[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DCZPTVPRR22DXKY5A0WDXN":3,"skill-same:01M6DCZPTVPRR22DXKY5A0WDXN":77},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":6,"ownerHtmlUrl":60,"ownerBlogUrl":6,"ownerDescription":61,"updatedAt":62,"install":63,"resources":76},"01M6DCZPTVPRR22DXKY5A0WDXN","searxng-search",null,"Free meta-search via SearXNG — aggregates results from 70+ search engines. Self-hosted or use a public instance. No API key needed. Falls back automatically when the web search toolset is unavailable.","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\u002F1f\u002F1f3b9bd83b0d51e65b4f8a2b031bd0dddc792ecbc9d157259ff81345b3f8275c\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"searxng search","search","searxng","use","free","self","domain","aggregates","back","fallback","self-hosted","macos","results","public","hermes","web search","api","Meta","web","linux","2026-11-10 10:12:30",false,"---\r\nname: searxng-search\r\ndescription: Free meta-search via SearXNG — aggregates results from 70+ search engines. Self-hosted or use a public instance. No API key needed. Falls back automatically when the web search toolset is unavailable.\r\nversion: 1.0.0\r\nauthor: hermes-agent\r\nlicense: MIT\r\nplatforms: [linux, macos]\r\nmetadata:\r\n  hermes:\r\n    tags: [search, searxng, meta-search, self-hosted, free, fallback]\r\n    related_skills: [duckduckgo-search, domain-intel]\r\n    fallback_for_toolsets: [web]\r\n---\r\n\r\n# SearXNG Search\r\n\r\nFree meta-search using [SearXNG](https:\u002F\u002Fsearxng.org\u002F) — a privacy-respecting, self-hosted search aggregator that queries 70+ search engines simultaneously.\r\n\r\n**No API key required** when using a public instance. Can also be self-hosted for full control. Automatically appears as a fallback when the main web search toolset (`FIRECRAWL_API_KEY`) is not configured.\r\n\r\n## Configuration\r\n\r\nSearXNG requires a `SEARXNG_URL` environment variable pointing to your SearXNG instance:\r\n\r\n```bash\r\n# Public instances (no setup required)\r\nSEARXNG_URL=https:\u002F\u002Fsearxng.example.com\r\n\r\n# Self-hosted SearXNG\r\nSEARXNG_URL=http:\u002F\u002Flocalhost:8888\r\n```\r\n\r\nIf no instance is configured, this skill is unavailable and the agent falls back to other search options.\r\n\r\n## Detection Flow\r\n\r\nCheck what is actually available before choosing an approach:\r\n\r\n```bash\r\n# Check if SEARXNG_URL is set and the instance is reachable\r\ncurl -s --max-time 5 \"${SEARXNG_URL}\u002Fsearch?q=test&format=json\" | head -c 200\r\n```\r\n\r\nDecision tree:\r\n1. If `SEARXNG_URL` is set and the instance responds, use SearXNG\r\n2. If `SEARXNG_URL` is unset or unreachable, fall back to other available search tools\r\n3. If the user wants SearXNG specifically, help them set up an instance or find a public one\r\n\r\n## Method 1: CLI via curl (Preferred)\r\n\r\nUse `curl` via `terminal` to call the SearXNG JSON API. This avoids assuming any particular Python package is installed.\r\n\r\n```bash\r\n# Text search (JSON output)\r\ncurl -s --max-time 10 \\\r\n  \"${SEARXNG_URL}\u002Fsearch?q=python+async+programming&format=json&engines=google,bing&limit=10\"\r\n\r\n# With Safesearch off\r\ncurl -s --max-time 10 \\\r\n  \"${SEARXNG_URL}\u002Fsearch?q=example&format=json&safesearch=0\"\r\n\r\n# Specific categories (general, news, science, etc.)\r\ncurl -s --max-time 10 \\\r\n  \"${SEARXNG_URL}\u002Fsearch?q=AI+news&format=json&categories=news\"\r\n```\r\n\r\n### Common CLI Flags\r\n\r\n| Flag | Description | Example |\r\n|------|-------------|---------|\r\n| `q` | Query string (URL-encoded) | `q=python+async` |\r\n| `format` | Output format: `json`, `csv`, `rss` | `format=json` |\r\n| `engines` | Comma-separated engine names | `engines=google,bing,ddg` |\r\n| `limit` | Max results per engine (default 10) | `limit=5` |\r\n| `categories` | Filter by category | `categories=news,science` |\r\n| `safesearch` | 0=none, 1=moderate, 2=strict | `safesearch=0` |\r\n| `time_range` | Filter: `day`, `week`, `month`, `year` | `time_range=week` |\r\n\r\n### Parsing JSON Results\r\n\r\n```bash\r\n# Extract titles and URLs from JSON\r\ncurl -s --max-time 10 \"${SEARXNG_URL}\u002Fsearch?q=fastapi&format=json&limit=5\" \\\r\n  | python3 -c \"\r\nimport json, sys\r\ndata = json.load(sys.stdin)\r\nfor r in data.get('results', []):\r\n    print(r.get('title',''))\r\n    print(r.get('url',''))\r\n    print(r.get('content','')[:200])\r\n    print()\r\n\"\r\n```\r\n\r\nReturns per result: `title`, `url`, `content` (snippet), `engine`, `parsed_url`, `img_src`, `thumbnail`, `author`, `published_date`\r\n\r\n## Method 2: Python API via `requests`\r\n\r\nUse the SearXNG REST API directly from Python with the `requests` library:\r\n\r\n```python\r\nimport os, requests, urllib.parse\r\n\r\nbase_url = os.environ.get(\"SEARXNG_URL\", \"\")\r\nif not base_url:\r\n    raise RuntimeError(\"SEARXNG_URL is not set\")\r\n\r\nquery = \"fastapi deployment guide\"\r\nparams = {\r\n    \"q\": query,\r\n    \"format\": \"json\",\r\n    \"limit\": 5,\r\n    \"engines\": \"google,bing\",\r\n}\r\n\r\nresp = requests.get(f\"{base_url}\u002Fsearch\", params=params, timeout=10)\r\nresp.raise_for_status()\r\ndata = resp.json()\r\n\r\nfor r in data.get(\"results\", []):\r\n    print(r[\"title\"])\r\n    print(r[\"url\"])\r\n    print(r.get(\"content\", \"\")[:200])\r\n    print()\r\n```\r\n\r\n## Method 3: searxng-data Python Package\r\n\r\nFor more structured access, install the `searxng-data` package:\r\n\r\n```bash\r\npip install searxng-data\r\n```\r\n\r\n```python\r\nfrom searxng_data import engines\r\n\r\n# List available engines\r\nprint(engines.list_engines())\r\n```\r\n\r\nNote: This package only provides engine metadata, not the search API itself.\r\n\r\n## Self-Hosting SearXNG\r\n\r\nTo run your own SearXNG instance:\r\n\r\n```bash\r\n# Using Docker\r\ndocker run -d -p 8888:8080 \\\r\n  -v $(pwd)\u002Fsearxng:\u002Fetc\u002Fsearxng \\\r\n  searxng\u002Fsearxng:latest\r\n\r\n# Then set\r\nSEARXNG_URL=http:\u002F\u002Flocalhost:8888\r\n```\r\n\r\nOr install via pip:\r\n```bash\r\npip install searxng\r\n# Edit \u002Fetc\u002Fsearxng\u002Fsettings.yml\r\nsearxng-run\r\n```\r\n\r\nPublic SearXNG instances are available at:\r\n- `https:\u002F\u002Fsearxng.example.com` (replace with any public instance)\r\n\r\n## Workflow: Search then Extract\r\n\r\nSearXNG returns titles, URLs, and snippets — not full page content. To get full page content, search first and then extract the most relevant URL with `web_extract`, browser tools, or `curl`.\r\n\r\n```bash\r\n# Search for relevant pages\r\ncurl -s \"${SEARXNG_URL}\u002Fsearch?q=fastapi+deployment&format=json&limit=3\"\r\n# Output: list of results with titles and URLs\r\n\r\n# Then extract the best URL with web_extract\r\n```\r\n\r\n## Limitations\r\n\r\n- **Instance availability**: If the SearXNG instance is down or unreachable, search fails. Always check `SEARXNG_URL` is set and the instance is reachable.\r\n- **No content extraction**: SearXNG returns snippets, not full page content. Use `web_extract`, browser tools, or `curl` for full articles.\r\n- **Rate limiting**: Some public instances limit requests. Self-hosting avoids this.\r\n- **Engine coverage**: Available engines depend on the SearXNG instance configuration. Some engines may be disabled.\r\n- **Results freshness**: Meta-search aggregates external engines — result freshness depends on those engines.\r\n\r\n## Troubleshooting\r\n\r\n| Problem | Likely Cause | What To Do |\r\n|---------|--------------|------------|\r\n| `SEARXNG_URL` not set | No instance configured | Use a public SearXNG instance or set up your own |\r\n| Connection refused | Instance not running or wrong URL | Check the URL is correct and the instance is running |\r\n| Empty results | Instance blocks the query | Try a different instance or self-host |\r\n| Slow responses | Public instance under load | Self-host or use a less-loaded public instance |\r\n| `json` format not supported | Old SearXNG version | Try `format=rss` or upgrade SearXNG |\r\n\r\n## Pitfalls\r\n\r\n- **Always set `SEARXNG_URL`**: Without it, the skill cannot function.\r\n- **URL-encode queries**: Spaces and special characters must be URL-encoded in curl, or use `urllib.parse.quote()` in Python.\r\n- **Use `format=json`**: The default format may not be machine-readable. Always request JSON explicitly.\r\n- **Set a timeout**: Always use `--max-time` or `timeout=` to avoid hanging on unreachable instances.\r\n- **Self-hosting is best**: Public instances may go down, rate-limit, or block. A self-hosted instance is reliable.\r\n\r\n## Instance Discovery\r\n\r\nIf `SEARXNG_URL` is not set and the user asks about SearXNG, help them either:\r\n1. Find a public SearXNG instance (search for \"public searxng instance\")\r\n2. Set up their own with Docker or pip\r\n\r\nPublic instances are listed at: https:\u002F\u002Fsearxng.org\u002F\r\n","# SearXNG Search\r\n\r\nFree meta-search using [SearXNG](https:\u002F\u002Fsearxng.org\u002F) — a privacy-respecting, self-hosted search aggregator that queries 70+ search engines simultaneously.\r\n\r\n**No API key required** when using a public instance. Can also be self-hosted for full control. Automatically appears as a fallback when the main web search toolset (`FIRECRAWL_API_KEY`) is not configured.\r\n\r\n## Configuration\r\n\r\nSearXNG requires a `SEARXNG_URL` environment variable pointing to your SearXNG instance:\r\n\r\n```bash\r\n# Public instances (no setup required)\r\nSEARXNG_URL=https:\u002F\u002Fsearxng.example.com\r\n\r\n# Self-hosted SearXNG\r\nSEARXNG_URL=http:\u002F\u002Flocalhost:8888\r\n```\r\n\r\nIf no instance is configured, this skill is unavailable and the agent falls back to other search options.\r\n\r\n## Detection Flow\r\n\r\nCheck what is actually available before choosing an approach:\r\n\r\n```bash\r\n# Check if SEARXNG_URL is set and the instance is reachable\r\ncurl -s --max-time 5 \"${SEARXNG_URL}\u002Fsearch?q=test&format=json\" | head -c 200\r\n```\r\n\r\nDecision tree:\r\n1. If `SEARXNG_URL` is set and the instance responds, use SearXNG\r\n2. If `SEARXNG_URL` is unset or unreachable, fall back to other available search tools\r\n3. If the user wants SearXNG specifically, help them set up an instance or find a public one\r\n\r\n## Method 1: CLI via curl (Preferred)\r\n\r\nUse `curl` via `terminal` to call the SearXNG JSON API. This avoids assuming any particular Python package is installed.\r\n\r\n```bash\r\n# Text search (JSON output)\r\ncurl -s --max-time 10 \\\r\n  \"${SEARXNG_URL}\u002Fsearch?q=python+async+programming&format=json&engines=google,bing&limit=10\"\r\n\r\n# With Safesearch off\r\ncurl -s --max-time 10 \\\r\n  \"${SEARXNG_URL}\u002Fsearch?q=example&format=json&safesearch=0\"\r\n\r\n# Specific categories (general, news, science, etc.)\r\ncurl -s --max-time 10 \\\r\n  \"${SEARXNG_URL}\u002Fsearch?q=AI+news&format=json&categories=news\"\r\n```\r\n\r\n### Common CLI Flags\r\n\r\n| Flag | Description | Example |\r\n|------|-------------|---------|\r\n| `q` | Query string (URL-encoded) | `q=python+async` |\r\n| `format` | Output format: `json`, `csv`, `rss` | `format=json` |\r\n| `engines` | Comma-separated engine names | `engines=google,bing,ddg` |\r\n| `limit` | Max results per engine (default 10) | `limit=5` |\r\n| `categories` | Filter by category | `categories=news,science` |\r\n| `safesearch` | 0=none, 1=moderate, 2=strict | `safesearch=0` |\r\n| `time_range` | Filter: `day`, `week`, `month`, `year` | `time_range=week` |\r\n\r\n### Parsing JSON Results\r\n\r\n```bash\r\n# Extract titles and URLs from JSON\r\ncurl -s --max-time 10 \"${SEARXNG_URL}\u002Fsearch?q=fastapi&format=json&limit=5\" \\\r\n  | python3 -c \"\r\nimport json, sys\r\ndata = json.load(sys.stdin)\r\nfor r in data.get('results', []):\r\n    print(r.get('title',''))\r\n    print(r.get('url',''))\r\n    print(r.get('content','')[:200])\r\n    print()\r\n\"\r\n```\r\n\r\nReturns per result: `title`, `url`, `content` (snippet), `engine`, `parsed_url`, `img_src`, `thumbnail`, `author`, `published_date`\r\n\r\n## Method 2: Python API via `requests`\r\n\r\nUse the SearXNG REST API directly from Python with the `requests` library:\r\n\r\n```python\r\nimport os, requests, urllib.parse\r\n\r\nbase_url = os.environ.get(\"SEARXNG_URL\", \"\")\r\nif not base_url:\r\n    raise RuntimeError(\"SEARXNG_URL is not set\")\r\n\r\nquery = \"fastapi deployment guide\"\r\nparams = {\r\n    \"q\": query,\r\n    \"format\": \"json\",\r\n    \"limit\": 5,\r\n    \"engines\": \"google,bing\",\r\n}\r\n\r\nresp = requests.get(f\"{base_url}\u002Fsearch\", params=params, timeout=10)\r\nresp.raise_for_status()\r\ndata = resp.json()\r\n\r\nfor r in data.get(\"results\", []):\r\n    print(r[\"title\"])\r\n    print(r[\"url\"])\r\n    print(r.get(\"content\", \"\")[:200])\r\n    print()\r\n```\r\n\r\n## Method 3: searxng-data Python Package\r\n\r\nFor more structured access, install the `searxng-data` package:\r\n\r\n```bash\r\npip install searxng-data\r\n```\r\n\r\n```python\r\nfrom searxng_data import engines\r\n\r\n# List available engines\r\nprint(engines.list_engines())\r\n```\r\n\r\nNote: This package only provides engine metadata, not the search API itself.\r\n\r\n## Self-Hosting SearXNG\r\n\r\nTo run your own SearXNG instance:\r\n\r\n```bash\r\n# Using Docker\r\ndocker run -d -p 8888:8080 \\\r\n  -v $(pwd)\u002Fsearxng:\u002Fetc\u002Fsearxng \\\r\n  searxng\u002Fsearxng:latest\r\n\r\n# Then set\r\nSEARXNG_URL=http:\u002F\u002Flocalhost:8888\r\n```\r\n\r\nOr install via pip:\r\n```bash\r\npip install searxng\r\n# Edit \u002Fetc\u002Fsearxng\u002Fsettings.yml\r\nsearxng-run\r\n```\r\n\r\nPublic SearXNG instances are available at:\r\n- `https:\u002F\u002Fsearxng.example.com` (replace with any public instance)\r\n\r\n## Workflow: Search then Extract\r\n\r\nSearXNG returns titles, URLs, and snippets — not full page content. To get full page content, search first and then extract the most relevant URL with `web_extract`, browser tools, or `curl`.\r\n\r\n```bash\r\n# Search for relevant pages\r\ncurl -s \"${SEARXNG_URL}\u002Fsearch?q=fastapi+deployment&format=json&limit=3\"\r\n# Output: list of results with titles and URLs\r\n\r\n# Then extract the best URL with web_extract\r\n```\r\n\r\n## Limitations\r\n\r\n- **Instance availability**: If the SearXNG instance is down or unreachable, search fails. Always check `SEARXNG_URL` is set and the instance is reachable.\r\n- **No content extraction**: SearXNG returns snippets, not full page content. Use `web_extract`, browser tools, or `curl` for full articles.\r\n- **Rate limiting**: Some public instances limit requests. Self-hosting avoids this.\r\n- **Engine coverage**: Available engines depend on the SearXNG instance configuration. Some engines may be disabled.\r\n- **Results freshness**: Meta-search aggregates external engines — result freshness depends on those engines.\r\n\r\n## Troubleshooting\r\n\r\n| Problem | Likely Cause | What To Do |\r\n|---------|--------------|------------|\r\n| `SEARXNG_URL` not set | No instance configured | Use a public SearXNG instance or set up your own |\r\n| Connection refused | Instance not running or wrong URL | Check the URL is correct and the instance is running |\r\n| Empty results | Instance blocks the query | Try a different instance or self-host |\r\n| Slow responses | Public instance under load | Self-host or use a less-loaded public instance |\r\n| `json` format not supported | Old SearXNG version | Try `format=rss` or upgrade SearXNG |\r\n\r\n## Pitfalls\r\n\r\n- **Always set `SEARXNG_URL`**: Without it, the skill cannot function.\r\n- **URL-encode queries**: Spaces and special characters must be URL-encoded in curl, or use `urllib.parse.quote()` in Python.\r\n- **Use `format=json`**: The default format may not be machine-readable. Always request JSON explicitly.\r\n- **Set a timeout**: Always use `--max-time` or `timeout=` to avoid hanging on unreachable instances.\r\n- **Self-hosting is best**: Public instances may go down, rate-limit, or block. A self-hosted instance is reliable.\r\n\r\n## Instance Discovery\r\n\r\nIf `SEARXNG_URL` is not set and the user asks about SearXNG, help them either:\r\n1. Find a public SearXNG instance (search for \"public searxng instance\")\r\n2. Set up their own with Docker or pip\r\n\r\nPublic instances are listed at: https:\u002F\u002Fsearxng.org\u002F\r\n",{"name":5,"author":44,"license":15,"version":45,"metadata":46,"platforms":54,"description":7},"hermes-agent","1.0.0",{"hermes":47},{"tags":48,"related_skills":50,"fallback_for_toolsets":53},[20,21,49,29,23,28],"meta-search",[51,52],"duckduckgo-search","domain-intel",[37],[38,30],"main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002F1f\u002F1f3b9bd83b0d51e65b4f8a2b031bd0dddc792ecbc9d157259ff81345b3f8275c",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":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add zapabob\u002FSkills --skill searxng-search",{"tool":69,"command":70},"bunx","bunx skills add zapabob\u002FSkills --skill searxng-search",{"tool":72,"command":73},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill searxng-search","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F1f\u002F1f3b9bd83b0d51e65b4f8a2b031bd0dddc792ecbc9d157259ff81345b3f8275c\u002FSKILL.md",true,[],[78,111,146,172,199,216],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":97,"publishedAt":39},"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",[84,89,92],{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":90,"categoryName":91,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":93,"categoryName":94,"taxonomyType":95,"taxonomyTypeDesc":96},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[80,98,30,99,100,38,101,102,20,103,104,35,105,33,106,107,55,108,109,110],"openclaw","cli","github","windows","official","https","social-media","Media","hermes agent","twitter","social","via","post",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":128,"publishedAt":39},"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",[117,120,123,124,125],{"categoryNo":118,"categoryName":119,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":121,"categoryName":122,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":90,"categoryName":91,"taxonomyType":87,"taxonomyTypeDesc":88},{"categoryNo":93,"categoryName":94,"taxonomyType":95,"taxonomyTypeDesc":96},{"categoryNo":126,"categoryName":127,"taxonomyType":95,"taxonomyTypeDesc":96},"01JBSEEDCAT000000000000036","内容创作者",[129,130,131,132,30,133,38,134,101,135,136,137,138,139,140,141,142,143,144,145],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":155,"publishedAt":39},"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",[152],{"categoryNo":153,"categoryName":154,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000016","图像与多媒体",[148,30,38,156,157,158,159,160,161,162,163,164,22,165,166,167,168,169,170,171],"openai","speech","multimodal","Transformers","ASR","Audio","text","model","speech recognition","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":181,"publishedAt":39},"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",[178],{"categoryNo":179,"categoryName":180,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000013","分析与可视化",[182,30,183,184,101,185,186,187,188,189,190,163,191,192,193,194,195,196,197,198],"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":200,"name":201,"nameZh":6,"description":202,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":203,"categories":204,"keywords":206,"publishedAt":39},"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",[205],{"categoryNo":90,"categoryName":91,"taxonomyType":87,"taxonomyTypeDesc":88},[201,30,207,100,38,208,209,210,211,212,213,33,106,214,215],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":217,"name":218,"nameZh":6,"description":219,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":220,"categories":221,"keywords":224,"publishedAt":39},"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",[222,223],{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},{"categoryNo":93,"categoryName":94,"taxonomyType":95,"taxonomyTypeDesc":96},[225,226,227,38,228,156,229,230,231,159,232,35,233,234,235,236,237,238,239,240],"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"]