[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BWYVDCBSBF178W71CSXY4X":3,"skill-same:01M7BWYVDCBSBF178W71CSXY4X":92},{"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":47,"commitSha":48,"skillDirectory":49,"forksCount":14,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M7BWYVDCBSBF178W71CSXY4X","fastmcp",null,"Build, test, inspect, install, and deploy MCP servers with FastMCP in Python. Use when creating a new MCP server, wrapping an API or database as MCP tools, exposing resources or prompts, or preparing a FastMCP server for Claude Code, Cursor, or HTTP deployment.","yuxua24\u002Fworkspace","yuxua24","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F145311182?v=4","01M7BWRX3SGTW32KC66ZKHKKJT","Yuxuan Ao","01M7BWRX4GD7VN7NV8WQPWHQJE",0,"MIT","https:\u002F\u002Fgithub.com\u002Fyuxua24\u002Fworkspace\u002Fblob\u002Fautoresearch\u002Fpi-agent-merchantbench-net-assets-workspace-omp-20260901\u002Fhermes-agent\u002Foptional-skills\u002Fmcp\u002Ffastmcp\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: fastmcp\ndescription: Build, test, inspect, install, and deploy MCP servers with FastMCP in Python. Use when creating a new MCP server, wrapping an API or database as MCP tools, exposing resources or prompts, or preparing a FastMCP server for Claude Code, Cursor, or HTTP deployment.\nversion: 1.0.0\nauthor: Hermes Agent\nlicense: MIT\nplatforms: [linux, macos, windows]\nmetadata:\n  hermes:\n    tags: [MCP, FastMCP, Python, Tools, Resources, Prompts, Deployment]\n    homepage: https:\u002F\u002Fgofastmcp.com\n    related_skills: [native-mcp, mcporter]\nprerequisites:\n  commands: [python3]\n---\n\n# FastMCP\n\nBuild MCP servers in Python with FastMCP, validate them locally, install them into MCP clients, and deploy them as HTTP endpoints.\n\n## When to Use\n\nUse this skill when the task is to:\n\n- create a new MCP server in Python\n- wrap an API, database, CLI, or file-processing workflow as MCP tools\n- expose resources or prompts in addition to tools\n- smoke-test a server with the FastMCP CLI before wiring it into Hermes or another client\n- install a server into Claude Code, Claude Desktop, Cursor, or a similar MCP client\n- prepare a FastMCP server repo for HTTP deployment\n\nUse `native-mcp` when the server already exists and only needs to be connected to Hermes. Use `mcporter` when the goal is ad-hoc CLI access to an existing MCP server instead of building one.\n\n## Prerequisites\n\nInstall FastMCP in the working environment first:\n\n```bash\npip install fastmcp\nfastmcp version\n```\n\nFor the API template, install `httpx` if it is not already present:\n\n```bash\npip install httpx\n```\n\n## Included Files\n\n### Templates\n\n- `templates\u002Fapi_wrapper.py` - REST API wrapper with auth header support\n- `templates\u002Fdatabase_server.py` - read-only SQLite query server\n- `templates\u002Ffile_processor.py` - text-file inspection and search server\n\n### Scripts\n\n- `scripts\u002Fscaffold_fastmcp.py` - copy a starter template and replace the server name placeholder\n\n### References\n\n- `references\u002Ffastmcp-cli.md` - FastMCP CLI workflow, installation targets, and deployment checks\n\n## Workflow\n\n### 1. Pick the Smallest Viable Server Shape\n\nChoose the narrowest useful surface area first:\n\n- API wrapper: start with 1-3 high-value endpoints, not the whole API\n- database server: expose read-only introspection and a constrained query path\n- file processor: expose deterministic operations with explicit path arguments\n- prompts\u002Fresources: add only when the client needs reusable prompt templates or discoverable documents\n\nPrefer a thin server with good names, docstrings, and schemas over a large server with vague tools.\n\n### 2. Scaffold from a Template\n\nCopy a template directly or use the scaffold helper:\n\n```bash\npython ~\u002F.hermes\u002Fskills\u002Fmcp\u002Ffastmcp\u002Fscripts\u002Fscaffold_fastmcp.py \\\n  --template api_wrapper \\\n  --name \"Acme API\" \\\n  --output .\u002Facme_server.py\n```\n\nAvailable templates:\n\n```bash\npython ~\u002F.hermes\u002Fskills\u002Fmcp\u002Ffastmcp\u002Fscripts\u002Fscaffold_fastmcp.py --list\n```\n\nIf copying manually, replace `__SERVER_NAME__` with a real server name.\n\n### 3. Implement Tools First\n\nStart with `@mcp.tool` functions before adding resources or prompts.\n\nRules for tool design:\n\n- Give every tool a concrete verb-based name\n- Write docstrings as user-facing tool descriptions\n- Keep parameters explicit and typed\n- Return structured JSON-safe data where possible\n- Validate unsafe inputs early\n- Prefer read-only behavior by default for first versions\n\nGood tool examples:\n\n- `get_customer`\n- `search_tickets`\n- `describe_table`\n- `summarize_text_file`\n\nWeak tool examples:\n\n- `run`\n- `process`\n- `do_thing`\n\n### 4. Add Resources and Prompts Only When They Help\n\nAdd `@mcp.resource` when the client benefits from fetching stable read-only content such as schemas, policy docs, or generated reports.\n\nAdd `@mcp.prompt` when the server should provide a reusable prompt template for a known workflow.\n\nDo not turn every document into a prompt. Prefer:\n\n- tools for actions\n- resources for data\u002Fdocument retrieval\n- prompts for reusable LLM instructions\n\n### 5. Test the Server Before Integrating It Anywhere\n\nUse the FastMCP CLI for local validation:\n\n```bash\nfastmcp inspect acme_server.py:mcp\nfastmcp list acme_server.py --json\nfastmcp call acme_server.py search_resources query=router limit=5 --json\n```\n\nFor fast iterative debugging, run the server locally:\n\n```bash\nfastmcp run acme_server.py:mcp\n```\n\nTo test HTTP transport locally:\n\n```bash\nfastmcp run acme_server.py:mcp --transport http --host 127.0.0.1 --port 8000\nfastmcp list http:\u002F\u002F127.0.0.1:8000\u002Fmcp --json\nfastmcp call http:\u002F\u002F127.0.0.1:8000\u002Fmcp search_resources query=router --json\n```\n\nAlways run at least one real `fastmcp call` against each new tool before claiming the server works.\n\n### 6. Install into a Client When Local Validation Passes\n\nFastMCP can register the server with supported MCP clients:\n\n```bash\nfastmcp install claude-code acme_server.py\nfastmcp install claude-desktop acme_server.py\nfastmcp install cursor acme_server.py -e .\n```\n\nUse `fastmcp discover` to inspect named MCP servers already configured on the machine.\n\nWhen the goal is Hermes integration, either:\n\n- configure the server in `~\u002F.hermes\u002Fconfig.yaml` using the `native-mcp` skill, or\n- keep using FastMCP CLI commands during development until the interface stabilizes\n\n### 7. Deploy After the Local Contract Is Stable\n\nFor managed hosting, Prefect Horizon is the path FastMCP documents most directly. Before deployment:\n\n```bash\nfastmcp inspect acme_server.py:mcp\n```\n\nMake sure the repo contains:\n\n- a Python file with the FastMCP server object\n- `requirements.txt` or `pyproject.toml`\n- any environment-variable documentation needed for deployment\n\nFor generic HTTP hosting, validate the HTTP transport locally first, then deploy on any Python-compatible platform that can expose the server port.\n\n## Common Patterns\n\n### API Wrapper Pattern\n\nUse when exposing a REST or HTTP API as MCP tools.\n\nRecommended first slice:\n\n- one read path\n- one list\u002Fsearch path\n- optional health check\n\nImplementation notes:\n\n- keep auth in environment variables, not hardcoded\n- centralize request logic in one helper\n- surface API errors with concise context\n- normalize inconsistent upstream payloads before returning them\n\nStart from `templates\u002Fapi_wrapper.py`.\n\n### Database Pattern\n\nUse when exposing safe query and inspection capabilities.\n\nRecommended first slice:\n\n- `list_tables`\n- `describe_table`\n- one constrained read query tool\n\nImplementation notes:\n\n- default to read-only DB access\n- reject non-`SELECT` SQL in early versions\n- limit row counts\n- return rows plus column names\n\nStart from `templates\u002Fdatabase_server.py`.\n\n### File Processor Pattern\n\nUse when the server needs to inspect or transform files on demand.\n\nRecommended first slice:\n\n- summarize file contents\n- search within files\n- extract deterministic metadata\n\nImplementation notes:\n\n- accept explicit file paths\n- check for missing files and encoding failures\n- cap previews and result counts\n- avoid shelling out unless a specific external tool is required\n\nStart from `templates\u002Ffile_processor.py`.\n\n## Quality Bar\n\nBefore handing off a FastMCP server, verify all of the following:\n\n- server imports cleanly\n- `fastmcp inspect \u003Cfile.py:mcp>` succeeds\n- `fastmcp list \u003Cserver spec> --json` succeeds\n- every new tool has at least one real `fastmcp call`\n- environment variables are documented\n- the tool surface is small enough to understand without guesswork\n\n## Troubleshooting\n\n### FastMCP command missing\n\nInstall the package in the active environment:\n\n```bash\npip install fastmcp\nfastmcp version\n```\n\n### `fastmcp inspect` fails\n\nCheck that:\n\n- the file imports without side effects that crash\n- the FastMCP instance is named correctly in `\u003Cfile.py:object>`\n- optional dependencies from the template are installed\n\n### Tool works in Python but not through CLI\n\nRun:\n\n```bash\nfastmcp list server.py --json\nfastmcp call server.py your_tool_name --json\n```\n\nThis usually exposes naming mismatches, missing required arguments, or non-serializable return values.\n\n### Hermes cannot see the deployed server\n\nThe server-building part may be correct while the Hermes config is not. Load the `native-mcp` skill and configure the server in `~\u002F.hermes\u002Fconfig.yaml`, then restart Hermes.\n\n## References\n\nFor CLI details, install targets, and deployment checks, read `references\u002Ffastmcp-cli.md`.\n","# FastMCP\n\nBuild MCP servers in Python with FastMCP, validate them locally, install them into MCP clients, and deploy them as HTTP endpoints.\n\n## When to Use\n\nUse this skill when the task is to:\n\n- create a new MCP server in Python\n- wrap an API, database, CLI, or file-processing workflow as MCP tools\n- expose resources or prompts in addition to tools\n- smoke-test a server with the FastMCP CLI before wiring it into Hermes or another client\n- install a server into Claude Code, Claude Desktop, Cursor, or a similar MCP client\n- prepare a FastMCP server repo for HTTP deployment\n\nUse `native-mcp` when the server already exists and only needs to be connected to Hermes. Use `mcporter` when the goal is ad-hoc CLI access to an existing MCP server instead of building one.\n\n## Prerequisites\n\nInstall FastMCP in the working environment first:\n\n```bash\npip install fastmcp\nfastmcp version\n```\n\nFor the API template, install `httpx` if it is not already present:\n\n```bash\npip install httpx\n```\n\n## Included Files\n\n### Templates\n\n- `templates\u002Fapi_wrapper.py` - REST API wrapper with auth header support\n- `templates\u002Fdatabase_server.py` - read-only SQLite query server\n- `templates\u002Ffile_processor.py` - text-file inspection and search server\n\n### Scripts\n\n- `scripts\u002Fscaffold_fastmcp.py` - copy a starter template and replace the server name placeholder\n\n### References\n\n- `references\u002Ffastmcp-cli.md` - FastMCP CLI workflow, installation targets, and deployment checks\n\n## Workflow\n\n### 1. Pick the Smallest Viable Server Shape\n\nChoose the narrowest useful surface area first:\n\n- API wrapper: start with 1-3 high-value endpoints, not the whole API\n- database server: expose read-only introspection and a constrained query path\n- file processor: expose deterministic operations with explicit path arguments\n- prompts\u002Fresources: add only when the client needs reusable prompt templates or discoverable documents\n\nPrefer a thin server with good names, docstrings, and schemas over a large server with vague tools.\n\n### 2. Scaffold from a Template\n\nCopy a template directly or use the scaffold helper:\n\n```bash\npython ~\u002F.hermes\u002Fskills\u002Fmcp\u002Ffastmcp\u002Fscripts\u002Fscaffold_fastmcp.py \\\n  --template api_wrapper \\\n  --name \"Acme API\" \\\n  --output .\u002Facme_server.py\n```\n\nAvailable templates:\n\n```bash\npython ~\u002F.hermes\u002Fskills\u002Fmcp\u002Ffastmcp\u002Fscripts\u002Fscaffold_fastmcp.py --list\n```\n\nIf copying manually, replace `__SERVER_NAME__` with a real server name.\n\n### 3. Implement Tools First\n\nStart with `@mcp.tool` functions before adding resources or prompts.\n\nRules for tool design:\n\n- Give every tool a concrete verb-based name\n- Write docstrings as user-facing tool descriptions\n- Keep parameters explicit and typed\n- Return structured JSON-safe data where possible\n- Validate unsafe inputs early\n- Prefer read-only behavior by default for first versions\n\nGood tool examples:\n\n- `get_customer`\n- `search_tickets`\n- `describe_table`\n- `summarize_text_file`\n\nWeak tool examples:\n\n- `run`\n- `process`\n- `do_thing`\n\n### 4. Add Resources and Prompts Only When They Help\n\nAdd `@mcp.resource` when the client benefits from fetching stable read-only content such as schemas, policy docs, or generated reports.\n\nAdd `@mcp.prompt` when the server should provide a reusable prompt template for a known workflow.\n\nDo not turn every document into a prompt. Prefer:\n\n- tools for actions\n- resources for data\u002Fdocument retrieval\n- prompts for reusable LLM instructions\n\n### 5. Test the Server Before Integrating It Anywhere\n\nUse the FastMCP CLI for local validation:\n\n```bash\nfastmcp inspect acme_server.py:mcp\nfastmcp list acme_server.py --json\nfastmcp call acme_server.py search_resources query=router limit=5 --json\n```\n\nFor fast iterative debugging, run the server locally:\n\n```bash\nfastmcp run acme_server.py:mcp\n```\n\nTo test HTTP transport locally:\n\n```bash\nfastmcp run acme_server.py:mcp --transport http --host 127.0.0.1 --port 8000\nfastmcp list http:\u002F\u002F127.0.0.1:8000\u002Fmcp --json\nfastmcp call http:\u002F\u002F127.0.0.1:8000\u002Fmcp search_resources query=router --json\n```\n\nAlways run at least one real `fastmcp call` against each new tool before claiming the server works.\n\n### 6. Install into a Client When Local Validation Passes\n\nFastMCP can register the server with supported MCP clients:\n\n```bash\nfastmcp install claude-code acme_server.py\nfastmcp install claude-desktop acme_server.py\nfastmcp install cursor acme_server.py -e .\n```\n\nUse `fastmcp discover` to inspect named MCP servers already configured on the machine.\n\nWhen the goal is Hermes integration, either:\n\n- configure the server in `~\u002F.hermes\u002Fconfig.yaml` using the `native-mcp` skill, or\n- keep using FastMCP CLI commands during development until the interface stabilizes\n\n### 7. Deploy After the Local Contract Is Stable\n\nFor managed hosting, Prefect Horizon is the path FastMCP documents most directly. Before deployment:\n\n```bash\nfastmcp inspect acme_server.py:mcp\n```\n\nMake sure the repo contains:\n\n- a Python file with the FastMCP server object\n- `requirements.txt` or `pyproject.toml`\n- any environment-variable documentation needed for deployment\n\nFor generic HTTP hosting, validate the HTTP transport locally first, then deploy on any Python-compatible platform that can expose the server port.\n\n## Common Patterns\n\n### API Wrapper Pattern\n\nUse when exposing a REST or HTTP API as MCP tools.\n\nRecommended first slice:\n\n- one read path\n- one list\u002Fsearch path\n- optional health check\n\nImplementation notes:\n\n- keep auth in environment variables, not hardcoded\n- centralize request logic in one helper\n- surface API errors with concise context\n- normalize inconsistent upstream payloads before returning them\n\nStart from `templates\u002Fapi_wrapper.py`.\n\n### Database Pattern\n\nUse when exposing safe query and inspection capabilities.\n\nRecommended first slice:\n\n- `list_tables`\n- `describe_table`\n- one constrained read query tool\n\nImplementation notes:\n\n- default to read-only DB access\n- reject non-`SELECT` SQL in early versions\n- limit row counts\n- return rows plus column names\n\nStart from `templates\u002Fdatabase_server.py`.\n\n### File Processor Pattern\n\nUse when the server needs to inspect or transform files on demand.\n\nRecommended first slice:\n\n- summarize file contents\n- search within files\n- extract deterministic metadata\n\nImplementation notes:\n\n- accept explicit file paths\n- check for missing files and encoding failures\n- cap previews and result counts\n- avoid shelling out unless a specific external tool is required\n\nStart from `templates\u002Ffile_processor.py`.\n\n## Quality Bar\n\nBefore handing off a FastMCP server, verify all of the following:\n\n- server imports cleanly\n- `fastmcp inspect \u003Cfile.py:mcp>` succeeds\n- `fastmcp list \u003Cserver spec> --json` succeeds\n- every new tool has at least one real `fastmcp call`\n- environment variables are documented\n- the tool surface is small enough to understand without guesswork\n\n## Troubleshooting\n\n### FastMCP command missing\n\nInstall the package in the active environment:\n\n```bash\npip install fastmcp\nfastmcp version\n```\n\n### `fastmcp inspect` fails\n\nCheck that:\n\n- the file imports without side effects that crash\n- the FastMCP instance is named correctly in `\u003Cfile.py:object>`\n- optional dependencies from the template are installed\n\n### Tool works in Python but not through CLI\n\nRun:\n\n```bash\nfastmcp list server.py --json\nfastmcp call server.py your_tool_name --json\n```\n\nThis usually exposes naming mismatches, missing required arguments, or non-serializable return values.\n\n### Hermes cannot see the deployed server\n\nThe server-building part may be correct while the Hermes config is not. Load the `native-mcp` skill and configure the server in `~\u002F.hermes\u002Fconfig.yaml`, then restart Hermes.\n\n## References\n\nFor CLI details, install targets, and deployment checks, read `references\u002Ffastmcp-cli.md`.\n",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"platforms":40,"description":7,"prerequisites":44},"Hermes Agent","1.0.0",{"hermes":27},{"tags":28,"homepage":36,"related_skills":37},[29,30,31,32,33,34,35],"MCP","FastMCP","Python","Tools","Resources","Prompts","Deployment","https:\u002F\u002Fgofastmcp.com",[38,39],"native-mcp","mcporter",[41,42,43],"linux","macos","windows",{"commands":45},[46],"python3","autoresearch\u002Fpi-agent-merchantbench-net-assets-workspace-omp-20260901","762e83a83bedbed565e95e7d42d39204c367c9eb","hermes-agent\u002Foptional-skills\u002Fmcp\u002Ffastmcp","https:\u002F\u002Fgithub.com\u002Fyuxua24\u002Fworkspace","https:\u002F\u002Fgithub.com\u002Fyuxua24","I am Ao Yuxuan, a student in Xi'an Jiaotong University. I am eager to learn on GitHub and contribute my part to this community.","2026-09-01 17:37:09",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add yuxua24\u002Fworkspace --skill fastmcp",{"tool":60,"command":61},"bunx","bunx skills add yuxua24\u002Fworkspace --skill fastmcp",{"tool":63,"command":64},"pnpm","pnpm dlx skills add yuxua24\u002Fworkspace --skill fastmcp","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fyuxua24\u002Fworkspace\u002Fblob\u002Fautoresearch\u002Fpi-agent-merchantbench-net-assets-workspace-omp-20260901\u002Fhermes-agent\u002Foptional-skills\u002Fmcp\u002Ffastmcp\u002FSKILL.md",true,[68,74,80,84,88],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Ffastmcp-cli.md","REFERENCE","参考文档",2359,"https:\u002F\u002Fgithub.com\u002Fyuxua24\u002Fworkspace\u002Fblob\u002Fautoresearch\u002Fpi-agent-merchantbench-net-assets-workspace-omp-20260901\u002Fhermes-agent\u002Foptional-skills\u002Fmcp\u002Ffastmcp\u002Freferences\u002Ffastmcp-cli.md",{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"scripts\u002Fscaffold_fastmcp.py","SCRIPT","脚本",2005,"https:\u002F\u002Fgithub.com\u002Fyuxua24\u002Fworkspace\u002Fblob\u002Fautoresearch\u002Fpi-agent-merchantbench-net-assets-workspace-omp-20260901\u002Fhermes-agent\u002Foptional-skills\u002Fmcp\u002Ffastmcp\u002Fscripts\u002Fscaffold_fastmcp.py",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"templates\u002Fapi_wrapper.py",1608,"https:\u002F\u002Fgithub.com\u002Fyuxua24\u002Fworkspace\u002Fblob\u002Fautoresearch\u002Fpi-agent-merchantbench-net-assets-workspace-omp-20260901\u002Fhermes-agent\u002Foptional-skills\u002Fmcp\u002Ffastmcp\u002Ftemplates\u002Fapi_wrapper.py",{"path":85,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":86,"sourceHtmlUrl":87},"templates\u002Fdatabase_server.py",2238,"https:\u002F\u002Fgithub.com\u002Fyuxua24\u002Fworkspace\u002Fblob\u002Fautoresearch\u002Fpi-agent-merchantbench-net-assets-workspace-omp-20260901\u002Fhermes-agent\u002Foptional-skills\u002Fmcp\u002Ffastmcp\u002Ftemplates\u002Fdatabase_server.py",{"path":89,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":90,"sourceHtmlUrl":91},"templates\u002Ffile_processor.py",1663,"https:\u002F\u002Fgithub.com\u002Fyuxua24\u002Fworkspace\u002Fblob\u002Fautoresearch\u002Fpi-agent-merchantbench-net-assets-workspace-omp-20260901\u002Fhermes-agent\u002Foptional-skills\u002Fmcp\u002Ffastmcp\u002Ftemplates\u002Ffile_processor.py",[93,100,107,114,121,128],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7BXERWENH07XE9XAV53QZ2D","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002Fyuxua24\u002Fworkspace\u002Fblob\u002Fautoresearch\u002Fpi-agent-merchantbench-net-assets-workspace-omp-20260901\u002Fhermes-agent\u002Fskills\u002Fsoftware-development\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7BXEMHAJQA0RVGZ43ZNDFH2","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002Fyuxua24\u002Fworkspace\u002Fblob\u002Fautoresearch\u002Fpi-agent-merchantbench-net-assets-workspace-omp-20260901\u002Fhermes-agent\u002Fskills\u002Fsoftware-development\u002Fsystematic-debugging\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M7BXEGNTY1MJD5W8GSWT7MAP","spike","Throwaway experiments to validate an idea before build.","https:\u002F\u002Fgithub.com\u002Fyuxua24\u002Fworkspace\u002Fblob\u002Fautoresearch\u002Fpi-agent-merchantbench-net-assets-workspace-omp-20260901\u002Fhermes-agent\u002Fskills\u002Fsoftware-development\u002Fspike\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":19},"01M7BXEE77341X1N35WV5CBXAY","simplify-code","Parallel 3-agent cleanup of recent code changes.","https:\u002F\u002Fgithub.com\u002Fyuxua24\u002Fworkspace\u002Fblob\u002Fautoresearch\u002Fpi-agent-merchantbench-net-assets-workspace-omp-20260901\u002Fhermes-agent\u002Fskills\u002Fsoftware-development\u002Fsimplify-code\u002FSKILL.md",[],[],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":19},"01M7BXEASY2T61Y8FRYTXGMKWY","requesting-code-review","Pre-commit review: security scan, quality gates, auto-fix.","https:\u002F\u002Fgithub.com\u002Fyuxua24\u002Fworkspace\u002Fblob\u002Fautoresearch\u002Fpi-agent-merchantbench-net-assets-workspace-omp-20260901\u002Fhermes-agent\u002Fskills\u002Fsoftware-development\u002Frequesting-code-review\u002FSKILL.md",[],[],{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":19},"01M7BXE6H4KWMW0DKVXR5G61E4","python-debugpy","Debug Python: pdb REPL + debugpy remote (DAP).","https:\u002F\u002Fgithub.com\u002Fyuxua24\u002Fworkspace\u002Fblob\u002Fautoresearch\u002Fpi-agent-merchantbench-net-assets-workspace-omp-20260901\u002Fhermes-agent\u002Fskills\u002Fsoftware-development\u002Fpython-debugpy\u002FSKILL.md",[],[]]