[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6G9Z760RDZ2WBQNJPRS8QKB":3,"skill-same:01M6G9Z760RDZ2WBQNJPRS8QKB":98},{"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":34,"publishedAt":54,"linkOnly":55,"markdownContent":56,"markdownBody":57,"frontMatter":58,"refName":76,"commitSha":77,"skillDirectory":78,"forksCount":79,"repositoryHtmlUrl":80,"repositoryHomepageUrl":6,"ownerHtmlUrl":81,"ownerBlogUrl":6,"ownerDescription":82,"updatedAt":83,"install":84,"resources":97},"01M6G9Z760RDZ2WBQNJPRS8QKB","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, Codex, or HTTP deployment.","zapabob\u002FSkills","zapabob","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130830376?v=4","01M6DBMYZAGRTFQDSQYW3W764P","峯岸 亮","01M6DBMZ3GKDSJ01NZ9XTZD7JD",2,"MIT","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F81\u002F81bcf70ee61de81c5fb9c45aa11e820561f124391d89fc3c8ea09ca746c4e71a\u002FSKILL.md",[18,23,26,29],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":30,"categoryName":31,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[5,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53],"server","native","resources","as","use","install","python3","api","fastmcp server","Tools","MCP","database","code","deployment","windows","mcp server","linux","python","macos","2026-11-10 10:12:30",false,"---\r\nname: fastmcp\r\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, Codex, or HTTP deployment.\r\nversion: 1.0.0\r\nauthor: Hermes Agent\r\nlicense: MIT\r\nplatforms: [linux, macos, windows]\r\nmetadata:\r\n  hermes:\r\n    tags: [MCP, FastMCP, Python, Tools, Resources, Prompts, Deployment]\r\n    homepage: https:\u002F\u002Fgofastmcp.com\r\n    related_skills: [native-mcp, mcporter]\r\nprerequisites:\r\n  commands: [python3]\r\n---\r\n\r\n# FastMCP\r\n\r\nBuild MCP servers in Python with FastMCP, validate them locally, install them into MCP clients, and deploy them as HTTP endpoints.\r\n\r\n## When to Use\r\n\r\nUse this skill when the task is to:\r\n\r\n- create a new MCP server in Python\r\n- wrap an API, database, CLI, or file-processing workflow as MCP tools\r\n- expose resources or prompts in addition to tools\r\n- smoke-test a server with the FastMCP CLI before wiring it into Hermes or another client\r\n- install a server into Claude Code, Claude Desktop, Codex, or a similar MCP client\r\n- prepare a FastMCP server repo for HTTP deployment\r\n\r\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.\r\n\r\n## Prerequisites\r\n\r\nInstall FastMCP in the working environment first:\r\n\r\n```bash\r\npip install fastmcp\r\nfastmcp version\r\n```\r\n\r\nFor the API template, install `httpx` if it is not already present:\r\n\r\n```bash\r\npip install httpx\r\n```\r\n\r\n## Included Files\r\n\r\n### Templates\r\n\r\n- `templates\u002Fapi_wrapper.py` - REST API wrapper with auth header support\r\n- `templates\u002Fdatabase_server.py` - read-only SQLite query server\r\n- `templates\u002Ffile_processor.py` - text-file inspection and search server\r\n\r\n### Scripts\r\n\r\n- `scripts\u002Fscaffold_fastmcp.py` - copy a starter template and replace the server name placeholder\r\n\r\n### References\r\n\r\n- `references\u002Ffastmcp-cli.md` - FastMCP CLI workflow, installation targets, and deployment checks\r\n\r\n## Workflow\r\n\r\n### 1. Pick the Smallest Viable Server Shape\r\n\r\nChoose the narrowest useful surface area first:\r\n\r\n- API wrapper: start with 1-3 high-value endpoints, not the whole API\r\n- database server: expose read-only introspection and a constrained query path\r\n- file processor: expose deterministic operations with explicit path arguments\r\n- prompts\u002Fresources: add only when the client needs reusable prompt templates or discoverable documents\r\n\r\nPrefer a thin server with good names, docstrings, and schemas over a large server with vague tools.\r\n\r\n### 2. Scaffold from a Template\r\n\r\nCopy a template directly or use the scaffold helper:\r\n\r\n```bash\r\npython ~\u002F.hermes\u002Fskills\u002Fmcp\u002Ffastmcp\u002Fscripts\u002Fscaffold_fastmcp.py \\\r\n  --template api_wrapper \\\r\n  --name \"Acme API\" \\\r\n  --output .\u002Facme_server.py\r\n```\r\n\r\nAvailable templates:\r\n\r\n```bash\r\npython ~\u002F.hermes\u002Fskills\u002Fmcp\u002Ffastmcp\u002Fscripts\u002Fscaffold_fastmcp.py --list\r\n```\r\n\r\nIf copying manually, replace `__SERVER_NAME__` with a real server name.\r\n\r\n### 3. Implement Tools First\r\n\r\nStart with `@mcp.tool` functions before adding resources or prompts.\r\n\r\nRules for tool design:\r\n\r\n- Give every tool a concrete verb-based name\r\n- Write docstrings as user-facing tool descriptions\r\n- Keep parameters explicit and typed\r\n- Return structured JSON-safe data where possible\r\n- Validate unsafe inputs early\r\n- Prefer read-only behavior by default for first versions\r\n\r\nGood tool examples:\r\n\r\n- `get_customer`\r\n- `search_tickets`\r\n- `describe_table`\r\n- `summarize_text_file`\r\n\r\nWeak tool examples:\r\n\r\n- `run`\r\n- `process`\r\n- `do_thing`\r\n\r\n### 4. Add Resources and Prompts Only When They Help\r\n\r\nAdd `@mcp.resource` when the client benefits from fetching stable read-only content such as schemas, policy docs, or generated reports.\r\n\r\nAdd `@mcp.prompt` when the server should provide a reusable prompt template for a known workflow.\r\n\r\nDo not turn every document into a prompt. Prefer:\r\n\r\n- tools for actions\r\n- resources for data\u002Fdocument retrieval\r\n- prompts for reusable LLM instructions\r\n\r\n### 5. Test the Server Before Integrating It Anywhere\r\n\r\nUse the FastMCP CLI for local validation:\r\n\r\n```bash\r\nfastmcp inspect acme_server.py:mcp\r\nfastmcp list acme_server.py --json\r\nfastmcp call acme_server.py search_resources query=router limit=5 --json\r\n```\r\n\r\nFor fast iterative debugging, run the server locally:\r\n\r\n```bash\r\nfastmcp run acme_server.py:mcp\r\n```\r\n\r\nTo test HTTP transport locally:\r\n\r\n```bash\r\nfastmcp run acme_server.py:mcp --transport http --host 127.0.0.1 --port 8000\r\nfastmcp list http:\u002F\u002F127.0.0.1:8000\u002Fmcp --json\r\nfastmcp call http:\u002F\u002F127.0.0.1:8000\u002Fmcp search_resources query=router --json\r\n```\r\n\r\nAlways run at least one real `fastmcp call` against each new tool before claiming the server works.\r\n\r\n### 6. Install into a Client When Local Validation Passes\r\n\r\nFastMCP can register the server with supported MCP clients:\r\n\r\n```bash\r\nfastmcp install claude-code acme_server.py\r\nfastmcp install claude-desktop acme_server.py\r\nfastmcp install cursor acme_server.py -e .\r\n```\r\n\r\nUse `fastmcp discover` to inspect named MCP servers already configured on the machine.\r\n\r\nWhen the goal is Hermes integration, either:\r\n\r\n- configure the server in `~\u002F.hermes\u002Fconfig.yaml` using the `native-mcp` skill, or\r\n- keep using FastMCP CLI commands during development until the interface stabilizes\r\n\r\n### 7. Deploy After the Local Contract Is Stable\r\n\r\nFor managed hosting, Prefect Horizon is the path FastMCP documents most directly. Before deployment:\r\n\r\n```bash\r\nfastmcp inspect acme_server.py:mcp\r\n```\r\n\r\nMake sure the repo contains:\r\n\r\n- a Python file with the FastMCP server object\r\n- `requirements.txt` or `pyproject.toml`\r\n- any environment-variable documentation needed for deployment\r\n\r\nFor generic HTTP hosting, validate the HTTP transport locally first, then deploy on any Python-compatible platform that can expose the server port.\r\n\r\n## Common Patterns\r\n\r\n### API Wrapper Pattern\r\n\r\nUse when exposing a REST or HTTP API as MCP tools.\r\n\r\nRecommended first slice:\r\n\r\n- one read path\r\n- one list\u002Fsearch path\r\n- optional health check\r\n\r\nImplementation notes:\r\n\r\n- keep auth in environment variables, not hardcoded\r\n- centralize request logic in one helper\r\n- surface API errors with concise context\r\n- normalize inconsistent upstream payloads before returning them\r\n\r\nStart from `templates\u002Fapi_wrapper.py`.\r\n\r\n### Database Pattern\r\n\r\nUse when exposing safe query and inspection capabilities.\r\n\r\nRecommended first slice:\r\n\r\n- `list_tables`\r\n- `describe_table`\r\n- one constrained read query tool\r\n\r\nImplementation notes:\r\n\r\n- default to read-only DB access\r\n- reject non-`SELECT` SQL in early versions\r\n- limit row counts\r\n- return rows plus column names\r\n\r\nStart from `templates\u002Fdatabase_server.py`.\r\n\r\n### File Processor Pattern\r\n\r\nUse when the server needs to inspect or transform files on demand.\r\n\r\nRecommended first slice:\r\n\r\n- summarize file contents\r\n- search within files\r\n- extract deterministic metadata\r\n\r\nImplementation notes:\r\n\r\n- accept explicit file paths\r\n- check for missing files and encoding failures\r\n- cap previews and result counts\r\n- avoid shelling out unless a specific external tool is required\r\n\r\nStart from `templates\u002Ffile_processor.py`.\r\n\r\n## Quality Bar\r\n\r\nBefore handing off a FastMCP server, verify all of the following:\r\n\r\n- server imports cleanly\r\n- `fastmcp inspect \u003Cfile.py:mcp>` succeeds\r\n- `fastmcp list \u003Cserver spec> --json` succeeds\r\n- every new tool has at least one real `fastmcp call`\r\n- environment variables are documented\r\n- the tool surface is small enough to understand without guesswork\r\n\r\n## Troubleshooting\r\n\r\n### FastMCP command missing\r\n\r\nInstall the package in the active environment:\r\n\r\n```bash\r\npip install fastmcp\r\nfastmcp version\r\n```\r\n\r\n### `fastmcp inspect` fails\r\n\r\nCheck that:\r\n\r\n- the file imports without side effects that crash\r\n- the FastMCP instance is named correctly in `\u003Cfile.py:object>`\r\n- optional dependencies from the template are installed\r\n\r\n### Tool works in Python but not through CLI\r\n\r\nRun:\r\n\r\n```bash\r\nfastmcp list server.py --json\r\nfastmcp call server.py your_tool_name --json\r\n```\r\n\r\nThis usually exposes naming mismatches, missing required arguments, or non-serializable return values.\r\n\r\n### Hermes cannot see the deployed server\r\n\r\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.\r\n\r\n## References\r\n\r\nFor CLI details, install targets, and deployment checks, read `references\u002Ffastmcp-cli.md`.\r\n","# FastMCP\r\n\r\nBuild MCP servers in Python with FastMCP, validate them locally, install them into MCP clients, and deploy them as HTTP endpoints.\r\n\r\n## When to Use\r\n\r\nUse this skill when the task is to:\r\n\r\n- create a new MCP server in Python\r\n- wrap an API, database, CLI, or file-processing workflow as MCP tools\r\n- expose resources or prompts in addition to tools\r\n- smoke-test a server with the FastMCP CLI before wiring it into Hermes or another client\r\n- install a server into Claude Code, Claude Desktop, Codex, or a similar MCP client\r\n- prepare a FastMCP server repo for HTTP deployment\r\n\r\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.\r\n\r\n## Prerequisites\r\n\r\nInstall FastMCP in the working environment first:\r\n\r\n```bash\r\npip install fastmcp\r\nfastmcp version\r\n```\r\n\r\nFor the API template, install `httpx` if it is not already present:\r\n\r\n```bash\r\npip install httpx\r\n```\r\n\r\n## Included Files\r\n\r\n### Templates\r\n\r\n- `templates\u002Fapi_wrapper.py` - REST API wrapper with auth header support\r\n- `templates\u002Fdatabase_server.py` - read-only SQLite query server\r\n- `templates\u002Ffile_processor.py` - text-file inspection and search server\r\n\r\n### Scripts\r\n\r\n- `scripts\u002Fscaffold_fastmcp.py` - copy a starter template and replace the server name placeholder\r\n\r\n### References\r\n\r\n- `references\u002Ffastmcp-cli.md` - FastMCP CLI workflow, installation targets, and deployment checks\r\n\r\n## Workflow\r\n\r\n### 1. Pick the Smallest Viable Server Shape\r\n\r\nChoose the narrowest useful surface area first:\r\n\r\n- API wrapper: start with 1-3 high-value endpoints, not the whole API\r\n- database server: expose read-only introspection and a constrained query path\r\n- file processor: expose deterministic operations with explicit path arguments\r\n- prompts\u002Fresources: add only when the client needs reusable prompt templates or discoverable documents\r\n\r\nPrefer a thin server with good names, docstrings, and schemas over a large server with vague tools.\r\n\r\n### 2. Scaffold from a Template\r\n\r\nCopy a template directly or use the scaffold helper:\r\n\r\n```bash\r\npython ~\u002F.hermes\u002Fskills\u002Fmcp\u002Ffastmcp\u002Fscripts\u002Fscaffold_fastmcp.py \\\r\n  --template api_wrapper \\\r\n  --name \"Acme API\" \\\r\n  --output .\u002Facme_server.py\r\n```\r\n\r\nAvailable templates:\r\n\r\n```bash\r\npython ~\u002F.hermes\u002Fskills\u002Fmcp\u002Ffastmcp\u002Fscripts\u002Fscaffold_fastmcp.py --list\r\n```\r\n\r\nIf copying manually, replace `__SERVER_NAME__` with a real server name.\r\n\r\n### 3. Implement Tools First\r\n\r\nStart with `@mcp.tool` functions before adding resources or prompts.\r\n\r\nRules for tool design:\r\n\r\n- Give every tool a concrete verb-based name\r\n- Write docstrings as user-facing tool descriptions\r\n- Keep parameters explicit and typed\r\n- Return structured JSON-safe data where possible\r\n- Validate unsafe inputs early\r\n- Prefer read-only behavior by default for first versions\r\n\r\nGood tool examples:\r\n\r\n- `get_customer`\r\n- `search_tickets`\r\n- `describe_table`\r\n- `summarize_text_file`\r\n\r\nWeak tool examples:\r\n\r\n- `run`\r\n- `process`\r\n- `do_thing`\r\n\r\n### 4. Add Resources and Prompts Only When They Help\r\n\r\nAdd `@mcp.resource` when the client benefits from fetching stable read-only content such as schemas, policy docs, or generated reports.\r\n\r\nAdd `@mcp.prompt` when the server should provide a reusable prompt template for a known workflow.\r\n\r\nDo not turn every document into a prompt. Prefer:\r\n\r\n- tools for actions\r\n- resources for data\u002Fdocument retrieval\r\n- prompts for reusable LLM instructions\r\n\r\n### 5. Test the Server Before Integrating It Anywhere\r\n\r\nUse the FastMCP CLI for local validation:\r\n\r\n```bash\r\nfastmcp inspect acme_server.py:mcp\r\nfastmcp list acme_server.py --json\r\nfastmcp call acme_server.py search_resources query=router limit=5 --json\r\n```\r\n\r\nFor fast iterative debugging, run the server locally:\r\n\r\n```bash\r\nfastmcp run acme_server.py:mcp\r\n```\r\n\r\nTo test HTTP transport locally:\r\n\r\n```bash\r\nfastmcp run acme_server.py:mcp --transport http --host 127.0.0.1 --port 8000\r\nfastmcp list http:\u002F\u002F127.0.0.1:8000\u002Fmcp --json\r\nfastmcp call http:\u002F\u002F127.0.0.1:8000\u002Fmcp search_resources query=router --json\r\n```\r\n\r\nAlways run at least one real `fastmcp call` against each new tool before claiming the server works.\r\n\r\n### 6. Install into a Client When Local Validation Passes\r\n\r\nFastMCP can register the server with supported MCP clients:\r\n\r\n```bash\r\nfastmcp install claude-code acme_server.py\r\nfastmcp install claude-desktop acme_server.py\r\nfastmcp install cursor acme_server.py -e .\r\n```\r\n\r\nUse `fastmcp discover` to inspect named MCP servers already configured on the machine.\r\n\r\nWhen the goal is Hermes integration, either:\r\n\r\n- configure the server in `~\u002F.hermes\u002Fconfig.yaml` using the `native-mcp` skill, or\r\n- keep using FastMCP CLI commands during development until the interface stabilizes\r\n\r\n### 7. Deploy After the Local Contract Is Stable\r\n\r\nFor managed hosting, Prefect Horizon is the path FastMCP documents most directly. Before deployment:\r\n\r\n```bash\r\nfastmcp inspect acme_server.py:mcp\r\n```\r\n\r\nMake sure the repo contains:\r\n\r\n- a Python file with the FastMCP server object\r\n- `requirements.txt` or `pyproject.toml`\r\n- any environment-variable documentation needed for deployment\r\n\r\nFor generic HTTP hosting, validate the HTTP transport locally first, then deploy on any Python-compatible platform that can expose the server port.\r\n\r\n## Common Patterns\r\n\r\n### API Wrapper Pattern\r\n\r\nUse when exposing a REST or HTTP API as MCP tools.\r\n\r\nRecommended first slice:\r\n\r\n- one read path\r\n- one list\u002Fsearch path\r\n- optional health check\r\n\r\nImplementation notes:\r\n\r\n- keep auth in environment variables, not hardcoded\r\n- centralize request logic in one helper\r\n- surface API errors with concise context\r\n- normalize inconsistent upstream payloads before returning them\r\n\r\nStart from `templates\u002Fapi_wrapper.py`.\r\n\r\n### Database Pattern\r\n\r\nUse when exposing safe query and inspection capabilities.\r\n\r\nRecommended first slice:\r\n\r\n- `list_tables`\r\n- `describe_table`\r\n- one constrained read query tool\r\n\r\nImplementation notes:\r\n\r\n- default to read-only DB access\r\n- reject non-`SELECT` SQL in early versions\r\n- limit row counts\r\n- return rows plus column names\r\n\r\nStart from `templates\u002Fdatabase_server.py`.\r\n\r\n### File Processor Pattern\r\n\r\nUse when the server needs to inspect or transform files on demand.\r\n\r\nRecommended first slice:\r\n\r\n- summarize file contents\r\n- search within files\r\n- extract deterministic metadata\r\n\r\nImplementation notes:\r\n\r\n- accept explicit file paths\r\n- check for missing files and encoding failures\r\n- cap previews and result counts\r\n- avoid shelling out unless a specific external tool is required\r\n\r\nStart from `templates\u002Ffile_processor.py`.\r\n\r\n## Quality Bar\r\n\r\nBefore handing off a FastMCP server, verify all of the following:\r\n\r\n- server imports cleanly\r\n- `fastmcp inspect \u003Cfile.py:mcp>` succeeds\r\n- `fastmcp list \u003Cserver spec> --json` succeeds\r\n- every new tool has at least one real `fastmcp call`\r\n- environment variables are documented\r\n- the tool surface is small enough to understand without guesswork\r\n\r\n## Troubleshooting\r\n\r\n### FastMCP command missing\r\n\r\nInstall the package in the active environment:\r\n\r\n```bash\r\npip install fastmcp\r\nfastmcp version\r\n```\r\n\r\n### `fastmcp inspect` fails\r\n\r\nCheck that:\r\n\r\n- the file imports without side effects that crash\r\n- the FastMCP instance is named correctly in `\u003Cfile.py:object>`\r\n- optional dependencies from the template are installed\r\n\r\n### Tool works in Python but not through CLI\r\n\r\nRun:\r\n\r\n```bash\r\nfastmcp list server.py --json\r\nfastmcp call server.py your_tool_name --json\r\n```\r\n\r\nThis usually exposes naming mismatches, missing required arguments, or non-serializable return values.\r\n\r\n### Hermes cannot see the deployed server\r\n\r\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.\r\n\r\n## References\r\n\r\nFor CLI details, install targets, and deployment checks, read `references\u002Ffastmcp-cli.md`.\r\n",{"name":5,"author":59,"license":15,"version":60,"metadata":61,"platforms":73,"description":7,"prerequisites":74},"Hermes Agent","1.0.0",{"hermes":62},{"tags":63,"homepage":69,"related_skills":70},[45,64,65,44,66,67,68],"FastMCP","Python","Resources","Prompts","Deployment","https:\u002F\u002Fgofastmcp.com",[71,72],"native-mcp","mcporter",[51,53,49],{"commands":75},[41],"main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002F81\u002F81bcf70ee61de81c5fb9c45aa11e820561f124391d89fc3c8ea09ca746c4e71a",0,"https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills","https:\u002F\u002Fgithub.com\u002Fzapabob","The Open University of JAPAN　2019-now\r\n\r\nTokyo University of Science　2007-2010","2026-10-26 16:29:01",{"source":8,"skillName":5,"commands":85,"prompt":95,"zipAvailable":96},[86,89,92],{"tool":87,"command":88},"npx","npx skills add zapabob\u002FSkills --skill fastmcp",{"tool":90,"command":91},"bunx","bunx skills add zapabob\u002FSkills --skill fastmcp",{"tool":93,"command":94},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill fastmcp","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F81\u002F81bcf70ee61de81c5fb9c45aa11e820561f124391d89fc3c8ea09ca746c4e71a\u002FSKILL.md",true,[],[99,123,157,183,210,227],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":108,"publishedAt":54},"01M6GJTE1GESGGF9K028Y7753E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fxurl\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[105,106,107],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":30,"categoryName":31,"taxonomyType":32,"taxonomyTypeDesc":33},[101,109,53,110,111,51,49,112,113,114,115,42,116,117,118,119,76,120,121,122],"openclaw","cli","github","official","search","https","social-media","Media","hermes","hermes agent","twitter","social","via","post",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":140,"publishedAt":54},"01M6GJT8S1PXQ8WPXT1HSNBWH2","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwriting-plans\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[129,132,135,136,137],{"categoryNo":130,"categoryName":131,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":133,"categoryName":134,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":30,"categoryName":31,"taxonomyType":32,"taxonomyTypeDesc":33},{"categoryNo":138,"categoryName":139,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000036","内容创作者",[141,142,143,144,53,145,51,146,49,147,148,149,47,150,151,152,153,154,155,156],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":166,"publishedAt":54},"01M6GJST0H5X7WHBJ3BZK0DVKH","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwhisper\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[163],{"categoryNo":164,"categoryName":165,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[159,53,51,167,168,169,170,171,172,173,174,175,39,176,177,178,179,180,181,182],"openai","speech","multimodal","Transformers","ASR","Audio","text","model","speech recognition","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":192,"publishedAt":54},"01M6GJSMRQ8EETZTYMG72P70EA","weights-and-biases","W&B: log ML experiments, sweeps, model registry, dashboards.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fweights-and-biases\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[189],{"categoryNo":190,"categoryName":191,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",[193,53,194,195,49,196,197,198,199,200,201,174,202,203,204,205,206,207,208,209],"weights and biases","tensorflow","experiments","pytorch","visualization","registry","real-time","tuning","dashboards","experiment","log","time","Experiment Tracking","Model Registry","Hyperparameter Tuning","WandB","Real-Time Visualization",{"skillNo":211,"name":212,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":214,"categories":215,"keywords":217,"publishedAt":54},"01M6GJS19KDPRY112JTR326S06","watchers","Poll RSS, JSON APIs, and GitHub with watermark dedup.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwatchers\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[216],{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[212,53,218,111,51,219,220,221,222,223,224,117,118,225,226],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":228,"name":229,"nameZh":6,"description":230,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":231,"categories":232,"keywords":235,"publishedAt":54},"01M6GJRHJD2A6Q830SWF9W48BC","serving-llms-vllm","vLLM: high-throughput LLM serving, OpenAI API, quantization.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fvllm\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[233,234],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":30,"categoryName":31,"taxonomyType":32,"taxonomyTypeDesc":33},[236,237,238,51,239,167,240,241,242,170,243,42,244,245,246,247,248,249,250,251],"llms","vLLM","serving llms vllm","research","openai api","tensor","Inference Serving","Production","llm serving","High Throughput","PagedAttention","Continuous Batching","Quantization","Tensor Parallelism","high-throughput","throughput"]