[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79N8JYPCTAN9GF4BKX3EHC4":3,"skill-same:01M79N8JYPCTAN9GF4BKX3EHC4":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M79N8JYPCTAN9GF4BKX3EHC4","codebase-onboarding",null,"Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md. Use when joining a new project or setting up Claude Code for the first time in a repo.","JunMystery\u002FAgent-Guidance","JunMystery","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F161468934?v=4","01M79MTMV8F0BY8NK1A92RA8A0","Jun","01M79MTMWCFBKPHN5B25E6V20B",0,"MIT","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fcodebase-onboarding\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: codebase-onboarding\ndescription: Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md. Use when joining a new project or setting up Claude Code for the first time in a repo.\nmetadata:\n  origin: ECC\n---\n\n# Codebase Onboarding\n\nSystematically analyze an unfamiliar codebase and produce a structured onboarding guide. Designed for developers joining a new project or setting up Claude Code in an existing repo for the first time.\n\n## When to Use\n\n- First time opening a project with Claude Code\n- Joining a new team or repository\n- User asks \"help me understand this codebase\"\n- User asks to generate a CLAUDE.md for a project\n- User says \"onboard me\" or \"walk me through this repo\"\n\n## How It Works\n\n### Phase 1: Reconnaissance\n\nGather raw signals about the project without reading every file. Run these checks in parallel:\n\n```\n1. Package manifest detection\n   → package.json, go.mod, Cargo.toml, pyproject.toml, pom.xml, build.gradle,\n     Gemfile, composer.json, mix.exs, pubspec.yaml\n\n2. Framework fingerprinting\n   → next.config.*, nuxt.config.*, angular.json, vite.config.*,\n     django settings, flask app factory, fastapi main, rails config\n\n3. Entry point identification\n   → main.*, index.*, app.*, server.*, cmd\u002F, src\u002Fmain\u002F\n\n4. Directory structure snapshot\n   → Top 2 levels of the directory tree, ignoring node_modules, vendor,\n     .git, dist, build, __pycache__, .next\n\n5. Config and tooling detection\n   → .eslintrc*, .prettierrc*, tsconfig.json, Makefile, Dockerfile,\n     docker-compose*, .github\u002Fworkflows\u002F, .env.example, CI configs\n\n6. Test structure detection\n   → tests\u002F, test\u002F, __tests__\u002F, *_test.go, *.spec.ts, *.test.js,\n     pytest.ini, jest.config.*, vitest.config.*\n```\n\n### Phase 2: Architecture Mapping\n\nFrom the reconnaissance data, identify:\n\n**Tech Stack**\n- Language(s) and version constraints\n- Framework(s) and major libraries\n- Database(s) and ORMs\n- Build tools and bundlers\n- CI\u002FCD platform\n\n**Architecture Pattern**\n- Monolith, monorepo, microservices, or serverless\n- Frontend\u002Fbackend split or full-stack\n- API style: REST, GraphQL, gRPC, tRPC\n\n**Key Directories**\nMap the top-level directories to their purpose:\n\n\u003C!-- Example for a React project — replace with detected directories -->\n```\nsrc\u002Fcomponents\u002F  → React UI components\nsrc\u002Fapi\u002F         → API route handlers\nsrc\u002Flib\u002F         → Shared utilities\nsrc\u002Fdb\u002F          → Database models and migrations\ntests\u002F           → Test suites\nscripts\u002F         → Build and deployment scripts\n```\n\n**Data Flow**\nTrace one request from entry to response:\n- Where does a request enter? (router, handler, controller)\n- How is it validated? (middleware, schemas, guards)\n- Where is business logic? (services, models, use cases)\n- How does it reach the database? (ORM, raw queries, repositories)\n\n### Phase 3: Convention Detection\n\nIdentify patterns the codebase already follows:\n\n**Naming Conventions**\n- File naming: kebab-case, camelCase, PascalCase, snake_case\n- Component\u002Fclass naming patterns\n- Test file naming: `*.test.ts`, `*.spec.ts`, `*_test.go`\n\n**Code Patterns**\n- Error handling style: try\u002Fcatch, Result types, error codes\n- Dependency injection or direct imports\n- State management approach\n- Async patterns: callbacks, promises, async\u002Fawait, channels\n\n**Git Conventions**\n- Branch naming from recent branches\n- Commit message style from recent commits\n- PR workflow (squash, merge, rebase)\n- If the repo has no commits yet or only a shallow history (e.g. `git clone --depth 1`), skip this section and note \"Git history unavailable or too shallow to detect conventions\"\n\n### Phase 4: Generate Onboarding Artifacts\n\nProduce two outputs:\n\n#### Output 1: Onboarding Guide\n\n```markdown\n# Onboarding Guide: [Project Name]\n\n## Overview\n[2-3 sentences: what this project does and who it serves]\n\n## Tech Stack\n\u003C!-- Example for a Next.js project — replace with detected stack -->\n| Layer | Technology | Version |\n|-------|-----------|---------|\n| Language | TypeScript | 5.x |\n| Framework | Next.js | 14.x |\n| Database | PostgreSQL | 16 |\n| ORM | Prisma | 5.x |\n| Testing | Jest + Playwright | - |\n\n## Architecture\n[Diagram or description of how components connect]\n\n## Key Entry Points\n\u003C!-- Example for a Next.js project — replace with detected paths -->\n- **API routes**: `src\u002Fapp\u002Fapi\u002F` — Next.js route handlers\n- **UI pages**: `src\u002Fapp\u002F(dashboard)\u002F` — authenticated pages\n- **Database**: `prisma\u002Fschema.prisma` — data model source of truth\n- **Config**: `next.config.ts` — build and runtime config\n\n## Directory Map\n[Top-level directory → purpose mapping]\n\n## Request Lifecycle\n[Trace one API request from entry to response]\n\n## Conventions\n- [File naming pattern]\n- [Error handling approach]\n- [Testing patterns]\n- [Git workflow]\n\n## Common Tasks\n\u003C!-- Example for a Node.js project — replace with detected commands -->\n- **Run dev server**: `npm run dev`\n- **Run tests**: `npm test`\n- **Run linter**: `npm run lint`\n- **Database migrations**: `npx prisma migrate dev`\n- **Build for production**: `npm run build`\n\n## Where to Look\n\u003C!-- Example for a Next.js project — replace with detected paths -->\n| I want to... | Look at... |\n|--------------|-----------|\n| Add an API endpoint | `src\u002Fapp\u002Fapi\u002F` |\n| Add a UI page | `src\u002Fapp\u002F(dashboard)\u002F` |\n| Add a database table | `prisma\u002Fschema.prisma` |\n| Add a test | `tests\u002F` matching the source path |\n| Change build config | `next.config.ts` |\n```\n\n#### Output 2: Starter CLAUDE.md\n\nGenerate or update a project-specific CLAUDE.md based on detected conventions. If `CLAUDE.md` already exists, read it first and enhance it — preserve existing project-specific instructions and clearly call out what was added or changed.\n\n```markdown\n# Project Instructions\n\n## Tech Stack\n[Detected stack summary]\n\n## Code Style\n- [Detected naming conventions]\n- [Detected patterns to follow]\n\n## Testing\n- Run tests: `[detected test command]`\n- Test pattern: [detected test file convention]\n- Coverage: [if configured, the coverage command]\n\n## Build & Run\n- Dev: `[detected dev command]`\n- Build: `[detected build command]`\n- Lint: `[detected lint command]`\n\n## Project Structure\n[Key directory → purpose map]\n\n## Conventions\n- [Commit style if detectable]\n- [PR workflow if detectable]\n- [Error handling patterns]\n```\n\n## Best Practices\n\n1. **Don't read everything** — reconnaissance should use Glob and Grep, not Read on every file. Read selectively only for ambiguous signals.\n2. **Verify, don't guess** — if a framework is detected from config but the actual code uses something different, trust the code.\n3. **Respect existing CLAUDE.md** — if one already exists, enhance it rather than replacing it. Call out what's new vs existing.\n4. **Stay concise** — the onboarding guide should be scannable in 2 minutes. Details belong in the code, not the guide.\n5. **Flag unknowns** — if a convention can't be confidently detected, say so rather than guessing. \"Could not determine test runner\" is better than a wrong answer.\n\n## Anti-Patterns to Avoid\n\n- Generating a CLAUDE.md that's longer than 100 lines — keep it focused\n- Listing every dependency — highlight only the ones that shape how you write code\n- Describing obvious directory names — `src\u002F` doesn't need an explanation\n- Copying the README — the onboarding guide adds structural insight the README lacks\n\n## Examples\n\n### Example 1: First time in a new repo\n**User**: \"Onboard me to this codebase\"\n**Action**: Run full 4-phase workflow → produce Onboarding Guide + Starter CLAUDE.md\n**Output**: Onboarding Guide printed directly to the conversation, plus a `CLAUDE.md` written to the project root\n\n### Example 2: Generate CLAUDE.md for existing project\n**User**: \"Generate a CLAUDE.md for this project\"\n**Action**: Run Phases 1-3, skip Onboarding Guide, produce only CLAUDE.md\n**Output**: Project-specific `CLAUDE.md` with detected conventions\n\n### Example 3: Enhance existing CLAUDE.md\n**User**: \"Update the CLAUDE.md with current project conventions\"\n**Action**: Read existing CLAUDE.md, run Phases 1-3, merge new findings\n**Output**: Updated `CLAUDE.md` with additions clearly marked\n","# Codebase Onboarding\n\nSystematically analyze an unfamiliar codebase and produce a structured onboarding guide. Designed for developers joining a new project or setting up Claude Code in an existing repo for the first time.\n\n## When to Use\n\n- First time opening a project with Claude Code\n- Joining a new team or repository\n- User asks \"help me understand this codebase\"\n- User asks to generate a CLAUDE.md for a project\n- User says \"onboard me\" or \"walk me through this repo\"\n\n## How It Works\n\n### Phase 1: Reconnaissance\n\nGather raw signals about the project without reading every file. Run these checks in parallel:\n\n```\n1. Package manifest detection\n   → package.json, go.mod, Cargo.toml, pyproject.toml, pom.xml, build.gradle,\n     Gemfile, composer.json, mix.exs, pubspec.yaml\n\n2. Framework fingerprinting\n   → next.config.*, nuxt.config.*, angular.json, vite.config.*,\n     django settings, flask app factory, fastapi main, rails config\n\n3. Entry point identification\n   → main.*, index.*, app.*, server.*, cmd\u002F, src\u002Fmain\u002F\n\n4. Directory structure snapshot\n   → Top 2 levels of the directory tree, ignoring node_modules, vendor,\n     .git, dist, build, __pycache__, .next\n\n5. Config and tooling detection\n   → .eslintrc*, .prettierrc*, tsconfig.json, Makefile, Dockerfile,\n     docker-compose*, .github\u002Fworkflows\u002F, .env.example, CI configs\n\n6. Test structure detection\n   → tests\u002F, test\u002F, __tests__\u002F, *_test.go, *.spec.ts, *.test.js,\n     pytest.ini, jest.config.*, vitest.config.*\n```\n\n### Phase 2: Architecture Mapping\n\nFrom the reconnaissance data, identify:\n\n**Tech Stack**\n- Language(s) and version constraints\n- Framework(s) and major libraries\n- Database(s) and ORMs\n- Build tools and bundlers\n- CI\u002FCD platform\n\n**Architecture Pattern**\n- Monolith, monorepo, microservices, or serverless\n- Frontend\u002Fbackend split or full-stack\n- API style: REST, GraphQL, gRPC, tRPC\n\n**Key Directories**\nMap the top-level directories to their purpose:\n\n\u003C!-- Example for a React project — replace with detected directories -->\n```\nsrc\u002Fcomponents\u002F  → React UI components\nsrc\u002Fapi\u002F         → API route handlers\nsrc\u002Flib\u002F         → Shared utilities\nsrc\u002Fdb\u002F          → Database models and migrations\ntests\u002F           → Test suites\nscripts\u002F         → Build and deployment scripts\n```\n\n**Data Flow**\nTrace one request from entry to response:\n- Where does a request enter? (router, handler, controller)\n- How is it validated? (middleware, schemas, guards)\n- Where is business logic? (services, models, use cases)\n- How does it reach the database? (ORM, raw queries, repositories)\n\n### Phase 3: Convention Detection\n\nIdentify patterns the codebase already follows:\n\n**Naming Conventions**\n- File naming: kebab-case, camelCase, PascalCase, snake_case\n- Component\u002Fclass naming patterns\n- Test file naming: `*.test.ts`, `*.spec.ts`, `*_test.go`\n\n**Code Patterns**\n- Error handling style: try\u002Fcatch, Result types, error codes\n- Dependency injection or direct imports\n- State management approach\n- Async patterns: callbacks, promises, async\u002Fawait, channels\n\n**Git Conventions**\n- Branch naming from recent branches\n- Commit message style from recent commits\n- PR workflow (squash, merge, rebase)\n- If the repo has no commits yet or only a shallow history (e.g. `git clone --depth 1`), skip this section and note \"Git history unavailable or too shallow to detect conventions\"\n\n### Phase 4: Generate Onboarding Artifacts\n\nProduce two outputs:\n\n#### Output 1: Onboarding Guide\n\n```markdown\n# Onboarding Guide: [Project Name]\n\n## Overview\n[2-3 sentences: what this project does and who it serves]\n\n## Tech Stack\n\u003C!-- Example for a Next.js project — replace with detected stack -->\n| Layer | Technology | Version |\n|-------|-----------|---------|\n| Language | TypeScript | 5.x |\n| Framework | Next.js | 14.x |\n| Database | PostgreSQL | 16 |\n| ORM | Prisma | 5.x |\n| Testing | Jest + Playwright | - |\n\n## Architecture\n[Diagram or description of how components connect]\n\n## Key Entry Points\n\u003C!-- Example for a Next.js project — replace with detected paths -->\n- **API routes**: `src\u002Fapp\u002Fapi\u002F` — Next.js route handlers\n- **UI pages**: `src\u002Fapp\u002F(dashboard)\u002F` — authenticated pages\n- **Database**: `prisma\u002Fschema.prisma` — data model source of truth\n- **Config**: `next.config.ts` — build and runtime config\n\n## Directory Map\n[Top-level directory → purpose mapping]\n\n## Request Lifecycle\n[Trace one API request from entry to response]\n\n## Conventions\n- [File naming pattern]\n- [Error handling approach]\n- [Testing patterns]\n- [Git workflow]\n\n## Common Tasks\n\u003C!-- Example for a Node.js project — replace with detected commands -->\n- **Run dev server**: `npm run dev`\n- **Run tests**: `npm test`\n- **Run linter**: `npm run lint`\n- **Database migrations**: `npx prisma migrate dev`\n- **Build for production**: `npm run build`\n\n## Where to Look\n\u003C!-- Example for a Next.js project — replace with detected paths -->\n| I want to... | Look at... |\n|--------------|-----------|\n| Add an API endpoint | `src\u002Fapp\u002Fapi\u002F` |\n| Add a UI page | `src\u002Fapp\u002F(dashboard)\u002F` |\n| Add a database table | `prisma\u002Fschema.prisma` |\n| Add a test | `tests\u002F` matching the source path |\n| Change build config | `next.config.ts` |\n```\n\n#### Output 2: Starter CLAUDE.md\n\nGenerate or update a project-specific CLAUDE.md based on detected conventions. If `CLAUDE.md` already exists, read it first and enhance it — preserve existing project-specific instructions and clearly call out what was added or changed.\n\n```markdown\n# Project Instructions\n\n## Tech Stack\n[Detected stack summary]\n\n## Code Style\n- [Detected naming conventions]\n- [Detected patterns to follow]\n\n## Testing\n- Run tests: `[detected test command]`\n- Test pattern: [detected test file convention]\n- Coverage: [if configured, the coverage command]\n\n## Build & Run\n- Dev: `[detected dev command]`\n- Build: `[detected build command]`\n- Lint: `[detected lint command]`\n\n## Project Structure\n[Key directory → purpose map]\n\n## Conventions\n- [Commit style if detectable]\n- [PR workflow if detectable]\n- [Error handling patterns]\n```\n\n## Best Practices\n\n1. **Don't read everything** — reconnaissance should use Glob and Grep, not Read on every file. Read selectively only for ambiguous signals.\n2. **Verify, don't guess** — if a framework is detected from config but the actual code uses something different, trust the code.\n3. **Respect existing CLAUDE.md** — if one already exists, enhance it rather than replacing it. Call out what's new vs existing.\n4. **Stay concise** — the onboarding guide should be scannable in 2 minutes. Details belong in the code, not the guide.\n5. **Flag unknowns** — if a convention can't be confidently detected, say so rather than guessing. \"Could not determine test runner\" is better than a wrong answer.\n\n## Anti-Patterns to Avoid\n\n- Generating a CLAUDE.md that's longer than 100 lines — keep it focused\n- Listing every dependency — highlight only the ones that shape how you write code\n- Describing obvious directory names — `src\u002F` doesn't need an explanation\n- Copying the README — the onboarding guide adds structural insight the README lacks\n\n## Examples\n\n### Example 1: First time in a new repo\n**User**: \"Onboard me to this codebase\"\n**Action**: Run full 4-phase workflow → produce Onboarding Guide + Starter CLAUDE.md\n**Output**: Onboarding Guide printed directly to the conversation, plus a `CLAUDE.md` written to the project root\n\n### Example 2: Generate CLAUDE.md for existing project\n**User**: \"Generate a CLAUDE.md for this project\"\n**Action**: Run Phases 1-3, skip Onboarding Guide, produce only CLAUDE.md\n**Output**: Project-specific `CLAUDE.md` with detected conventions\n\n### Example 3: Enhance existing CLAUDE.md\n**User**: \"Update the CLAUDE.md with current project conventions\"\n**Action**: Read existing CLAUDE.md, run Phases 1-3, merge new findings\n**Output**: Updated `CLAUDE.md` with additions clearly marked\n",{"name":5,"metadata":24,"description":7},{"origin":25},"ECC","main","5d0a87185c0e172c3901e2a6e5916b6d544b8b94","skills\u002Fcodebase-onboarding","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance","https:\u002F\u002Fgithub.com\u002FJunMystery","AI is the typist, I am the architect. Building efficient, secure, and user-centric products through disciplined AI prompt engineering.","2026-11-13 17:41:25",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add JunMystery\u002FAgent-Guidance --skill codebase-onboarding",{"tool":39,"command":40},"bunx","bunx skills add JunMystery\u002FAgent-Guidance --skill codebase-onboarding",{"tool":42,"command":43},"pnpm","pnpm dlx skills add JunMystery\u002FAgent-Guidance --skill codebase-onboarding","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fcodebase-onboarding\u002FSKILL.md",true,[],[48,54,60,66,72,78],{"skillNo":49,"name":50,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M79QR1E309VJ6CTQKB32AWWA","zero-trust-architecture-cheat-sheet","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fzero-trust-architecture-cheat-sheet\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M79QQV7GHYR02DYGN41S23WN","xss-filter-evasion-cheat-sheet","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fxss-filter-evasion-cheat-sheet\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M79QQNSN7YB8XB61FFSCS3WH","xs-leaks-cheat-sheet","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fxs-leaks-cheat-sheet\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M79QQHZZJKFDY9132G5A65C2","xpath-injection-prevention-cheat-sheet","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fxpath-injection-prevention-cheat-sheet\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M79QQB9ZSD3DJG8658EHQXR1","xml-security-cheat-sheet","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fxml-security-cheat-sheet\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M79QQ60WKV7PFMXWT9CW8PM6","xml-external-entity-prevention-cheat-sheet","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fxml-external-entity-prevention-cheat-sheet\u002FSKILL.md",[],[]]