n\n## Core Principles\n\n1. **High-Density Vector Indexing (`G[001..N]`)**: Map all discovered issues into compact symbolic representations rather than verbose prose.\n2. **Fractal Clustering ($\\alpha, \\beta, \\gamma, \\delta$)**: Group micro-gaps into macro structural categories to solve systemic root causes rather than patching symptoms.\n3. **Pragmatic ROI Filtering**: Evaluate all potential additions\u002Fenhancements using the **Impact vs. Complexity** matrix. Reject speculative or over-engineered suggestions.\n4. **Code is Liability**: Prefer solution vectors that delete redundant code, recycle existing helpers, or leverage standard\u002Fnative APIs over introducing new dependencies or heavy layers.\n\n---\n\n## Execution Workflow\n\n```\n[Target Codebase \u002F Feature Scope]\n              │\n              ▼\n  Phase 1: Vector Indexing G[001..N] (High-Density Scanning)\n              │\n              ▼\n  Phase 2: Fractal Category Clustering (α, β, γ, δ)\n              │\n              ▼\n  Phase 3: Pragmatic ROI Filter (Impact vs Complexity Matrix)\n              │\n              ▼\n  Phase 4: Actionable Resolution Vectors (Lean Patch Blueprints)\n```\n\n---\n\n### Phase 1: High-Density Diagnostic Scanning (`G[001..N]`)\n\nScan the target scope (code files, routing, state management, API routes, configurations) and convert each finding into a vectorized symbolic index:\n\n```text\nG[001..N] = { ID, FileLocation, IssueType, InvariantBreach, Symptom }\n```\n\n*Example Indexing*:\n- `G001: [routes\u002Fuser.ts:L42] ↔ [Missing Validation] ⇒ [Invalid Payload crash] → TYPE: Gap`\n- `G002: [services\u002Fsync.ts:L115] ↔ [Sequential Await Loop] ⇒ [High Latency] → TYPE: Bottleneck`\n- `G003: [components\u002FChat.tsx] ↔ [No Retry on Websocket Disconnect] ⇒ [Stale UI State] → TYPE: MissingFeature`\n\n---\n\n### Phase 2: Fractal Category Clustering\n\nGroup all `G[001..N]` micro-findings into **4 Macro Root Cause Clusters**:\n\n| Cluster | Category | Focus Area | Example Symptoms |\n|---|---|---|---|\n| **Cluster $\\alpha$** | **Missing Features & Incomplete Flows** | Missing API capabilities, unhandled user intents, incomplete lifecycle events, missing UI states (empty\u002Floading\u002Ferror). | No pagination on list endpoint, missing session resume feature. |\n| **Cluster $\\beta$** | **Architectural & Security Gaps** | Type safety holes, unhandled edge cases, race conditions, missing input bounds, broken authorization checks. | Missing payload schema validation, uncaught promise rejection in background job. |\n| **Cluster $\\gamma$** | **Performance & Resource Bottlenecks** | Blocking sync execution, redundant DB\u002Fnetwork calls, memory leaks, unindexed queries, expensive re-renders. | Sequential `await` in `Array.map`, unthrottled search handler. |\n| **Cluster $\\delta$** | **Complexity & Maintainability Liabilities** | Over-engineered layers, duplicate utility functions, dead code, single-caller abstractions, tight coupling. | Custom HTTP wrapper replacing standard `fetch`, 1500-line bloated router file. |\n\n---\n\n### Phase 3: Pragmatic ROI Filter Matrix\n\nFilter every proposed improvement through the **Pragmatic ROI Grid** before presenting recommendations:\n\n```\n                  High Impact\n                      │\n     [QUICK WIN]      │    [CORE REFACTOR]\n     High Value,      │    High Value,\n     Low Complexity   │    Medium\u002FHigh Effort\n──────────────────────┼──────────────────────\n     [DISCARD]        │    [DEFER \u002F AVOID]\n     Low Value,       │    Low Value,\n     Low Complexity   │    High Complexity (Over-engineering)\n                      │\n                  Low Impact\n  Low Complexity ────────────── High Complexity\n```\n\n- **Include**: Quick Wins & Core Refactors.\n- **Reject \u002F Exclude**: Low-impact over-engineering, speculative abstractions, or installing heavy third-party libraries when built-in runtime APIs suffice.\n\n---\n\n### Phase 4: Output & Actionable Resolution Vectors\n\nPresent the analysis using a **Zero-Fluff Findings Matrix** followed by **Pragmatic Improvement Blueprints**.\n\n#### 1. Discovered Gaps & Bottlenecks Matrix\n\n```markdown\n| Index | Category | Target File \u002F Location | Issue Description | Impact \u002F Priority |\n|---|---|---|---|---|\n| G001 | Cluster α (Missing Feature) | `backend\u002Fsrc\u002Fuser.ts:L42` | Missing pagination & field filtering on list API | High (Quick Win) |\n| G002 | Cluster β (Arch Gap) | `backend\u002Fsrc\u002Fbridge.ts:L88` | Unhandled WebSocket ECONNRESET crashes process | Critical (Core Refactor) |\n| G003 | Cluster γ (Bottleneck) | `frontend\u002Fsrc\u002FFeed.tsx:L12` | Un-memoized item list triggers full UI re-renders | Med (Quick Win) |\n| G004 | Cluster δ (Liability) | `backend\u002Fsrc\u002Futils.ts:L100` | Custom 200-line string parser replacing `URLSearchParams` | Med (Cleanup) |\n```\n\n#### 2. Pragmatic Improvement Blueprints\n\nFor each high-priority cluster\u002Findex, provide lean, actionable improvement blueprints:\n\n```markdown\n### Blueprint 1: [G001] Add Lean Pagination & Filtering\n- **Target**: `[user.ts](file:\u002F\u002F\u002Fd:\u002Fpath\u002Fto\u002Fuser.ts#L42-L60)`\n- **Problem**: Large payloads cause high latency and memory spikes.\n- **Pragmatic Solution**: Leverage native SQL `LIMIT\u002FOFFSET` or query param parsing with zero extra packages.\n- **Delta Vector**:\n  ```diff\n  - const users = await db.query('SELECT * FROM users');\n  + const limit = Math.min(Number(req.query.limit) || 20, 100);\n  + const offset = Number(req.query.offset) || 0;\n  + const users = await db.query('SELECT * FROM users LIMIT ? OFFSET ?', [limit, offset]);\n  ```\n- **Verification**: Test API with `?limit=10&offset=0`.\n```\n\n---\n\n## Quick Diagnostic Checklist\n\nWhen running this skill, answer these 5 diagnostic questions:\n1. **Feature Check**: What logical user flow or system interaction ends abruptly without resolution?\n2. **Robustness Check**: Where does the application crash when given unexpected or missing inputs?\n3. **Bottleneck Check**: Where is execution synchronously blocked waiting on sequential I\u002FO or heavy loops?\n4. **Complexity Check**: What custom hand-rolled code can be replaced by built-in runtime\u002Fplatform APIs?\n5. **Liability Check**: Which files exceed length\u002Fcomplexity bounds (>500 lines or high nesting) and need modular splitting?\n","# Feature, Gap & Bottleneck Analysis (`feature-gap-bottleneck-analysis`)\n\nCombines **Single-Agent Cognitive Scale-Up** (high-density batch scanning, symbolic indexing, fractal clustering) with **Pragmatic Minimalism** (lean solutions, liability reduction, zero unnecessary abstractions) to audit codebases for missing capabilities, structural gaps, performance bottlenecks, and system friction—followed by concrete, high-ROI improvement blueprints.\n\n---\n\n## When to Use This Skill\n\n- Triggered by keywords or user intent:\n  - **English**: \"missing feature\", \"feature gap\", \"gap analysis\", \"find bottlenecks\", \"system bottleneck\", \"performance gap\", \"architectural gap\", \"audit codebase gaps\", \"system audit\", \"improvement suggestions\".\n  - **Indonesian**: \"missing fitur\", \"fitur hilang\", \"fitur terlewat\", \"analisis gap\", \"analisis bottleneck\", \"temukan bottleneck\", \"saran perbaikan\", \"penambahan fitur\", \"peningkatan sistem\".\n- When conducting system health checks, pre-refactor audits, or technical debt assessments.\n- When reviewing a module\u002Fworkspace for missing edge-case handling, incomplete user flows, or latent performance limiters.\n\n---\n\n## Core Principles\n\n1. **High-Density Vector Indexing (`G[001..N]`)**: Map all discovered issues into compact symbolic representations rather than verbose prose.\n2. **Fractal Clustering ($\\alpha, \\beta, \\gamma, \\delta$)**: Group micro-gaps into macro structural categories to solve systemic root causes rather than patching symptoms.\n3. **Pragmatic ROI Filtering**: Evaluate all potential additions\u002Fenhancements using the **Impact vs. Complexity** matrix. Reject speculative or over-engineered suggestions.\n4. **Code is Liability**: Prefer solution vectors that delete redundant code, recycle existing helpers, or leverage standard\u002Fnative APIs over introducing new dependencies or heavy layers.\n\n---\n\n## Execution Workflow\n\n```\n[Target Codebase \u002F Feature Scope]\n              │\n              ▼\n  Phase 1: Vector Indexing G[001..N] (High-Density Scanning)\n              │\n              ▼\n  Phase 2: Fractal Category Clustering (α, β, γ, δ)\n              │\n              ▼\n  Phase 3: Pragmatic ROI Filter (Impact vs Complexity Matrix)\n              │\n              ▼\n  Phase 4: Actionable Resolution Vectors (Lean Patch Blueprints)\n```\n\n---\n\n### Phase 1: High-Density Diagnostic Scanning (`G[001..N]`)\n\nScan the target scope (code files, routing, state management, API routes, configurations) and convert each finding into a vectorized symbolic index:\n\n```text\nG[001..N] = { ID, FileLocation, IssueType, InvariantBreach, Symptom }\n```\n\n*Example Indexing*:\n- `G001: [routes\u002Fuser.ts:L42] ↔ [Missing Validation] ⇒ [Invalid Payload crash] → TYPE: Gap`\n- `G002: [services\u002Fsync.ts:L115] ↔ [Sequential Await Loop] ⇒ [High Latency] → TYPE: Bottleneck`\n- `G003: [components\u002FChat.tsx] ↔ [No Retry on Websocket Disconnect] ⇒ [Stale UI State] → TYPE: MissingFeature`\n\n---\n\n### Phase 2: Fractal Category Clustering\n\nGroup all `G[001..N]` micro-findings into **4 Macro Root Cause Clusters**:\n\n| Cluster | Category | Focus Area | Example Symptoms |\n|---|---|---|---|\n| **Cluster $\\alpha$** | **Missing Features & Incomplete Flows** | Missing API capabilities, unhandled user intents, incomplete lifecycle events, missing UI states (empty\u002Floading\u002Ferror). | No pagination on list endpoint, missing session resume feature. |\n| **Cluster $\\beta$** | **Architectural & Security Gaps** | Type safety holes, unhandled edge cases, race conditions, missing input bounds, broken authorization checks. | Missing payload schema validation, uncaught promise rejection in background job. |\n| **Cluster $\\gamma$** | **Performance & Resource Bottlenecks** | Blocking sync execution, redundant DB\u002Fnetwork calls, memory leaks, unindexed queries, expensive re-renders. | Sequential `await` in `Array.map`, unthrottled search handler. |\n| **Cluster $\\delta$** | **Complexity & Maintainability Liabilities** | Over-engineered layers, duplicate utility functions, dead code, single-caller abstractions, tight coupling. | Custom HTTP wrapper replacing standard `fetch`, 1500-line bloated router file. |\n\n---\n\n### Phase 3: Pragmatic ROI Filter Matrix\n\nFilter every proposed improvement through the **Pragmatic ROI Grid** before presenting recommendations:\n\n```\n                  High Impact\n                      │\n     [QUICK WIN]      │    [CORE REFACTOR]\n     High Value,      │    High Value,\n     Low Complexity   │    Medium\u002FHigh Effort\n──────────────────────┼──────────────────────\n     [DISCARD]        │    [DEFER \u002F AVOID]\n     Low Value,       │    Low Value,\n     Low Complexity   │    High Complexity (Over-engineering)\n                      │\n                  Low Impact\n  Low Complexity ────────────── High Complexity\n```\n\n- **Include**: Quick Wins & Core Refactors.\n- **Reject \u002F Exclude**: Low-impact over-engineering, speculative abstractions, or installing heavy third-party libraries when built-in runtime APIs suffice.\n\n---\n\n### Phase 4: Output & Actionable Resolution Vectors\n\nPresent the analysis using a **Zero-Fluff Findings Matrix** followed by **Pragmatic Improvement Blueprints**.\n\n#### 1. Discovered Gaps & Bottlenecks Matrix\n\n```markdown\n| Index | Category | Target File \u002F Location | Issue Description | Impact \u002F Priority |\n|---|---|---|---|---|\n| G001 | Cluster α (Missing Feature) | `backend\u002Fsrc\u002Fuser.ts:L42` | Missing pagination & field filtering on list API | High (Quick Win) |\n| G002 | Cluster β (Arch Gap) | `backend\u002Fsrc\u002Fbridge.ts:L88` | Unhandled WebSocket ECONNRESET crashes process | Critical (Core Refactor) |\n| G003 | Cluster γ (Bottleneck) | `frontend\u002Fsrc\u002FFeed.tsx:L12` | Un-memoized item list triggers full UI re-renders | Med (Quick Win) |\n| G004 | Cluster δ (Liability) | `backend\u002Fsrc\u002Futils.ts:L100` | Custom 200-line string parser replacing `URLSearchParams` | Med (Cleanup) |\n```\n\n#### 2. Pragmatic Improvement Blueprints\n\nFor each high-priority cluster\u002Findex, provide lean, actionable improvement blueprints:\n\n```markdown\n### Blueprint 1: [G001] Add Lean Pagination & Filtering\n- **Target**: `[user.ts](file:\u002F\u002F\u002Fd:\u002Fpath\u002Fto\u002Fuser.ts#L42-L60)`\n- **Problem**: Large payloads cause high latency and memory spikes.\n- **Pragmatic Solution**: Leverage native SQL `LIMIT\u002FOFFSET` or query param parsing with zero extra packages.\n- **Delta Vector**:\n  ```diff\n  - const users = await db.query('SELECT * FROM users');\n  + const limit = Math.min(Number(req.query.limit) || 20, 100);\n  + const offset = Number(req.query.offset) || 0;\n  + const users = await db.query('SELECT * FROM users LIMIT ? OFFSET ?', [limit, offset]);\n  ```\n- **Verification**: Test API with `?limit=10&offset=0`.\n```\n\n---\n\n## Quick Diagnostic Checklist\n\nWhen running this skill, answer these 5 diagnostic questions:\n1. **Feature Check**: What logical user flow or system interaction ends abruptly without resolution?\n2. **Robustness Check**: Where does the application crash when given unexpected or missing inputs?\n3. **Bottleneck Check**: Where is execution synchronously blocked waiting on sequential I\u002FO or heavy loops?\n4. **Complexity Check**: What custom hand-rolled code can be replaced by built-in runtime\u002Fplatform APIs?\n5. **Liability Check**: Which files exceed length\u002Fcomplexity bounds (>500 lines or high nesting) and need modular splitting?\n",{"name":5,"description":7},"main","62c7af5ced2c21355d148c243edb6d5921cca1a6",".agents\u002Fskills\u002Ffeature-gap-bottleneck-analysis",8,"https:\u002F\u002Fgithub.com\u002FRudyCity\u002Fsuperagent","https:\u002F\u002Fgithub.com\u002FRudyCity","2026-11-14 22:58:49",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add RudyCity\u002Fsuperagent --skill feature-gap-bottleneck-analysis",{"tool":36,"command":37},"bunx","bunx skills add RudyCity\u002Fsuperagent --skill feature-gap-bottleneck-analysis",{"tool":39,"command":40},"pnpm","pnpm dlx skills add RudyCity\u002Fsuperagent --skill feature-gap-bottleneck-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FRudyCity\u002Fsuperagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ffeature-gap-bottleneck-analysis\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M75GP28CM6QCSXSHKFF3NNKS","telegram_bot","Use Telegram Bot when the user asks for Telegram Bot or this provider's API.","https:\u002F\u002Fgithub.com\u002FRudyCity\u002Fsuperagent\u002Fblob\u002Fmain\u002Fmuse-bridge-kit\u002Fskills\u002Ftelegram-bot\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M75GNZGZYM7NWDV6MBP3HS14","superagent-bridge","Operate the Muse\u003C->superagent Telegram bridge: poll the private group for task_request\u002Ftask_result envelopes, validate senders, and reply with task_batch\u002Ftask_done as Muse (the remote brain).","https:\u002F\u002Fgithub.com\u002FRudyCity\u002Fsuperagent\u002Fblob\u002Fmain\u002Fmuse-bridge-kit\u002Fskills\u002Fsuperagent-bridge\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M75GNHN19HJWZ7NAPM5E5JCV","Writing Skills","TDD for process documentation - test with subagents before writing, iterate until bulletproof","https:\u002F\u002Fgithub.com\u002FRudyCity\u002Fsuperagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M75GNCQEKVRA4FH161NZPZNB","writing-shape","Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.","https:\u002F\u002Fgithub.com\u002FRudyCity\u002Fsuperagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-shape\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M75GNAF9NAYCSTBDZDGMK0DZ","Writing Plans","Create detailed implementation plans with bite-sized tasks for engineers with zero codebase context","https:\u002F\u002Fgithub.com\u002FRudyCity\u002Fsuperagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M75GN72EV0V5NQAW9CSPFRFH","writing-guidelines","Review docs\u002Fprose for Writing Guidelines compliance. Use when asked to \"review my docs\", \"check writing style\", \"audit prose\", \"review docs voice and tone\", or \"check this page against the writing handbook\".","https:\u002F\u002Fgithub.com\u002FRudyCity\u002Fsuperagent\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-guidelines\u002FSKILL.md",[],[]]