[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M699G014BN3FHVDN64F0AZDH":3,"skill-same:01M699G014BN3FHVDN64F0AZDH":130},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M699G014BN3FHVDN64F0AZDH","github-repo-explore",null,"Guide for searching and exploring external GitHub repositories using the gh CLI. Use this when you need reference implementations, patterns, or code examples from open-source projects to help complete your task.","microsoft\u002Fsemantic-link-labs","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M699FKMT63C17BFNH8WHZN2K",600,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsemantic-link-labs\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgithub-repo-explore\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"github","github repo explore","explore","github repo","repo","repositories","cli","when","source","for","you","complete","patterns","use","guide","gh cli","gh","projects","open","code","2026-11-10 10:12:30",false,"---\nname: github-repo-explore\ndescription: Guide for searching and exploring external GitHub repositories using the gh CLI. Use this when you need reference implementations, patterns, or code examples from open-source projects to help complete your task.\n---\n\n# GitHub Repository Search and Exploration\n\nThis skill enables agents to discover, clone, and explore external GitHub repositories when implementing features that may benefit from reference implementations in open-source projects.\n\n## When to Use This Skill\n\nUse this skill when you need to:\n- Find reference implementations for features you're building\n- Explore how other projects implement similar patterns\n- Search for code examples across GitHub\n- Clone external repos for local exploration and learning\n- Find libraries or tools that could inform your implementation\n\n**Do NOT use this skill when**:\n- The task is straightforward and doesn't need external references\n- The codebase already has established patterns to follow\n- You're working on proprietary code that shouldn't reference external sources\n\n---\n\n## Resource Directory\n\nAll external GitHub repositories **MUST** be stored in:\n\n```\n.agent_cache\u002Fresources\u002F\n```\n\nThis is the **centralized** location for all cloned external repositories. Always check here first before searching GitHub.\n\n### Directory Structure\n\n```\n.agent_cache\u002F\n└── resources\u002F\n    ├── microsoft\u002F\n    │   ├── semantic-kernel\u002F\n    │   └── TypeChat\u002F\n    ├── langchain-ai\u002F\n    │   └── langchain\u002F\n    └── Significant-Gravitas\u002F\n        └── AutoGPT\u002F\n```\n\nRepositories are organized by `{owner}\u002F{repo}` structure to prevent naming conflicts.\n\n---\n\n## Workflow Overview\n\n```\n┌─────────────────────────────────────────────────────────────────┐\n│  1. Check Local Cache (.agent_cache\u002Fresources\u002F)                 │\n│     └─ If found → Use local repo for exploration                │\n└────────────────────────────┬────────────────────────────────────┘\n                             │ Not found\n                             ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  2. Authenticate with GitHub (if needed)                        │\n│     └─ gh auth login                                            │\n└────────────────────────────┬────────────────────────────────────┘\n                             │\n                             ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  3. Search GitHub for Repositories                              │\n│     └─ gh search repos \u003Cquery>                                  │\n│     └─ gh search code \u003Cquery>                                   │\n└────────────────────────────┬────────────────────────────────────┘\n                             │ Found match\n                             ▼\n┌───────────────────────────────────────────────────────────────────┐\n│  4. Clone to Cache Directory                                      │\n│     └─ gh repo clone owner\u002Frepo .agent_cache\u002Fresources\u002Fowner\u002Frepo │\n└────────────────────────────┬──────────────────────────────────────┘\n                             │\n                             ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  5. Explore Repository                                          │\n│     └─ Use gh commands and file reading tools                   │\n└─────────────────────────────────────────────────────────────────┘\n```\n\n---\n\n## Phase 1: Check Local Cache First\n\nBefore searching GitHub, always check if a relevant repository is already cloned locally.\n\n### List Cached Repositories\n\n```bash\n# List all cached repositories\nls -la .agent_cache\u002Fresources\u002F\n\n# List repos by owner\nls -la .agent_cache\u002Fresources\u002Fmicrosoft\u002F\n\n# Search for specific repo by name\nfind .agent_cache\u002Fresources -type d -name \"*semantic*\" 2>\u002Fdev\u002Fnull\n```\n\n### Explore Local Repository\n\nIf the repository exists locally, use standard file tools:\n\n```bash\n# View repository structure\ntree -L 2 .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel\u002F\n\n# Search for patterns in local repo\ngrep -r \"planning\" .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel\u002Fpython\u002F --include=\"*.py\" | head -20\n\n# Find specific files\nfind .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel -name \"*.md\" -path \"*skills*\"\n```\n\n---\n\n## Phase 2: GitHub Authentication\n\nIf you need to search or clone from GitHub, ensure authentication is set up.\n\n### Check Authentication Status\n\n```bash\ngh auth status\n```\n\n### Interactive Login (if needed)\n\n```bash\n# Interactive login - user will authenticate via browser\ngh auth login\n```\n\nThis opens a browser for the user to authenticate with their GitHub account.\n\n### Verify Login\n\n```bash\n# Verify authentication worked\ngh auth status\n```\n\n---\n\n## Phase 3: Search GitHub\n\nUse `gh search` commands to find relevant repositories or code.\n\n### Search for Repositories\n\n```bash\n# Search repos by keywords\ngh search repos \"agent planning skills\" --limit 10\n\n# Search with language filter\ngh search repos \"agent planning\" --language python --limit 10\n\n# Search by owner\ngh search repos --owner microsoft \"semantic kernel\" --limit 10\n\n# Search with JSON output for parsing\ngh search repos \"agent planning\" --json fullName,description,stargazersCount --limit 5\n\n# Sort by stars (most popular)\ngh search repos \"agent planning\" --sort stars --limit 10\n\n# Filter by number of stars\ngh search repos \"agent framework\" --stars \">1000\" --limit 10\n```\n\n### Search for Code\n\n```bash\n# Search code across GitHub\ngh search code \"TaskLedger\" --limit 10\n\n# Search code in specific language\ngh search code \"def plan\" --language python --limit 10\n\n# Search code in specific repo\ngh search code \"planning\" --repo microsoft\u002Fsemantic-kernel --limit 20\n\n# Search code by filename\ngh search code \"skills\" --filename \"*.md\" --limit 10\n\n# Search with JSON output\ngh search code \"agent skills\" --json path,repository --limit 10\n```\n\n### View Repository Details\n\n```bash\n# View repo README and description\ngh repo view microsoft\u002Fsemantic-kernel\n\n# View repo with specific fields as JSON\ngh repo view microsoft\u002Fsemantic-kernel --json name,description,stargazerCount,defaultBranchRef\n\n# Open repo in browser\ngh repo view microsoft\u002Fsemantic-kernel --web\n```\n\n---\n\n## Phase 4: Clone Repository to Cache\n\nWhen you find a useful repository, clone it to the cache directory.\n\n### Clone Commands\n\n```bash\n# Create cache directory structure\nmkdir -p .agent_cache\u002Fresources\u002F{owner}\n\n# Clone repository\ngh repo clone microsoft\u002Fsemantic-kernel .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel\n\n# Clone with shallow history (faster, uses less disk)\ngh repo clone microsoft\u002Fsemantic-kernel .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel -- --depth 1\n\n# Clone specific branch\ngh repo clone microsoft\u002Fsemantic-kernel .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel -- --branch main --depth 1\n```\n\n### Update Existing Clone\n\n```bash\n# Pull latest changes\ncd .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel && git pull && cd -\n```\n\n---\n\n## Phase 5: Explore Repository\n\nOnce cloned, use a combination of gh commands and file reading tools.\n\n### Repository Structure Exploration\n\n```bash\n# View directory structure\ntree -L 3 .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel\u002Fpython\u002F | head -50\n\n# Find README files\nfind .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel -name \"README.md\" | head -10\n\n# Find Python files related to agents\nfind .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel -path \"*agents*\" -name \"*.py\" | head -20\n```\n\n### Code Search in Local Clone\n\n```bash\n# Search for specific patterns\ngrep -r \"class.*Agent\" .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel\u002Fpython --include=\"*.py\" | head -20\n\n# Find function definitions\ngrep -rn \"def plan\" .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel\u002Fpython --include=\"*.py\"\n\n# Search for imports\ngrep -r \"from.*import\" .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel\u002Fpython --include=\"*.py\" | grep planning\n```\n\n### Read Specific Files\n\nAfter identifying relevant files with grep\u002Ffind, use the `read_file` tool to examine content:\n\n```bash\n# Example files to read\nread_file .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel\u002Fpython\u002Fsemantic_kernel\u002Fagents\u002Forchestration\u002Fmagentic.py\n```\n\n---\n\n## Useful gh Commands Reference\n\n### Repository Commands\n\n| Command | Description |\n|---------|-------------|\n| `gh repo view \u003Cowner\u002Frepo>` | View repo README and details |\n| `gh repo view \u003Cowner\u002Frepo> --json \u003Cfields>` | Get repo metadata as JSON |\n| `gh repo clone \u003Cowner\u002Frepo> \u003Cpath>` | Clone repo to specific path |\n| `gh repo list \u003Cowner>` | List repos owned by user\u002Forg |\n\n### Search Commands\n\n| Command | Description |\n|---------|-------------|\n| `gh search repos \u003Cquery>` | Search for repositories |\n| `gh search code \u003Cquery>` | Search within code |\n| `gh search issues \u003Cquery>` | Search issues |\n| `gh search prs \u003Cquery>` | Search pull requests |\n\n### Search Filters\n\n| Filter | Example | Description |\n|--------|---------|-------------|\n| `--language` | `--language python` | Filter by programming language |\n| `--owner` | `--owner microsoft` | Filter by repository owner |\n| `--stars` | `--stars \">1000\"` | Filter by star count |\n| `--limit` | `--limit 20` | Limit number of results |\n| `--sort` | `--sort stars` | Sort results (stars, forks, updated) |\n| `--json` | `--json fullName,description` | Output as JSON |\n\n### JSON Fields for Repos\n\nCommon fields for `--json` output:\n- `fullName` - owner\u002Frepo\n- `name` - repo name only\n- `description` - repo description\n- `stargazersCount` - number of stars\n- `language` - primary language\n- `url` - GitHub URL\n- `defaultBranchRef` - main branch name\n\n---\n\n## Example Workflows\n\n### Example 1: Find Reference Implementations for REST API Patterns\n\n```bash\n# 1. Check local cache\nls .agent_cache\u002Fresources\u002F 2>\u002Fdev\u002Fnull || echo \"Cache empty\"\n\n# 2. Search GitHub for Fabric\u002FPower BI SDK examples\ngh search repos \"fabric rest api python\" --stars \">50\" --limit 10\n\n# 3. View promising repo\ngh repo view microsoft\u002Fsemantic-link-labs\n\n# 4. Clone to cache\nmkdir -p .agent_cache\u002Fresources\u002Fmicrosoft\ngh repo clone microsoft\u002Fsemantic-link-labs .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-link-labs -- --depth 1\n\n# 5. Explore API patterns\ngrep -r \"_base_api\" .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-link-labs --include=\"*.py\" | head -20\n```\n\n### Example 2: Search for Code Patterns\n\n```bash\n# Search for specific pattern across GitHub\ngh search code \"FabricRestClient\" --language python --limit 5\n\n# Clone repo containing the pattern\ngh repo clone owner\u002Frepo .agent_cache\u002Fresources\u002Fowner\u002Frepo -- --depth 1\n\n# Find and read the file\ngrep -rn \"FabricRestClient\" .agent_cache\u002Fresources\u002Fowner\u002Frepo --include=\"*.py\"\n```\n\n### Example 3: Explore Multiple Repos\n\n```bash\n# Search for agent frameworks\ngh search repos \"agent framework\" --language python --stars \">2000\" --json fullName,description,stargazersCount\n\n# Clone top candidates\nfor repo in \"langchain-ai\u002Flangchain\" \"Significant-Gravitas\u002FAutoGPT\"; do\n    owner=$(dirname $repo)\n    mkdir -p \".agent_cache\u002Fresources\u002F$owner\"\n    gh repo clone \"$repo\" \".agent_cache\u002Fresources\u002F$repo\" -- --depth 1\ndone\n\n# Compare implementations\ndiff \u003C(grep -r \"def plan\" .agent_cache\u002Fresources\u002Flangchain-ai\u002Flangchain --include=\"*.py\" | head -5) \\\n     \u003C(grep -r \"def plan\" .agent_cache\u002Fresources\u002FSignificant-Gravitas\u002FAutoGPT --include=\"*.py\" | head -5)\n```\n\n---\n\n## Best Practices\n\n1. **Always check local cache first** -- Avoid redundant cloning\n2. **Use shallow clones** -- Add `-- --depth 1` to save disk space and time\n3. **Organize by owner\u002Frepo** -- Prevents naming conflicts\n4. **Use JSON output** -- Easier to parse programmatically\n5. **Start with grep\u002Ffind** -- Narrow down before reading full files\n6. **Respect rate limits** -- GitHub has API rate limits; cache results\n7. **Clean up periodically** -- Remove unused repos from cache\n\n---\n\n## Troubleshooting\n\n### Authentication Issues\n\n```bash\n# Check current auth status\ngh auth status\n\n# Re-authenticate\ngh auth login\n\n# Use different auth method\ngh auth login --with-token \u003C token.txt\n```\n\n### Rate Limiting\n\n```bash\n# Check rate limit status\ngh api rate_limit\n\n# If rate limited, wait or use cached repos\n```\n\n### Clone Failures\n\n```bash\n# If clone fails, try with HTTPS explicitly\ngit clone https:\u002F\u002Fgithub.com\u002Fowner\u002Frepo.git .agent_cache\u002Fresources\u002Fowner\u002Frepo\n\n# Or try shallow clone\ngit clone --depth 1 https:\u002F\u002Fgithub.com\u002Fowner\u002Frepo.git .agent_cache\u002Fresources\u002Fowner\u002Frepo\n```\n","# GitHub Repository Search and Exploration\n\nThis skill enables agents to discover, clone, and explore external GitHub repositories when implementing features that may benefit from reference implementations in open-source projects.\n\n## When to Use This Skill\n\nUse this skill when you need to:\n- Find reference implementations for features you're building\n- Explore how other projects implement similar patterns\n- Search for code examples across GitHub\n- Clone external repos for local exploration and learning\n- Find libraries or tools that could inform your implementation\n\n**Do NOT use this skill when**:\n- The task is straightforward and doesn't need external references\n- The codebase already has established patterns to follow\n- You're working on proprietary code that shouldn't reference external sources\n\n---\n\n## Resource Directory\n\nAll external GitHub repositories **MUST** be stored in:\n\n```\n.agent_cache\u002Fresources\u002F\n```\n\nThis is the **centralized** location for all cloned external repositories. Always check here first before searching GitHub.\n\n### Directory Structure\n\n```\n.agent_cache\u002F\n└── resources\u002F\n    ├── microsoft\u002F\n    │   ├── semantic-kernel\u002F\n    │   └── TypeChat\u002F\n    ├── langchain-ai\u002F\n    │   └── langchain\u002F\n    └── Significant-Gravitas\u002F\n        └── AutoGPT\u002F\n```\n\nRepositories are organized by `{owner}\u002F{repo}` structure to prevent naming conflicts.\n\n---\n\n## Workflow Overview\n\n```\n┌─────────────────────────────────────────────────────────────────┐\n│  1. Check Local Cache (.agent_cache\u002Fresources\u002F)                 │\n│     └─ If found → Use local repo for exploration                │\n└────────────────────────────┬────────────────────────────────────┘\n                             │ Not found\n                             ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  2. Authenticate with GitHub (if needed)                        │\n│     └─ gh auth login                                            │\n└────────────────────────────┬────────────────────────────────────┘\n                             │\n                             ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  3. Search GitHub for Repositories                              │\n│     └─ gh search repos \u003Cquery>                                  │\n│     └─ gh search code \u003Cquery>                                   │\n└────────────────────────────┬────────────────────────────────────┘\n                             │ Found match\n                             ▼\n┌───────────────────────────────────────────────────────────────────┐\n│  4. Clone to Cache Directory                                      │\n│     └─ gh repo clone owner\u002Frepo .agent_cache\u002Fresources\u002Fowner\u002Frepo │\n└────────────────────────────┬──────────────────────────────────────┘\n                             │\n                             ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  5. Explore Repository                                          │\n│     └─ Use gh commands and file reading tools                   │\n└─────────────────────────────────────────────────────────────────┘\n```\n\n---\n\n## Phase 1: Check Local Cache First\n\nBefore searching GitHub, always check if a relevant repository is already cloned locally.\n\n### List Cached Repositories\n\n```bash\n# List all cached repositories\nls -la .agent_cache\u002Fresources\u002F\n\n# List repos by owner\nls -la .agent_cache\u002Fresources\u002Fmicrosoft\u002F\n\n# Search for specific repo by name\nfind .agent_cache\u002Fresources -type d -name \"*semantic*\" 2>\u002Fdev\u002Fnull\n```\n\n### Explore Local Repository\n\nIf the repository exists locally, use standard file tools:\n\n```bash\n# View repository structure\ntree -L 2 .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel\u002F\n\n# Search for patterns in local repo\ngrep -r \"planning\" .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel\u002Fpython\u002F --include=\"*.py\" | head -20\n\n# Find specific files\nfind .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel -name \"*.md\" -path \"*skills*\"\n```\n\n---\n\n## Phase 2: GitHub Authentication\n\nIf you need to search or clone from GitHub, ensure authentication is set up.\n\n### Check Authentication Status\n\n```bash\ngh auth status\n```\n\n### Interactive Login (if needed)\n\n```bash\n# Interactive login - user will authenticate via browser\ngh auth login\n```\n\nThis opens a browser for the user to authenticate with their GitHub account.\n\n### Verify Login\n\n```bash\n# Verify authentication worked\ngh auth status\n```\n\n---\n\n## Phase 3: Search GitHub\n\nUse `gh search` commands to find relevant repositories or code.\n\n### Search for Repositories\n\n```bash\n# Search repos by keywords\ngh search repos \"agent planning skills\" --limit 10\n\n# Search with language filter\ngh search repos \"agent planning\" --language python --limit 10\n\n# Search by owner\ngh search repos --owner microsoft \"semantic kernel\" --limit 10\n\n# Search with JSON output for parsing\ngh search repos \"agent planning\" --json fullName,description,stargazersCount --limit 5\n\n# Sort by stars (most popular)\ngh search repos \"agent planning\" --sort stars --limit 10\n\n# Filter by number of stars\ngh search repos \"agent framework\" --stars \">1000\" --limit 10\n```\n\n### Search for Code\n\n```bash\n# Search code across GitHub\ngh search code \"TaskLedger\" --limit 10\n\n# Search code in specific language\ngh search code \"def plan\" --language python --limit 10\n\n# Search code in specific repo\ngh search code \"planning\" --repo microsoft\u002Fsemantic-kernel --limit 20\n\n# Search code by filename\ngh search code \"skills\" --filename \"*.md\" --limit 10\n\n# Search with JSON output\ngh search code \"agent skills\" --json path,repository --limit 10\n```\n\n### View Repository Details\n\n```bash\n# View repo README and description\ngh repo view microsoft\u002Fsemantic-kernel\n\n# View repo with specific fields as JSON\ngh repo view microsoft\u002Fsemantic-kernel --json name,description,stargazerCount,defaultBranchRef\n\n# Open repo in browser\ngh repo view microsoft\u002Fsemantic-kernel --web\n```\n\n---\n\n## Phase 4: Clone Repository to Cache\n\nWhen you find a useful repository, clone it to the cache directory.\n\n### Clone Commands\n\n```bash\n# Create cache directory structure\nmkdir -p .agent_cache\u002Fresources\u002F{owner}\n\n# Clone repository\ngh repo clone microsoft\u002Fsemantic-kernel .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel\n\n# Clone with shallow history (faster, uses less disk)\ngh repo clone microsoft\u002Fsemantic-kernel .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel -- --depth 1\n\n# Clone specific branch\ngh repo clone microsoft\u002Fsemantic-kernel .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel -- --branch main --depth 1\n```\n\n### Update Existing Clone\n\n```bash\n# Pull latest changes\ncd .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel && git pull && cd -\n```\n\n---\n\n## Phase 5: Explore Repository\n\nOnce cloned, use a combination of gh commands and file reading tools.\n\n### Repository Structure Exploration\n\n```bash\n# View directory structure\ntree -L 3 .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel\u002Fpython\u002F | head -50\n\n# Find README files\nfind .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel -name \"README.md\" | head -10\n\n# Find Python files related to agents\nfind .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel -path \"*agents*\" -name \"*.py\" | head -20\n```\n\n### Code Search in Local Clone\n\n```bash\n# Search for specific patterns\ngrep -r \"class.*Agent\" .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel\u002Fpython --include=\"*.py\" | head -20\n\n# Find function definitions\ngrep -rn \"def plan\" .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel\u002Fpython --include=\"*.py\"\n\n# Search for imports\ngrep -r \"from.*import\" .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel\u002Fpython --include=\"*.py\" | grep planning\n```\n\n### Read Specific Files\n\nAfter identifying relevant files with grep\u002Ffind, use the `read_file` tool to examine content:\n\n```bash\n# Example files to read\nread_file .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-kernel\u002Fpython\u002Fsemantic_kernel\u002Fagents\u002Forchestration\u002Fmagentic.py\n```\n\n---\n\n## Useful gh Commands Reference\n\n### Repository Commands\n\n| Command | Description |\n|---------|-------------|\n| `gh repo view \u003Cowner\u002Frepo>` | View repo README and details |\n| `gh repo view \u003Cowner\u002Frepo> --json \u003Cfields>` | Get repo metadata as JSON |\n| `gh repo clone \u003Cowner\u002Frepo> \u003Cpath>` | Clone repo to specific path |\n| `gh repo list \u003Cowner>` | List repos owned by user\u002Forg |\n\n### Search Commands\n\n| Command | Description |\n|---------|-------------|\n| `gh search repos \u003Cquery>` | Search for repositories |\n| `gh search code \u003Cquery>` | Search within code |\n| `gh search issues \u003Cquery>` | Search issues |\n| `gh search prs \u003Cquery>` | Search pull requests |\n\n### Search Filters\n\n| Filter | Example | Description |\n|--------|---------|-------------|\n| `--language` | `--language python` | Filter by programming language |\n| `--owner` | `--owner microsoft` | Filter by repository owner |\n| `--stars` | `--stars \">1000\"` | Filter by star count |\n| `--limit` | `--limit 20` | Limit number of results |\n| `--sort` | `--sort stars` | Sort results (stars, forks, updated) |\n| `--json` | `--json fullName,description` | Output as JSON |\n\n### JSON Fields for Repos\n\nCommon fields for `--json` output:\n- `fullName` - owner\u002Frepo\n- `name` - repo name only\n- `description` - repo description\n- `stargazersCount` - number of stars\n- `language` - primary language\n- `url` - GitHub URL\n- `defaultBranchRef` - main branch name\n\n---\n\n## Example Workflows\n\n### Example 1: Find Reference Implementations for REST API Patterns\n\n```bash\n# 1. Check local cache\nls .agent_cache\u002Fresources\u002F 2>\u002Fdev\u002Fnull || echo \"Cache empty\"\n\n# 2. Search GitHub for Fabric\u002FPower BI SDK examples\ngh search repos \"fabric rest api python\" --stars \">50\" --limit 10\n\n# 3. View promising repo\ngh repo view microsoft\u002Fsemantic-link-labs\n\n# 4. Clone to cache\nmkdir -p .agent_cache\u002Fresources\u002Fmicrosoft\ngh repo clone microsoft\u002Fsemantic-link-labs .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-link-labs -- --depth 1\n\n# 5. Explore API patterns\ngrep -r \"_base_api\" .agent_cache\u002Fresources\u002Fmicrosoft\u002Fsemantic-link-labs --include=\"*.py\" | head -20\n```\n\n### Example 2: Search for Code Patterns\n\n```bash\n# Search for specific pattern across GitHub\ngh search code \"FabricRestClient\" --language python --limit 5\n\n# Clone repo containing the pattern\ngh repo clone owner\u002Frepo .agent_cache\u002Fresources\u002Fowner\u002Frepo -- --depth 1\n\n# Find and read the file\ngrep -rn \"FabricRestClient\" .agent_cache\u002Fresources\u002Fowner\u002Frepo --include=\"*.py\"\n```\n\n### Example 3: Explore Multiple Repos\n\n```bash\n# Search for agent frameworks\ngh search repos \"agent framework\" --language python --stars \">2000\" --json fullName,description,stargazersCount\n\n# Clone top candidates\nfor repo in \"langchain-ai\u002Flangchain\" \"Significant-Gravitas\u002FAutoGPT\"; do\n    owner=$(dirname $repo)\n    mkdir -p \".agent_cache\u002Fresources\u002F$owner\"\n    gh repo clone \"$repo\" \".agent_cache\u002Fresources\u002F$repo\" -- --depth 1\ndone\n\n# Compare implementations\ndiff \u003C(grep -r \"def plan\" .agent_cache\u002Fresources\u002Flangchain-ai\u002Flangchain --include=\"*.py\" | head -5) \\\n     \u003C(grep -r \"def plan\" .agent_cache\u002Fresources\u002FSignificant-Gravitas\u002FAutoGPT --include=\"*.py\" | head -5)\n```\n\n---\n\n## Best Practices\n\n1. **Always check local cache first** -- Avoid redundant cloning\n2. **Use shallow clones** -- Add `-- --depth 1` to save disk space and time\n3. **Organize by owner\u002Frepo** -- Prevents naming conflicts\n4. **Use JSON output** -- Easier to parse programmatically\n5. **Start with grep\u002Ffind** -- Narrow down before reading full files\n6. **Respect rate limits** -- GitHub has API rate limits; cache results\n7. **Clean up periodically** -- Remove unused repos from cache\n\n---\n\n## Troubleshooting\n\n### Authentication Issues\n\n```bash\n# Check current auth status\ngh auth status\n\n# Re-authenticate\ngh auth login\n\n# Use different auth method\ngh auth login --with-token \u003C token.txt\n```\n\n### Rate Limiting\n\n```bash\n# Check rate limit status\ngh api rate_limit\n\n# If rate limited, wait or use cached repos\n```\n\n### Clone Failures\n\n```bash\n# If clone fails, try with HTTPS explicitly\ngit clone https:\u002F\u002Fgithub.com\u002Fowner\u002Frepo.git .agent_cache\u002Fresources\u002Fowner\u002Frepo\n\n# Or try shallow clone\ngit clone --depth 1 https:\u002F\u002Fgithub.com\u002Fowner\u002Frepo.git .agent_cache\u002Fresources\u002Fowner\u002Frepo\n```\n",{"name":5,"description":7},"main","2ddf46109c1209ceffa88149f4631e7b2275f9a1",".claude\u002Fskills\u002Fgithub-repo-explore",204,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsemantic-link-labs","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-13 04:54:42",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add microsoft\u002Fsemantic-link-labs --skill github-repo-explore",{"tool":64,"command":65},"bunx","bunx skills add microsoft\u002Fsemantic-link-labs --skill github-repo-explore",{"tool":67,"command":68},"pnpm","pnpm dlx skills add microsoft\u002Fsemantic-link-labs --skill github-repo-explore","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsemantic-link-labs\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgithub-repo-explore\u002FSKILL.md",true,[72,78,82,86,92,96,102,106,110,114,118,122,126],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"_meta.json","REFERENCE","参考文档",137,"https:\u002F\u002Fgithub.com\u002Fahat4pat-svg\u002Fjimi-skills\u002Fblob\u002Fmain\u002Fskills\u002Fopenclaw-dashboard\u002F_meta.json",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},".clawhub\u002Forigin.json",150,"https:\u002F\u002Fgithub.com\u002Fahat4pat-svg\u002Fjimi-skills\u002Fblob\u002Fmain\u002Fskills\u002Fopenclaw-dashboard\u002F.clawhub\u002Forigin.json",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"agent-dashboard.html",208578,"https:\u002F\u002Fgithub.com\u002Fahat4pat-svg\u002Fjimi-skills\u002Fblob\u002Fmain\u002Fskills\u002Fopenclaw-dashboard\u002Fagent-dashboard.html",{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"api-server.js","SCRIPT","脚本",133506,"https:\u002F\u002Fgithub.com\u002Fahat4pat-svg\u002Fjimi-skills\u002Fblob\u002Fmain\u002Fskills\u002Fopenclaw-dashboard\u002Fapi-server.js",{"path":93,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":94,"sourceHtmlUrl":95},"CHANGELOG.md",7240,"https:\u002F\u002Fgithub.com\u002Fahat4pat-svg\u002Fjimi-skills\u002Fblob\u002Fmain\u002Fskills\u002Fopenclaw-dashboard\u002FCHANGELOG.md",{"path":97,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":100,"sourceHtmlUrl":101},"favicon.svg","ASSET","资产文件",1194,"https:\u002F\u002Fgithub.com\u002Fahat4pat-svg\u002Fjimi-skills\u002Fblob\u002Fmain\u002Fskills\u002Fopenclaw-dashboard\u002Ffavicon.svg",{"path":103,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":104,"sourceHtmlUrl":105},"icon.svg",253,"https:\u002F\u002Fgithub.com\u002Fahat4pat-svg\u002Fjimi-skills\u002Fblob\u002Fmain\u002Fskills\u002Fopenclaw-dashboard\u002Ficon.svg",{"path":107,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":108,"sourceHtmlUrl":109},"marked.min.js",36546,"https:\u002F\u002Fgithub.com\u002Fahat4pat-svg\u002Fjimi-skills\u002Fblob\u002Fmain\u002Fskills\u002Fopenclaw-dashboard\u002Fmarked.min.js",{"path":111,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":112,"sourceHtmlUrl":113},"models-registry.json",1116,"https:\u002F\u002Fgithub.com\u002Fahat4pat-svg\u002Fjimi-skills\u002Fblob\u002Fmain\u002Fskills\u002Fopenclaw-dashboard\u002Fmodels-registry.json",{"path":115,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":116,"sourceHtmlUrl":117},"purify.min.js",23129,"https:\u002F\u002Fgithub.com\u002Fahat4pat-svg\u002Fjimi-skills\u002Fblob\u002Fmain\u002Fskills\u002Fopenclaw-dashboard\u002Fpurify.min.js",{"path":119,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":120,"sourceHtmlUrl":121},"README.md",5773,"https:\u002F\u002Fgithub.com\u002Fahat4pat-svg\u002Fjimi-skills\u002Fblob\u002Fmain\u002Fskills\u002Fopenclaw-dashboard\u002FREADME.md",{"path":123,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":124,"sourceHtmlUrl":125},"SECURITY.md",4725,"https:\u002F\u002Fgithub.com\u002Fahat4pat-svg\u002Fjimi-skills\u002Fblob\u002Fmain\u002Fskills\u002Fopenclaw-dashboard\u002FSECURITY.md",{"path":127,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":128,"sourceHtmlUrl":129},"server-monitor.html",16183,"https:\u002F\u002Fgithub.com\u002Fahat4pat-svg\u002Fjimi-skills\u002Fblob\u002Fmain\u002Fskills\u002Fopenclaw-dashboard\u002Fserver-monitor.html",[131,158,190,207,224,237],{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":148,"publishedAt":44},"01M699GKE0WWT6YVHBS06KM8AH","write-tests","Guide for writing unit tests. Use this when creating tests to verify Python logic.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsemantic-link-labs\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwrite-tests\u002FSKILL.md",[137,142,145],{"categoryNo":138,"categoryName":139,"taxonomyType":140,"taxonomyTypeDesc":141},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":143,"categoryName":144,"taxonomyType":140,"taxonomyTypeDesc":141},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":146,"categoryName":147,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000036","内容创作者",[149,150,151,33,152,31,153,154,155,156,37,38,157],"write tests","write","tests","unit","logic","writing","python","unit tests","verify",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":173,"publishedAt":44},"01M699GGVJHWCJNW68P08VWCMA","ui-styling","Guide for the visual style, structure, and shared building blocks used by Semantic Link Labs interactive UI tools (HTML widgets and anywidget-based widgets). Use this when adding a new interactive UI, modifying an existing one, or adding shared visual components.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsemantic-link-labs\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fui-styling\u002FSKILL.md",[164,167,170],{"categoryNo":165,"categoryName":166,"taxonomyType":140,"taxonomyTypeDesc":141},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":168,"categoryName":169,"taxonomyType":140,"taxonomyTypeDesc":141},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":171,"categoryName":172,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000032","设计师",[174,175,176,37,177,178,179,38,180,181,182,183,184,185,186,187,188,33,189,31],"ui styling","ui","styling","visual","structure","html","interactive","Building Blocks","Tools","components","shared","widgets","style","visual style","blocks","Existing",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":196,"publishedAt":44},"01M699GEZ3YRK8PCPVZF4NEEWF","tom-operations","Guide for working with the TOM (Tabular Object Model) wrapper. Use this when modifying semantic models programmatically.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsemantic-link-labs\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftom-operations\u002FSKILL.md",[],[197,198,38,199,33,200,201,202,203,204,37,31,205,206],"operations","tom operations","tabular","object","with","semantic","models","Wrapper","model","semantic models",{"skillNo":208,"name":209,"nameZh":6,"description":210,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":211,"categories":212,"keywords":219,"publishedAt":44},"01M699GCWWBZM2XFNW5PTGRFJP","sql_to_dax","Guide for translating SQL aggregation expressions into DAX measures.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsemantic-link-labs\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fsql_to_dax\u002FSKILL.md",[213,216],{"categoryNo":214,"categoryName":215,"taxonomyType":140,"taxonomyTypeDesc":141},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":217,"categoryName":218,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000033","数据分析师",[220,221,222,33,38,223],"sql","sql to dax","dax","aggregation",{"skillNo":225,"name":226,"nameZh":6,"description":227,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":228,"categories":229,"keywords":230,"publishedAt":44},"01M699GAY10VVK66E4QGT94A93","run-tests","Guide for running pytest tests locally. Use this when running tests to verify code changes.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsemantic-link-labs\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frun-tests\u002FSKILL.md",[],[151,231,232,33,233,37,38,157,234,43,235,236,31],"run","run tests","pytest","running tests","changes","running",{"skillNo":238,"name":239,"nameZh":6,"description":240,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":241,"categories":242,"keywords":245,"publishedAt":44},"01M699G8V718EXYE8BR7NX734G","rest-api-patterns","Guide for implementing REST API wrapper functions. Use this when adding new API wrappers or troubleshooting API calls.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsemantic-link-labs\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frest-api-patterns\u002FSKILL.md",[243,244],{"categoryNo":214,"categoryName":215,"taxonomyType":140,"taxonomyTypeDesc":141},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[246,247,248,249,250,36,33,31,251,252,253,204,37,38,254],"REST","api patterns","rest api","rest api patterns","api","implementing","calls","functions","troubleshooting"]