[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73G646ZC8S7BDC0CVCC7ABY":3,"skill-same:01M73G646ZC8S7BDC0CVCC7ABY":49},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M73G646ZC8S7BDC0CVCC7ABY","create-mcp-servers",null,"Create Model Context Protocol (MCP) servers that expose tools, resources, and prompts to Claude. Use when building custom integrations, APIs, data sources, or any server that Claude should interact with via the MCP protocol. Supports both TypeScript and Python implementations.","Horonomos-laps\u002FYana-AI","Horonomos-laps","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F355299122?v=4","01M76B3QPXE88ET2SQPDPVATZT"," Horonomos-laps","01M72ZQRJPCYPSSWT4D00VJR2A",13,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Ftaches--create-mcp-servers\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: create-mcp-servers\ndescription: Create Model Context Protocol (MCP) servers that expose tools, resources, and prompts to Claude. Use when building custom integrations, APIs, data sources, or any server that Claude should interact with via the MCP protocol. Supports both TypeScript and Python implementations.\norigin: \"https:\u002F\u002Fraw.githubusercontent.com\u002Fglittercowboy\u002Ftaches-cc-resources\u002Fmain\u002Fskills\u002Fcreate-mcp-servers\u002FSKILL.md\"\n---\n\n\u003Cobjective>\nMCP servers extend Claude's capabilities by exposing tools, resources, and prompts. This skill guides creation of production-ready MCP servers with API integrations, OAuth authentication, response optimization, and proper installation in Claude Code and Claude Desktop.\n\u003C\u002Fobjective>\n\n\u003Cessential_principles>\n\n\u003Cthe_5_rules>\nEvery MCP server must follow these:\n\n1. **Never Hardcode Secrets** - Use `${VAR}` expansion in configs, environment variables in code\n2. **Use `cwd` Property** - Isolates dependencies (not `--cwd` in args)\n3. **Always Absolute Paths** - `which uv` to find paths, never relative\n4. **One Server Per Directory** - `~\u002FDeveloper\u002Fmcp\u002F{server-name}\u002F`\n5. **Use `uv` for Python** - Better than pip, handles venvs automatically\n\u003C\u002Fthe_5_rules>\n\n\u003Csecurity_checklist>\n- Never ask user to paste secrets into chat\n- Always use environment variables for credentials\n- Use ${VAR} expansion in configs\n- Provide exact commands for user to run in terminal\n- Verify environment variable existence without showing values\n- Never hardcode API keys in code or configs\n\u003C\u002Fsecurity_checklist>\n\n\u003Carchitecture_decision>\nOperation count determines architecture:\n\n- **1-2 operations** → Traditional pattern (flat tools)\n- **3+ operations** → On-demand discovery pattern (meta-tools)\n\nTraditional: Each operation is a separate tool\nOn-demand: 4 meta-tools (discover, get_schema, execute, continue) + operations.json\n\u003C\u002Farchitecture_decision>\n\n\u003Ccontext>\nMCP servers expose:\n- **Tools**: Functions Claude can call (API requests, file operations, calculations)\n- **Resources**: Data Claude can read (files, database records, API responses)\n- **Prompts**: Reusable prompt templates with arguments\n\nStandard location: `~\u002FDeveloper\u002Fmcp\u002F{server-name}\u002F`\n\u003C\u002Fcontext>\n\n\u003C\u002Fessential_principles>\n\n\u003Crouting>\nBased on user intent, route to appropriate workflow:\n\n**No context provided** (skill invoked without description):\nUse AskUserQuestion:\n- header: \"Mode\"\n- question: \"What would you like to do?\"\n- options:\n  - \"Create a new MCP server\" → workflows\u002Fcreate-new-server.md\n  - \"Update an existing MCP server\" → workflows\u002Fupdate-existing-server.md\n  - \"Troubleshoot a server\" → workflows\u002Ftroubleshoot-server.md\n\n**Context provided** (user described what they want):\nRoute directly to workflows\u002Fcreate-new-server.md\n\u003C\u002Frouting>\n\n\u003Cworkflows_index>\n| Workflow | Purpose |\n|----------|---------|\n| create-new-server.md | Full 8-step workflow from intake to verification |\n| update-existing-server.md | Modify or extend an existing server |\n| troubleshoot-server.md | Diagnose and fix connection\u002Fruntime issues |\n\u003C\u002Fworkflows_index>\n\n\u003Ctemplates_index>\n| Template | Purpose |\n|----------|---------|\n| python-server.py | Traditional pattern starter for Python |\n| typescript-server.ts | Traditional pattern starter for TypeScript |\n| operations.json | On-demand discovery operations definition |\n\u003C\u002Ftemplates_index>\n\n\u003Cscripts_index>\n| Script | Purpose |\n|--------|---------|\n| setup-python-project.sh | Initialize Python MCP project with uv |\n| setup-typescript-project.sh | Initialize TypeScript MCP project with npm |\n\u003C\u002Fscripts_index>\n\n\u003Creferences_index>\n**Core workflow:**\n- creation-workflow.md - Complete step-by-step with exact commands\n\n**Architecture patterns:**\n- traditional-pattern.md - For 1-2 operations (flat tools)\n- large-api-pattern.md - For 3+ operations (on-demand discovery)\n\n**Language-specific:**\n- python-implementation.md - Async patterns, type hints\n- typescript-implementation.md - Type safety, SDK features\n\n**Advanced topics:**\n- oauth-implementation.md - OAuth with stdio isolation\n- response-optimization.md - Field truncation, pagination\n- tools-and-resources.md - Resources API, prompts, streaming\n- testing-and-deployment.md - Unit tests, packaging, publishing\n- validation-checkpoints.md - All validation checks\n- adaptive-questioning-guide.md - Question templates for intake\n- api-research-template.md - API research document format\n\u003C\u002Freferences_index>\n\n\u003Cquick_reference>\n```bash\n# List servers\nclaude mcp list\n\n# Add server (Python)\nclaude mcp add --transport stdio \u003Cname> \\\n  --env API_KEY='${API_KEY}' \\\n  -- uv --directory ~\u002FDeveloper\u002Fmcp\u002F\u003Cname> run python -m src.server\n\n# Add server (TypeScript)\nclaude mcp add --transport stdio \u003Cname> \\\n  --env API_KEY='${API_KEY}' \\\n  -- node ~\u002FDeveloper\u002Fmcp\u002F\u003Cname>\u002Fbuild\u002Findex.js\n\n# Remove server\nclaude mcp remove \u003Cname>\n\n# Check logs\ntail -f ~\u002FLibrary\u002FLogs\u002FClaude\u002Fmcp-server-\u003Cname>.log\n\n# Find paths\nwhich uv && which node && which python\n```\n\u003C\u002Fquick_reference>\n\n\u003Ctroubleshooting_quick>\n**Server not appearing:** Check `claude mcp list`, verify config in `~\u002F.claude\u002Fsettings.json`\n\n**\"command not found\":** Use absolute paths from `which uv` \u002F `which node`\n\n**Environment variable not found:**\n```bash\necho $MY_API_KEY  # Check if set\necho 'export MY_API_KEY=\"value\"' >> ~\u002F.zshrc && source ~\u002F.zshrc\n```\n\n**Secrets visible in conversation:** STOP. Delete conversation. Rotate credentials. Never paste secrets in chat.\n\nFull troubleshooting: workflows\u002Ftroubleshoot-server.md\n\u003C\u002Ftroubleshooting_quick>\n\n\u003Csuccess_criteria>\nA production-ready MCP server has:\n- Valid configuration in Claude Code (`claude mcp list` shows ✓ Connected)\n- Valid configuration in Claude Desktop config\n- Environment variables set securely in ~\u002F.zshrc\n- Architecture matches operation count\n- OAuth stdio isolation if applicable\n- Response optimization for list\u002Fsearch operations\n- All validation checkpoints passed\n- No errors in logs\n\u003C\u002Fsuccess_criteria>\n","\u003Cobjective>\nMCP servers extend Claude's capabilities by exposing tools, resources, and prompts. This skill guides creation of production-ready MCP servers with API integrations, OAuth authentication, response optimization, and proper installation in Claude Code and Claude Desktop.\n\u003C\u002Fobjective>\n\n\u003Cessential_principles>\n\n\u003Cthe_5_rules>\nEvery MCP server must follow these:\n\n1. **Never Hardcode Secrets** - Use `${VAR}` expansion in configs, environment variables in code\n2. **Use `cwd` Property** - Isolates dependencies (not `--cwd` in args)\n3. **Always Absolute Paths** - `which uv` to find paths, never relative\n4. **One Server Per Directory** - `~\u002FDeveloper\u002Fmcp\u002F{server-name}\u002F`\n5. **Use `uv` for Python** - Better than pip, handles venvs automatically\n\u003C\u002Fthe_5_rules>\n\n\u003Csecurity_checklist>\n- Never ask user to paste secrets into chat\n- Always use environment variables for credentials\n- Use ${VAR} expansion in configs\n- Provide exact commands for user to run in terminal\n- Verify environment variable existence without showing values\n- Never hardcode API keys in code or configs\n\u003C\u002Fsecurity_checklist>\n\n\u003Carchitecture_decision>\nOperation count determines architecture:\n\n- **1-2 operations** → Traditional pattern (flat tools)\n- **3+ operations** → On-demand discovery pattern (meta-tools)\n\nTraditional: Each operation is a separate tool\nOn-demand: 4 meta-tools (discover, get_schema, execute, continue) + operations.json\n\u003C\u002Farchitecture_decision>\n\n\u003Ccontext>\nMCP servers expose:\n- **Tools**: Functions Claude can call (API requests, file operations, calculations)\n- **Resources**: Data Claude can read (files, database records, API responses)\n- **Prompts**: Reusable prompt templates with arguments\n\nStandard location: `~\u002FDeveloper\u002Fmcp\u002F{server-name}\u002F`\n\u003C\u002Fcontext>\n\n\u003C\u002Fessential_principles>\n\n\u003Crouting>\nBased on user intent, route to appropriate workflow:\n\n**No context provided** (skill invoked without description):\nUse AskUserQuestion:\n- header: \"Mode\"\n- question: \"What would you like to do?\"\n- options:\n  - \"Create a new MCP server\" → workflows\u002Fcreate-new-server.md\n  - \"Update an existing MCP server\" → workflows\u002Fupdate-existing-server.md\n  - \"Troubleshoot a server\" → workflows\u002Ftroubleshoot-server.md\n\n**Context provided** (user described what they want):\nRoute directly to workflows\u002Fcreate-new-server.md\n\u003C\u002Frouting>\n\n\u003Cworkflows_index>\n| Workflow | Purpose |\n|----------|---------|\n| create-new-server.md | Full 8-step workflow from intake to verification |\n| update-existing-server.md | Modify or extend an existing server |\n| troubleshoot-server.md | Diagnose and fix connection\u002Fruntime issues |\n\u003C\u002Fworkflows_index>\n\n\u003Ctemplates_index>\n| Template | Purpose |\n|----------|---------|\n| python-server.py | Traditional pattern starter for Python |\n| typescript-server.ts | Traditional pattern starter for TypeScript |\n| operations.json | On-demand discovery operations definition |\n\u003C\u002Ftemplates_index>\n\n\u003Cscripts_index>\n| Script | Purpose |\n|--------|---------|\n| setup-python-project.sh | Initialize Python MCP project with uv |\n| setup-typescript-project.sh | Initialize TypeScript MCP project with npm |\n\u003C\u002Fscripts_index>\n\n\u003Creferences_index>\n**Core workflow:**\n- creation-workflow.md - Complete step-by-step with exact commands\n\n**Architecture patterns:**\n- traditional-pattern.md - For 1-2 operations (flat tools)\n- large-api-pattern.md - For 3+ operations (on-demand discovery)\n\n**Language-specific:**\n- python-implementation.md - Async patterns, type hints\n- typescript-implementation.md - Type safety, SDK features\n\n**Advanced topics:**\n- oauth-implementation.md - OAuth with stdio isolation\n- response-optimization.md - Field truncation, pagination\n- tools-and-resources.md - Resources API, prompts, streaming\n- testing-and-deployment.md - Unit tests, packaging, publishing\n- validation-checkpoints.md - All validation checks\n- adaptive-questioning-guide.md - Question templates for intake\n- api-research-template.md - API research document format\n\u003C\u002Freferences_index>\n\n\u003Cquick_reference>\n```bash\n# List servers\nclaude mcp list\n\n# Add server (Python)\nclaude mcp add --transport stdio \u003Cname> \\\n  --env API_KEY='${API_KEY}' \\\n  -- uv --directory ~\u002FDeveloper\u002Fmcp\u002F\u003Cname> run python -m src.server\n\n# Add server (TypeScript)\nclaude mcp add --transport stdio \u003Cname> \\\n  --env API_KEY='${API_KEY}' \\\n  -- node ~\u002FDeveloper\u002Fmcp\u002F\u003Cname>\u002Fbuild\u002Findex.js\n\n# Remove server\nclaude mcp remove \u003Cname>\n\n# Check logs\ntail -f ~\u002FLibrary\u002FLogs\u002FClaude\u002Fmcp-server-\u003Cname>.log\n\n# Find paths\nwhich uv && which node && which python\n```\n\u003C\u002Fquick_reference>\n\n\u003Ctroubleshooting_quick>\n**Server not appearing:** Check `claude mcp list`, verify config in `~\u002F.claude\u002Fsettings.json`\n\n**\"command not found\":** Use absolute paths from `which uv` \u002F `which node`\n\n**Environment variable not found:**\n```bash\necho $MY_API_KEY  # Check if set\necho 'export MY_API_KEY=\"value\"' >> ~\u002F.zshrc && source ~\u002F.zshrc\n```\n\n**Secrets visible in conversation:** STOP. Delete conversation. Rotate credentials. Never paste secrets in chat.\n\nFull troubleshooting: workflows\u002Ftroubleshoot-server.md\n\u003C\u002Ftroubleshooting_quick>\n\n\u003Csuccess_criteria>\nA production-ready MCP server has:\n- Valid configuration in Claude Code (`claude mcp list` shows ✓ Connected)\n- Valid configuration in Claude Desktop config\n- Environment variables set securely in ~\u002F.zshrc\n- Architecture matches operation count\n- OAuth stdio isolation if applicable\n- Response optimization for list\u002Fsearch operations\n- All validation checkpoints passed\n- No errors in logs\n\u003C\u002Fsuccess_criteria>\n",{"name":5,"origin":24,"description":7},"https:\u002F\u002Fraw.githubusercontent.com\u002Fglittercowboy\u002Ftaches-cc-resources\u002Fmain\u002Fskills\u002Fcreate-mcp-servers\u002FSKILL.md","main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa","core\u002Fskills\u002Ftaches--create-mcp-servers",2,"https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI","https:\u002F\u002Fyana.vutam.link\u002F","https:\u002F\u002Fgithub.com\u002FHoronomos-laps","https:\u002F\u002Fyana.vutam.link","An open-source governed runtime & execution environment for multi-agent AI systems.","2026-11-12 23:12:27",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add Horonomos-laps\u002FYana-AI --skill create-mcp-servers",{"tool":41,"command":42},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill create-mcp-servers",{"tool":44,"command":45},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill create-mcp-servers","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Ftaches--create-mcp-servers\u002FSKILL.md",true,[],[50,58,65,73,81,89],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":54,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M735GKET5YVYKAY62W2P5YXB","openai--sentry--sentry","Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.","MIT","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fopenai--sentry--sentry\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M73DCAP83T17HY7SMGK7MGFE","ito-basket-compare","Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fito-basket-compare\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":69,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M734CYEMZFDR3KH6SW0JP8TD","implementing-network-traffic-baselining","Build network traffic baselines from NetFlow\u002FIPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly\u002Fdaily traffic pattern profiling","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":77,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M73ASZ6NJRJM44Z2P84NGQ3Q","detecting-evasion-techniques-in-endpoint-logs","Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M734AFNXD06Z78QRK0VKGT7Q","implementing-microsegmentation-with-guardicore","Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"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":92,"categories":93,"keywords":94,"publishedAt":19},"01M736TK27QMCXK0DVCH25SJN5","ramdisk-tmpfs-patterns","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Framdisk-tmpfs-patterns\u002FSKILL.md",[],[]]