[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GGDZ0H8T2SXAVQJH1X4EP7":3,"skill-same:01M6GGDZ0H8T2SXAVQJH1X4EP7":75},{"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":23,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":6,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M6GGDZ0H8T2SXAVQJH1X4EP7","duckduckgo-search",null,"Free keyless web, news, and image search via ddgs.","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\u002Fea\u002Fea5ee32dee8ba94efc7e733086c0c71d23135850ca3dd8d377822c0c6fe31939\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"search","duckduckgo search","duckduckgo","image","macos","linux","web","windows","keyless","arxiv","fallback","image search","web-search","news","free","via","2026-11-10 10:12:30",false,"---\nname: duckduckgo-search\ndescription: Free keyless web, news, and image search via ddgs.\nversion: 1.3.0\nauthor: gamedevCloudy\nlicense: MIT\nplatforms: [linux, macos, windows]\nmetadata:\n  hermes:\n    tags: [search, duckduckgo, web-search, free, fallback]\n    related_skills: [arxiv]\n    fallback_for_toolsets: [web]\n---\n\n# DuckDuckGo Search\n\nFree web search using DuckDuckGo. **No API key required.**\n\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.\n\n## Detection Flow\n\nCheck what is actually available before choosing an approach:\n\n```bash\n# Check CLI availability\ncommand -v ddgs >\u002Fdev\u002Fnull && echo \"DDGS_CLI=installed\" || echo \"DDGS_CLI=missing\"\n```\n\nDecision tree:\n1. If `ddgs` CLI is installed, prefer `terminal` + `ddgs`\n2. If `ddgs` CLI is missing, do not assume `execute_code` can import `ddgs`\n3. If the user wants DuckDuckGo specifically, install `ddgs` first in the relevant environment\n4. Otherwise fall back to built-in web\u002Fbrowser tools\n\nImportant runtime note:\n- Terminal and `execute_code` are separate runtimes\n- A successful shell install does not guarantee `execute_code` can import `ddgs`\n- Never assume third-party Python packages are preinstalled inside `execute_code`\n\n## Installation\n\nInstall `ddgs` only when DuckDuckGo search is specifically needed and the runtime does not already provide it.\n\n```bash\n# Python package + CLI entrypoint\npip install ddgs\n\n# Verify CLI\nddgs --help\n```\n\nIf a workflow depends on Python imports, verify that same runtime can import `ddgs` before using `from ddgs import DDGS`.\n\n## Method 1: CLI Search (Preferred)\n\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.\n\n```bash\n# Text search\nddgs text -q \"python async programming\" -m 5\n\n# News search\nddgs news -q \"artificial intelligence\" -m 5\n\n# Image search\nddgs images -q \"landscape photography\" -m 10\n\n# Video search\nddgs videos -q \"python tutorial\" -m 5\n\n# With region filter\nddgs text -q \"best restaurants\" -m 5 -r us-en\n\n# Recent results only (d=day, w=week, m=month, y=year)\nddgs text -q \"latest AI news\" -m 5 -t w\n\n# JSON output for parsing\nddgs text -q \"fastapi tutorial\" -m 5 -o json\n```\n\n### CLI Flags\n\n| Flag | Description | Example |\n|------|-------------|---------|\n| `-q` | Query — **required** | `-q \"search terms\"` |\n| `-m` | Max results | `-m 5` |\n| `-r` | Region | `-r us-en` |\n| `-t` | Time limit | `-t w` (week) |\n| `-s` | Safe search | `-s off` |\n| `-o` | Output format | `-o json` |\n\n## Method 2: Python API (Only After Verification)\n\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.\n\nSafe wording:\n- \"Use `execute_code` with `ddgs` after installing or verifying the package if needed\"\n\nAvoid saying:\n- \"`execute_code` includes `ddgs`\"\n- \"DuckDuckGo search works by default in `execute_code`\"\n\n**Important:** `max_results` must always be passed as a **keyword argument** — positional usage raises an error on all methods.\n\n### Text Search\n\nBest for: general research, companies, documentation.\n\n```python\nfrom ddgs import DDGS\n\nwith DDGS() as ddgs:\n    for r in ddgs.text(\"python async programming\", max_results=5):\n        print(r[\"title\"])\n        print(r[\"href\"])\n        print(r.get(\"body\", \"\")[:200])\n        print()\n```\n\nReturns: `title`, `href`, `body`\n\n### News Search\n\nBest for: current events, breaking news, latest updates.\n\n```python\nfrom ddgs import DDGS\n\nwith DDGS() as ddgs:\n    for r in ddgs.news(\"AI regulation 2026\", max_results=5):\n        print(r[\"date\"], \"-\", r[\"title\"])\n        print(r.get(\"source\", \"\"), \"|\", r[\"url\"])\n        print(r.get(\"body\", \"\")[:200])\n        print()\n```\n\nReturns: `date`, `title`, `body`, `url`, `image`, `source`\n\n### Image Search\n\nBest for: visual references, product images, diagrams.\n\n```python\nfrom ddgs import DDGS\n\nwith DDGS() as ddgs:\n    for r in ddgs.images(\"semiconductor chip\", max_results=5):\n        print(r[\"title\"])\n        print(r[\"image\"])\n        print(r.get(\"thumbnail\", \"\"))\n        print(r.get(\"source\", \"\"))\n        print()\n```\n\nReturns: `title`, `image`, `thumbnail`, `url`, `height`, `width`, `source`\n\n### Video Search\n\nBest for: tutorials, demos, explainers.\n\n```python\nfrom ddgs import DDGS\n\nwith DDGS() as ddgs:\n    for r in ddgs.videos(\"FastAPI tutorial\", max_results=5):\n        print(r[\"title\"])\n        print(r.get(\"content\", \"\"))\n        print(r.get(\"duration\", \"\"))\n        print(r.get(\"provider\", \"\"))\n        print(r.get(\"published\", \"\"))\n        print()\n```\n\nReturns: `title`, `content`, `description`, `duration`, `provider`, `published`, `statistics`, `uploader`\n\n### Quick Reference\n\n| Method | Use When | Key Fields |\n|--------|----------|------------|\n| `text()` | General research, companies | title, href, body |\n| `news()` | Current events, updates | date, title, source, body, url |\n| `images()` | Visuals, diagrams | title, image, thumbnail, url |\n| `videos()` | Tutorials, demos | title, content, duration, provider |\n\n## Workflow: Search then Extract\n\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.\n\nCLI example:\n\n```bash\nddgs text -q \"fastapi deployment guide\" -m 3 -o json\n```\n\nPython example, only after verifying `ddgs` is installed in that runtime:\n\n```python\nfrom ddgs import DDGS\n\nwith DDGS() as ddgs:\n    results = list(ddgs.text(\"fastapi deployment guide\", max_results=3))\n    for r in results:\n        print(r[\"title\"], \"->\", r[\"href\"])\n```\n\nThen extract the best URL with `web_extract` or another content-retrieval tool.\n\n## Limitations\n\n- **Rate limiting**: DuckDuckGo may throttle after many rapid requests. Add a short delay between searches if needed.\n- **No content extraction**: `ddgs` returns snippets, not full page content. Use `web_extract`, browser tools, or curl for the full article\u002Fpage.\n- **Results quality**: Generally good but less configurable than Firecrawl's search.\n- **Availability**: DuckDuckGo may block requests from some cloud IPs. If searches return empty, try different keywords or wait a few seconds.\n- **Field variability**: Return fields may vary between results or `ddgs` versions. Use `.get()` for optional fields to avoid `KeyError`.\n- **Separate runtimes**: A successful `ddgs` install in terminal does not automatically mean `execute_code` can import it.\n\n## Troubleshooting\n\n| Problem | Likely Cause | What To Do |\n|---------|--------------|------------|\n| `ddgs: command not found` | CLI not installed in the shell environment | Install `ddgs`, or use built-in web\u002Fbrowser tools instead |\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 |\n| Search returns nothing | Temporary rate limiting or poor query | Wait a few seconds, retry, or adjust the query |\n| CLI works but `execute_code` import fails | Terminal and `execute_code` are different runtimes | Keep using CLI, or separately prepare the Python runtime |\n\n## Pitfalls\n\n- **`max_results` is keyword-only**: `ddgs.text(\"query\", 5)` raises an error. Use `ddgs.text(\"query\", max_results=5)`.\n- **Do not assume the CLI exists**: Check `command -v ddgs` before using it.\n- **Do not assume `execute_code` can import `ddgs`**: `from ddgs import DDGS` may fail with `ModuleNotFoundError` unless that runtime was prepared separately.\n- **Package name**: The package is `ddgs` (previously `duckduckgo-search`). Install with `pip install ddgs`.\n- **Don't confuse `-q` and `-m`** (CLI): `-q` is for the query, `-m` is for max results count.\n- **Empty results**: If `ddgs` returns nothing, it may be rate-limited. Wait a few seconds and retry.\n\n## Validated With\n\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.\n","# DuckDuckGo Search\n\nFree web search using DuckDuckGo. **No API key required.**\n\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.\n\n## Detection Flow\n\nCheck what is actually available before choosing an approach:\n\n```bash\n# Check CLI availability\ncommand -v ddgs >\u002Fdev\u002Fnull && echo \"DDGS_CLI=installed\" || echo \"DDGS_CLI=missing\"\n```\n\nDecision tree:\n1. If `ddgs` CLI is installed, prefer `terminal` + `ddgs`\n2. If `ddgs` CLI is missing, do not assume `execute_code` can import `ddgs`\n3. If the user wants DuckDuckGo specifically, install `ddgs` first in the relevant environment\n4. Otherwise fall back to built-in web\u002Fbrowser tools\n\nImportant runtime note:\n- Terminal and `execute_code` are separate runtimes\n- A successful shell install does not guarantee `execute_code` can import `ddgs`\n- Never assume third-party Python packages are preinstalled inside `execute_code`\n\n## Installation\n\nInstall `ddgs` only when DuckDuckGo search is specifically needed and the runtime does not already provide it.\n\n```bash\n# Python package + CLI entrypoint\npip install ddgs\n\n# Verify CLI\nddgs --help\n```\n\nIf a workflow depends on Python imports, verify that same runtime can import `ddgs` before using `from ddgs import DDGS`.\n\n## Method 1: CLI Search (Preferred)\n\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.\n\n```bash\n# Text search\nddgs text -q \"python async programming\" -m 5\n\n# News search\nddgs news -q \"artificial intelligence\" -m 5\n\n# Image search\nddgs images -q \"landscape photography\" -m 10\n\n# Video search\nddgs videos -q \"python tutorial\" -m 5\n\n# With region filter\nddgs text -q \"best restaurants\" -m 5 -r us-en\n\n# Recent results only (d=day, w=week, m=month, y=year)\nddgs text -q \"latest AI news\" -m 5 -t w\n\n# JSON output for parsing\nddgs text -q \"fastapi tutorial\" -m 5 -o json\n```\n\n### CLI Flags\n\n| Flag | Description | Example |\n|------|-------------|---------|\n| `-q` | Query — **required** | `-q \"search terms\"` |\n| `-m` | Max results | `-m 5` |\n| `-r` | Region | `-r us-en` |\n| `-t` | Time limit | `-t w` (week) |\n| `-s` | Safe search | `-s off` |\n| `-o` | Output format | `-o json` |\n\n## Method 2: Python API (Only After Verification)\n\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.\n\nSafe wording:\n- \"Use `execute_code` with `ddgs` after installing or verifying the package if needed\"\n\nAvoid saying:\n- \"`execute_code` includes `ddgs`\"\n- \"DuckDuckGo search works by default in `execute_code`\"\n\n**Important:** `max_results` must always be passed as a **keyword argument** — positional usage raises an error on all methods.\n\n### Text Search\n\nBest for: general research, companies, documentation.\n\n```python\nfrom ddgs import DDGS\n\nwith DDGS() as ddgs:\n    for r in ddgs.text(\"python async programming\", max_results=5):\n        print(r[\"title\"])\n        print(r[\"href\"])\n        print(r.get(\"body\", \"\")[:200])\n        print()\n```\n\nReturns: `title`, `href`, `body`\n\n### News Search\n\nBest for: current events, breaking news, latest updates.\n\n```python\nfrom ddgs import DDGS\n\nwith DDGS() as ddgs:\n    for r in ddgs.news(\"AI regulation 2026\", max_results=5):\n        print(r[\"date\"], \"-\", r[\"title\"])\n        print(r.get(\"source\", \"\"), \"|\", r[\"url\"])\n        print(r.get(\"body\", \"\")[:200])\n        print()\n```\n\nReturns: `date`, `title`, `body`, `url`, `image`, `source`\n\n### Image Search\n\nBest for: visual references, product images, diagrams.\n\n```python\nfrom ddgs import DDGS\n\nwith DDGS() as ddgs:\n    for r in ddgs.images(\"semiconductor chip\", max_results=5):\n        print(r[\"title\"])\n        print(r[\"image\"])\n        print(r.get(\"thumbnail\", \"\"))\n        print(r.get(\"source\", \"\"))\n        print()\n```\n\nReturns: `title`, `image`, `thumbnail`, `url`, `height`, `width`, `source`\n\n### Video Search\n\nBest for: tutorials, demos, explainers.\n\n```python\nfrom ddgs import DDGS\n\nwith DDGS() as ddgs:\n    for r in ddgs.videos(\"FastAPI tutorial\", max_results=5):\n        print(r[\"title\"])\n        print(r.get(\"content\", \"\"))\n        print(r.get(\"duration\", \"\"))\n        print(r.get(\"provider\", \"\"))\n        print(r.get(\"published\", \"\"))\n        print()\n```\n\nReturns: `title`, `content`, `description`, `duration`, `provider`, `published`, `statistics`, `uploader`\n\n### Quick Reference\n\n| Method | Use When | Key Fields |\n|--------|----------|------------|\n| `text()` | General research, companies | title, href, body |\n| `news()` | Current events, updates | date, title, source, body, url |\n| `images()` | Visuals, diagrams | title, image, thumbnail, url |\n| `videos()` | Tutorials, demos | title, content, duration, provider |\n\n## Workflow: Search then Extract\n\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.\n\nCLI example:\n\n```bash\nddgs text -q \"fastapi deployment guide\" -m 3 -o json\n```\n\nPython example, only after verifying `ddgs` is installed in that runtime:\n\n```python\nfrom ddgs import DDGS\n\nwith DDGS() as ddgs:\n    results = list(ddgs.text(\"fastapi deployment guide\", max_results=3))\n    for r in results:\n        print(r[\"title\"], \"->\", r[\"href\"])\n```\n\nThen extract the best URL with `web_extract` or another content-retrieval tool.\n\n## Limitations\n\n- **Rate limiting**: DuckDuckGo may throttle after many rapid requests. Add a short delay between searches if needed.\n- **No content extraction**: `ddgs` returns snippets, not full page content. Use `web_extract`, browser tools, or curl for the full article\u002Fpage.\n- **Results quality**: Generally good but less configurable than Firecrawl's search.\n- **Availability**: DuckDuckGo may block requests from some cloud IPs. If searches return empty, try different keywords or wait a few seconds.\n- **Field variability**: Return fields may vary between results or `ddgs` versions. Use `.get()` for optional fields to avoid `KeyError`.\n- **Separate runtimes**: A successful `ddgs` install in terminal does not automatically mean `execute_code` can import it.\n\n## Troubleshooting\n\n| Problem | Likely Cause | What To Do |\n|---------|--------------|------------|\n| `ddgs: command not found` | CLI not installed in the shell environment | Install `ddgs`, or use built-in web\u002Fbrowser tools instead |\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 |\n| Search returns nothing | Temporary rate limiting or poor query | Wait a few seconds, retry, or adjust the query |\n| CLI works but `execute_code` import fails | Terminal and `execute_code` are different runtimes | Keep using CLI, or separately prepare the Python runtime |\n\n## Pitfalls\n\n- **`max_results` is keyword-only**: `ddgs.text(\"query\", 5)` raises an error. Use `ddgs.text(\"query\", max_results=5)`.\n- **Do not assume the CLI exists**: Check `command -v ddgs` before using it.\n- **Do not assume `execute_code` can import `ddgs`**: `from ddgs import DDGS` may fail with `ModuleNotFoundError` unless that runtime was prepared separately.\n- **Package name**: The package is `ddgs` (previously `duckduckgo-search`). Install with `pip install ddgs`.\n- **Don't confuse `-q` and `-m`** (CLI): `-q` is for the query, `-m` is for max results count.\n- **Empty results**: If `ddgs` returns nothing, it may be rate-limited. Wait a few seconds and retry.\n\n## Validated With\n\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.\n",{"name":5,"author":45,"license":15,"version":46,"metadata":47,"platforms":52,"description":7},"gamedevCloudy","1.3.0",{"hermes":48},{"tags":49,"related_skills":50,"fallback_for_toolsets":51},[24,26,36,38,34],[33],[30],[29,28,31],"main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002Fea\u002Fea5ee32dee8ba94efc7e733086c0c71d23135850ca3dd8d377822c0c6fe31939",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":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add zapabob\u002FSkills --skill duckduckgo-search",{"tool":67,"command":68},"bunx","bunx skills add zapabob\u002FSkills --skill duckduckgo-search",{"tool":70,"command":71},"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\u002Fea\u002Fea5ee32dee8ba94efc7e733086c0c71d23135850ca3dd8d377822c0c6fe31939\u002FSKILL.md",true,[],[76,107,142,167,194,211],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":93,"publishedAt":40},"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",[82,85,88],{"categoryNo":83,"categoryName":84,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":86,"categoryName":87,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[78,94,28,95,96,29,31,97,24,98,99,100,101,102,103,104,53,105,39,106],"openclaw","cli","github","official","https","social-media","api","Media","hermes","hermes agent","twitter","social","post",{"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":124,"publishedAt":40},"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",[113,116,119,120,121],{"categoryNo":114,"categoryName":115,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":117,"categoryName":118,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":86,"categoryName":87,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},{"categoryNo":122,"categoryName":123,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000036","内容创作者",[125,126,127,128,28,129,29,130,31,131,132,133,134,135,136,137,138,139,140,141],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":149,"publishedAt":40},"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",[148],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[144,28,29,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166],"openai","speech","multimodal","Transformers","ASR","Audio","text","model","speech recognition","use","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":176,"publishedAt":40},"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",[173],{"categoryNo":174,"categoryName":175,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",[177,28,178,179,31,180,181,182,183,184,185,157,186,187,188,189,190,191,192,193],"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":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":201,"publishedAt":40},"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",[200],{"categoryNo":86,"categoryName":87,"taxonomyType":21,"taxonomyTypeDesc":22},[196,28,202,96,29,203,204,205,206,207,208,102,103,209,210],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":212,"name":213,"nameZh":6,"description":214,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":215,"categories":216,"keywords":219,"publishedAt":40},"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",[217,218],{"categoryNo":83,"categoryName":84,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},[220,221,222,29,223,150,224,225,226,153,227,100,228,229,230,231,232,233,234,235],"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"]