[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GA54VRCHV550M3AYZWW7C3":3,"skill-same:01M6GA54VRCHV550M3AYZWW7C3":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},"01M6GA54VRCHV550M3AYZWW7C3","duckduckgo-search",null,"Free web search via DuckDuckGo — text, news, images, videos. No API key needed. Prefer the `ddgs` CLI when installed; use the Python DDGS library only after verifying that `ddgs` is available in the current runtime.","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\u002F84\u002F84df053425ab0fec30e7217f02aebe4c58cd18c90d91e44e3a97ad798e7cb5f1\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"duckduckgo","search","duckduckgo search","only","videos","via","free","runtime","news","web-search","images","cli","use","text","web search","api","windows","web","linux","python","2026-11-10 10:12:30",false,"---\r\nname: duckduckgo-search\r\ndescription: Free web search via DuckDuckGo — text, news, images, videos. No API key needed. Prefer the `ddgs` CLI when installed; use the Python DDGS library only after verifying that `ddgs` is available in the current runtime.\r\nversion: 1.3.0\r\nauthor: gamedevCloudy\r\nlicense: MIT\r\nplatforms: [linux, macos, windows]\r\nmetadata:\r\n  hermes:\r\n    tags: [search, duckduckgo, web-search, free, fallback]\r\n    related_skills: [arxiv]\r\n    fallback_for_toolsets: [web]\r\n---\r\n\r\n# DuckDuckGo Search\r\n\r\nFree web search using DuckDuckGo. **No API key required.**\r\n\r\nPreferred when `web_search` is unavailable or unsuitable (for example when `FIRECRAWL_API_KEY` is not set). Can also be used as a standalone search path when DuckDuckGo results are specifically desired.\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 CLI availability\r\ncommand -v ddgs >\u002Fdev\u002Fnull && echo \"DDGS_CLI=installed\" || echo \"DDGS_CLI=missing\"\r\n```\r\n\r\nDecision tree:\r\n1. If `ddgs` CLI is installed, prefer `terminal` + `ddgs`\r\n2. If `ddgs` CLI is missing, do not assume `execute_code` can import `ddgs`\r\n3. If the user wants DuckDuckGo specifically, install `ddgs` first in the relevant environment\r\n4. Otherwise fall back to built-in web\u002Fbrowser tools\r\n\r\nImportant runtime note:\r\n- Terminal and `execute_code` are separate runtimes\r\n- A successful shell install does not guarantee `execute_code` can import `ddgs`\r\n- Never assume third-party Python packages are preinstalled inside `execute_code`\r\n\r\n## Installation\r\n\r\nInstall `ddgs` only when DuckDuckGo search is specifically needed and the runtime does not already provide it.\r\n\r\n```bash\r\n# Python package + CLI entrypoint\r\npip install ddgs\r\n\r\n# Verify CLI\r\nddgs --help\r\n```\r\n\r\nIf a workflow depends on Python imports, verify that same runtime can import `ddgs` before using `from ddgs import DDGS`.\r\n\r\n## Method 1: CLI Search (Preferred)\r\n\r\nUse the `ddgs` command via `terminal` when it exists. This is the preferred path because it avoids assuming the `execute_code` sandbox has the `ddgs` Python package installed.\r\n\r\n```bash\r\n# Text search\r\nddgs text -q \"python async programming\" -m 5\r\n\r\n# News search\r\nddgs news -q \"artificial intelligence\" -m 5\r\n\r\n# Image search\r\nddgs images -q \"landscape photography\" -m 10\r\n\r\n# Video search\r\nddgs videos -q \"python tutorial\" -m 5\r\n\r\n# With region filter\r\nddgs text -q \"best restaurants\" -m 5 -r us-en\r\n\r\n# Recent results only (d=day, w=week, m=month, y=year)\r\nddgs text -q \"latest AI news\" -m 5 -t w\r\n\r\n# JSON output for parsing\r\nddgs text -q \"fastapi tutorial\" -m 5 -o json\r\n```\r\n\r\n### CLI Flags\r\n\r\n| Flag | Description | Example |\r\n|------|-------------|---------|\r\n| `-q` | Query — **required** | `-q \"search terms\"` |\r\n| `-m` | Max results | `-m 5` |\r\n| `-r` | Region | `-r us-en` |\r\n| `-t` | Time limit | `-t w` (week) |\r\n| `-s` | Safe search | `-s off` |\r\n| `-o` | Output format | `-o json` |\r\n\r\n## Method 2: Python API (Only After Verification)\r\n\r\nUse the `DDGS` class in `execute_code` or another Python runtime only after verifying that `ddgs` is installed there. Do not assume `execute_code` includes third-party packages by default.\r\n\r\nSafe wording:\r\n- \"Use `execute_code` with `ddgs` after installing or verifying the package if needed\"\r\n\r\nAvoid saying:\r\n- \"`execute_code` includes `ddgs`\"\r\n- \"DuckDuckGo search works by default in `execute_code`\"\r\n\r\n**Important:** `max_results` must always be passed as a **keyword argument** — positional usage raises an error on all methods.\r\n\r\n### Text Search\r\n\r\nBest for: general research, companies, documentation.\r\n\r\n```python\r\nfrom ddgs import DDGS\r\n\r\nwith DDGS() as ddgs:\r\n    for r in ddgs.text(\"python async programming\", max_results=5):\r\n        print(r[\"title\"])\r\n        print(r[\"href\"])\r\n        print(r.get(\"body\", \"\")[:200])\r\n        print()\r\n```\r\n\r\nReturns: `title`, `href`, `body`\r\n\r\n### News Search\r\n\r\nBest for: current events, breaking news, latest updates.\r\n\r\n```python\r\nfrom ddgs import DDGS\r\n\r\nwith DDGS() as ddgs:\r\n    for r in ddgs.news(\"AI regulation 2026\", max_results=5):\r\n        print(r[\"date\"], \"-\", r[\"title\"])\r\n        print(r.get(\"source\", \"\"), \"|\", r[\"url\"])\r\n        print(r.get(\"body\", \"\")[:200])\r\n        print()\r\n```\r\n\r\nReturns: `date`, `title`, `body`, `url`, `image`, `source`\r\n\r\n### Image Search\r\n\r\nBest for: visual references, product images, diagrams.\r\n\r\n```python\r\nfrom ddgs import DDGS\r\n\r\nwith DDGS() as ddgs:\r\n    for r in ddgs.images(\"semiconductor chip\", max_results=5):\r\n        print(r[\"title\"])\r\n        print(r[\"image\"])\r\n        print(r.get(\"thumbnail\", \"\"))\r\n        print(r.get(\"source\", \"\"))\r\n        print()\r\n```\r\n\r\nReturns: `title`, `image`, `thumbnail`, `url`, `height`, `width`, `source`\r\n\r\n### Video Search\r\n\r\nBest for: tutorials, demos, explainers.\r\n\r\n```python\r\nfrom ddgs import DDGS\r\n\r\nwith DDGS() as ddgs:\r\n    for r in ddgs.videos(\"FastAPI tutorial\", max_results=5):\r\n        print(r[\"title\"])\r\n        print(r.get(\"content\", \"\"))\r\n        print(r.get(\"duration\", \"\"))\r\n        print(r.get(\"provider\", \"\"))\r\n        print(r.get(\"published\", \"\"))\r\n        print()\r\n```\r\n\r\nReturns: `title`, `content`, `description`, `duration`, `provider`, `published`, `statistics`, `uploader`\r\n\r\n### Quick Reference\r\n\r\n| Method | Use When | Key Fields |\r\n|--------|----------|------------|\r\n| `text()` | General research, companies | title, href, body |\r\n| `news()` | Current events, updates | date, title, source, body, url |\r\n| `images()` | Visuals, diagrams | title, image, thumbnail, url |\r\n| `videos()` | Tutorials, demos | title, content, duration, provider |\r\n\r\n## Workflow: Search then Extract\r\n\r\nDuckDuckGo 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\nCLI example:\r\n\r\n```bash\r\nddgs text -q \"fastapi deployment guide\" -m 3 -o json\r\n```\r\n\r\nPython example, only after verifying `ddgs` is installed in that runtime:\r\n\r\n```python\r\nfrom ddgs import DDGS\r\n\r\nwith DDGS() as ddgs:\r\n    results = list(ddgs.text(\"fastapi deployment guide\", max_results=3))\r\n    for r in results:\r\n        print(r[\"title\"], \"->\", r[\"href\"])\r\n```\r\n\r\nThen extract the best URL with `web_extract` or another content-retrieval tool.\r\n\r\n## Limitations\r\n\r\n- **Rate limiting**: DuckDuckGo may throttle after many rapid requests. Add a short delay between searches if needed.\r\n- **No content extraction**: `ddgs` returns snippets, not full page content. Use `web_extract`, browser tools, or curl for the full article\u002Fpage.\r\n- **Results quality**: Generally good but less configurable than Firecrawl's search.\r\n- **Availability**: DuckDuckGo may block requests from some cloud IPs. If searches return empty, try different keywords or wait a few seconds.\r\n- **Field variability**: Return fields may vary between results or `ddgs` versions. Use `.get()` for optional fields to avoid `KeyError`.\r\n- **Separate runtimes**: A successful `ddgs` install in terminal does not automatically mean `execute_code` can import it.\r\n\r\n## Troubleshooting\r\n\r\n| Problem | Likely Cause | What To Do |\r\n|---------|--------------|------------|\r\n| `ddgs: command not found` | CLI not installed in the shell environment | Install `ddgs`, or use built-in web\u002Fbrowser tools instead |\r\n| `ModuleNotFoundError: No module named 'ddgs'` | Python runtime does not have the package installed | Do not use Python DDGS there until that runtime is prepared |\r\n| Search returns nothing | Temporary rate limiting or poor query | Wait a few seconds, retry, or adjust the query |\r\n| CLI works but `execute_code` import fails | Terminal and `execute_code` are different runtimes | Keep using CLI, or separately prepare the Python runtime |\r\n\r\n## Pitfalls\r\n\r\n- **`max_results` is keyword-only**: `ddgs.text(\"query\", 5)` raises an error. Use `ddgs.text(\"query\", max_results=5)`.\r\n- **Do not assume the CLI exists**: Check `command -v ddgs` before using it.\r\n- **Do not assume `execute_code` can import `ddgs`**: `from ddgs import DDGS` may fail with `ModuleNotFoundError` unless that runtime was prepared separately.\r\n- **Package name**: The package is `ddgs` (previously `duckduckgo-search`). Install with `pip install ddgs`.\r\n- **Don't confuse `-q` and `-m`** (CLI): `-q` is for the query, `-m` is for max results count.\r\n- **Empty results**: If `ddgs` returns nothing, it may be rate-limited. Wait a few seconds and retry.\r\n\r\n## Validated With\r\n\r\nValidated examples against `ddgs==9.11.2` semantics. Skill guidance now treats CLI availability and Python import availability as separate concerns so the documented workflow matches actual runtime behavior.\r\n","# DuckDuckGo Search\r\n\r\nFree web search using DuckDuckGo. **No API key required.**\r\n\r\nPreferred when `web_search` is unavailable or unsuitable (for example when `FIRECRAWL_API_KEY` is not set). Can also be used as a standalone search path when DuckDuckGo results are specifically desired.\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 CLI availability\r\ncommand -v ddgs >\u002Fdev\u002Fnull && echo \"DDGS_CLI=installed\" || echo \"DDGS_CLI=missing\"\r\n```\r\n\r\nDecision tree:\r\n1. If `ddgs` CLI is installed, prefer `terminal` + `ddgs`\r\n2. If `ddgs` CLI is missing, do not assume `execute_code` can import `ddgs`\r\n3. If the user wants DuckDuckGo specifically, install `ddgs` first in the relevant environment\r\n4. Otherwise fall back to built-in web\u002Fbrowser tools\r\n\r\nImportant runtime note:\r\n- Terminal and `execute_code` are separate runtimes\r\n- A successful shell install does not guarantee `execute_code` can import `ddgs`\r\n- Never assume third-party Python packages are preinstalled inside `execute_code`\r\n\r\n## Installation\r\n\r\nInstall `ddgs` only when DuckDuckGo search is specifically needed and the runtime does not already provide it.\r\n\r\n```bash\r\n# Python package + CLI entrypoint\r\npip install ddgs\r\n\r\n# Verify CLI\r\nddgs --help\r\n```\r\n\r\nIf a workflow depends on Python imports, verify that same runtime can import `ddgs` before using `from ddgs import DDGS`.\r\n\r\n## Method 1: CLI Search (Preferred)\r\n\r\nUse the `ddgs` command via `terminal` when it exists. This is the preferred path because it avoids assuming the `execute_code` sandbox has the `ddgs` Python package installed.\r\n\r\n```bash\r\n# Text search\r\nddgs text -q \"python async programming\" -m 5\r\n\r\n# News search\r\nddgs news -q \"artificial intelligence\" -m 5\r\n\r\n# Image search\r\nddgs images -q \"landscape photography\" -m 10\r\n\r\n# Video search\r\nddgs videos -q \"python tutorial\" -m 5\r\n\r\n# With region filter\r\nddgs text -q \"best restaurants\" -m 5 -r us-en\r\n\r\n# Recent results only (d=day, w=week, m=month, y=year)\r\nddgs text -q \"latest AI news\" -m 5 -t w\r\n\r\n# JSON output for parsing\r\nddgs text -q \"fastapi tutorial\" -m 5 -o json\r\n```\r\n\r\n### CLI Flags\r\n\r\n| Flag | Description | Example |\r\n|------|-------------|---------|\r\n| `-q` | Query — **required** | `-q \"search terms\"` |\r\n| `-m` | Max results | `-m 5` |\r\n| `-r` | Region | `-r us-en` |\r\n| `-t` | Time limit | `-t w` (week) |\r\n| `-s` | Safe search | `-s off` |\r\n| `-o` | Output format | `-o json` |\r\n\r\n## Method 2: Python API (Only After Verification)\r\n\r\nUse the `DDGS` class in `execute_code` or another Python runtime only after verifying that `ddgs` is installed there. Do not assume `execute_code` includes third-party packages by default.\r\n\r\nSafe wording:\r\n- \"Use `execute_code` with `ddgs` after installing or verifying the package if needed\"\r\n\r\nAvoid saying:\r\n- \"`execute_code` includes `ddgs`\"\r\n- \"DuckDuckGo search works by default in `execute_code`\"\r\n\r\n**Important:** `max_results` must always be passed as a **keyword argument** — positional usage raises an error on all methods.\r\n\r\n### Text Search\r\n\r\nBest for: general research, companies, documentation.\r\n\r\n```python\r\nfrom ddgs import DDGS\r\n\r\nwith DDGS() as ddgs:\r\n    for r in ddgs.text(\"python async programming\", max_results=5):\r\n        print(r[\"title\"])\r\n        print(r[\"href\"])\r\n        print(r.get(\"body\", \"\")[:200])\r\n        print()\r\n```\r\n\r\nReturns: `title`, `href`, `body`\r\n\r\n### News Search\r\n\r\nBest for: current events, breaking news, latest updates.\r\n\r\n```python\r\nfrom ddgs import DDGS\r\n\r\nwith DDGS() as ddgs:\r\n    for r in ddgs.news(\"AI regulation 2026\", max_results=5):\r\n        print(r[\"date\"], \"-\", r[\"title\"])\r\n        print(r.get(\"source\", \"\"), \"|\", r[\"url\"])\r\n        print(r.get(\"body\", \"\")[:200])\r\n        print()\r\n```\r\n\r\nReturns: `date`, `title`, `body`, `url`, `image`, `source`\r\n\r\n### Image Search\r\n\r\nBest for: visual references, product images, diagrams.\r\n\r\n```python\r\nfrom ddgs import DDGS\r\n\r\nwith DDGS() as ddgs:\r\n    for r in ddgs.images(\"semiconductor chip\", max_results=5):\r\n        print(r[\"title\"])\r\n        print(r[\"image\"])\r\n        print(r.get(\"thumbnail\", \"\"))\r\n        print(r.get(\"source\", \"\"))\r\n        print()\r\n```\r\n\r\nReturns: `title`, `image`, `thumbnail`, `url`, `height`, `width`, `source`\r\n\r\n### Video Search\r\n\r\nBest for: tutorials, demos, explainers.\r\n\r\n```python\r\nfrom ddgs import DDGS\r\n\r\nwith DDGS() as ddgs:\r\n    for r in ddgs.videos(\"FastAPI tutorial\", max_results=5):\r\n        print(r[\"title\"])\r\n        print(r.get(\"content\", \"\"))\r\n        print(r.get(\"duration\", \"\"))\r\n        print(r.get(\"provider\", \"\"))\r\n        print(r.get(\"published\", \"\"))\r\n        print()\r\n```\r\n\r\nReturns: `title`, `content`, `description`, `duration`, `provider`, `published`, `statistics`, `uploader`\r\n\r\n### Quick Reference\r\n\r\n| Method | Use When | Key Fields |\r\n|--------|----------|------------|\r\n| `text()` | General research, companies | title, href, body |\r\n| `news()` | Current events, updates | date, title, source, body, url |\r\n| `images()` | Visuals, diagrams | title, image, thumbnail, url |\r\n| `videos()` | Tutorials, demos | title, content, duration, provider |\r\n\r\n## Workflow: Search then Extract\r\n\r\nDuckDuckGo 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\nCLI example:\r\n\r\n```bash\r\nddgs text -q \"fastapi deployment guide\" -m 3 -o json\r\n```\r\n\r\nPython example, only after verifying `ddgs` is installed in that runtime:\r\n\r\n```python\r\nfrom ddgs import DDGS\r\n\r\nwith DDGS() as ddgs:\r\n    results = list(ddgs.text(\"fastapi deployment guide\", max_results=3))\r\n    for r in results:\r\n        print(r[\"title\"], \"->\", r[\"href\"])\r\n```\r\n\r\nThen extract the best URL with `web_extract` or another content-retrieval tool.\r\n\r\n## Limitations\r\n\r\n- **Rate limiting**: DuckDuckGo may throttle after many rapid requests. Add a short delay between searches if needed.\r\n- **No content extraction**: `ddgs` returns snippets, not full page content. Use `web_extract`, browser tools, or curl for the full article\u002Fpage.\r\n- **Results quality**: Generally good but less configurable than Firecrawl's search.\r\n- **Availability**: DuckDuckGo may block requests from some cloud IPs. If searches return empty, try different keywords or wait a few seconds.\r\n- **Field variability**: Return fields may vary between results or `ddgs` versions. Use `.get()` for optional fields to avoid `KeyError`.\r\n- **Separate runtimes**: A successful `ddgs` install in terminal does not automatically mean `execute_code` can import it.\r\n\r\n## Troubleshooting\r\n\r\n| Problem | Likely Cause | What To Do |\r\n|---------|--------------|------------|\r\n| `ddgs: command not found` | CLI not installed in the shell environment | Install `ddgs`, or use built-in web\u002Fbrowser tools instead |\r\n| `ModuleNotFoundError: No module named 'ddgs'` | Python runtime does not have the package installed | Do not use Python DDGS there until that runtime is prepared |\r\n| Search returns nothing | Temporary rate limiting or poor query | Wait a few seconds, retry, or adjust the query |\r\n| CLI works but `execute_code` import fails | Terminal and `execute_code` are different runtimes | Keep using CLI, or separately prepare the Python runtime |\r\n\r\n## Pitfalls\r\n\r\n- **`max_results` is keyword-only**: `ddgs.text(\"query\", 5)` raises an error. Use `ddgs.text(\"query\", max_results=5)`.\r\n- **Do not assume the CLI exists**: Check `command -v ddgs` before using it.\r\n- **Do not assume `execute_code` can import `ddgs`**: `from ddgs import DDGS` may fail with `ModuleNotFoundError` unless that runtime was prepared separately.\r\n- **Package name**: The package is `ddgs` (previously `duckduckgo-search`). Install with `pip install ddgs`.\r\n- **Don't confuse `-q` and `-m`** (CLI): `-q` is for the query, `-m` is for max results count.\r\n- **Empty results**: If `ddgs` returns nothing, it may be rate-limited. Wait a few seconds and retry.\r\n\r\n## Validated With\r\n\r\nValidated examples against `ddgs==9.11.2` semantics. Skill guidance now treats CLI availability and Python import availability as separate concerns so the documented workflow matches actual runtime behavior.\r\n",{"name":5,"author":44,"license":15,"version":45,"metadata":46,"platforms":53,"description":7},"gamedevCloudy","1.3.0",{"hermes":47},{"tags":48,"related_skills":50,"fallback_for_toolsets":52},[20,19,28,25,49],"fallback",[51],"arxiv",[36],[37,54,35],"macos","main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002F84\u002F84df053425ab0fec30e7217f02aebe4c58cd18c90d91e44e3a97ad798e7cb5f1",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 duckduckgo-search",{"tool":69,"command":70},"bunx","bunx skills add zapabob\u002FSkills --skill duckduckgo-search",{"tool":72,"command":73},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill duckduckgo-search","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F84\u002F84df053425ab0fec30e7217f02aebe4c58cd18c90d91e44e3a97ad798e7cb5f1\u002FSKILL.md",true,[],[78,109,144,169,196,213],{"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",[80,98,54,30,99,37,35,100,20,101,102,34,103,104,105,106,55,107,24,108],"openclaw","github","official","https","social-media","Media","hermes","hermes agent","twitter","social","post",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":126,"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",[115,118,121,122,123],{"categoryNo":116,"categoryName":117,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":119,"categoryName":120,"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":124,"categoryName":125,"taxonomyType":95,"taxonomyTypeDesc":96},"01JBSEEDCAT000000000000036","内容创作者",[127,128,129,130,54,131,37,132,35,133,134,135,136,137,138,139,140,141,142,143],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":153,"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",[150],{"categoryNo":151,"categoryName":152,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000016","图像与多媒体",[146,54,37,154,155,156,157,158,159,32,160,161,31,162,163,164,165,166,167,168],"openai","speech","multimodal","Transformers","ASR","Audio","model","speech recognition","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":178,"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",[175],{"categoryNo":176,"categoryName":177,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000013","分析与可视化",[179,54,180,181,35,182,183,184,185,186,187,160,188,189,190,191,192,193,194,195],"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":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":200,"categories":201,"keywords":203,"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",[202],{"categoryNo":90,"categoryName":91,"taxonomyType":87,"taxonomyTypeDesc":88},[198,54,204,99,37,205,206,207,208,209,210,104,105,211,212],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":214,"name":215,"nameZh":6,"description":216,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":217,"categories":218,"keywords":221,"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",[219,220],{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},{"categoryNo":93,"categoryName":94,"taxonomyType":95,"taxonomyTypeDesc":96},[222,223,224,37,225,154,226,227,228,157,229,34,230,231,232,233,234,235,236,237],"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"]