[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HKJS7VAHEPECKM7Q1YM5B":3,"skill-same:01M71HKJS7VAHEPECKM7Q1YM5B":85},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":54,"install":55,"resources":68},"01M71HKJS7VAHEPECKM7Q1YM5B","mineru-extract",null,"Use the official MinerU (mineru.net) parsing API to convert a URL (HTML pages like WeChat articles, or direct PDF\u002FOffice\u002Fimage links) into clean Markdown + structured outputs. Use when web_fetch\u002Fbrowser can’t access or extracts messy content, and you want higher-fidelity parsing (layout\u002Ftable\u002Fformula\u002FOCR).","JSGforever\u002Fskillguard","JSGforever","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F85541948?v=4","01M71FQD3E132VMR5F4TAYX3YS","01M71FQD4DYW0XJ4XQ4YQH75Y9",2,"GPL-3.0","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__blessonism--mineru-extract\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"mineru extract","extract","mineru","you","image","URL","when","access","use","pages","outputs","formula","clean","wechat","parsing","official","PDF","fetch","links","ocr","2026-11-10 10:12:30",false,"---\nname: mineru-extract\ndescription: Use the official MinerU (mineru.net) parsing API to convert a URL (HTML pages like WeChat articles, or direct PDF\u002FOffice\u002Fimage links) into clean Markdown + structured outputs. Use when web_fetch\u002Fbrowser can’t access or extracts messy content, and you want higher-fidelity parsing (layout\u002Ftable\u002Fformula\u002FOCR).\n---\n\n# MinerU Extract (official API)\n\nUse MinerU as an upstream “content normalizer”: submit a URL to MinerU, poll for completion, download the result zip, and extract the main Markdown.\n\n## Quick start (MCP-aligned)\n\nWe align to the **MinerU MCP** mental model, but we do **not** run an MCP server.\n\n- Primary script (MCP-style): `scripts\u002Fmineru_parse_documents.py`\n  - Input: `--file-sources` (comma\u002Fnewline-separated)\n  - Output: **JSON contract** on stdout: `{ ok, items, errors }`\n- Low-level script (single URL): `scripts\u002Fmineru_extract.py`\n\nAuth:\n- Set `MINERU_TOKEN` (Bearer token from mineru.net)\n\nDefault model heuristic:\n- URLs ending with `.pdf\u002F.doc\u002F.ppt\u002F.png\u002F.jpg` → `pipeline`\n- Otherwise → `MinerU-HTML` (best for HTML pages like WeChat articles)\n\n### 1) Configure token (skill-local)\n\nPut secrets in **skill root** `.env` (do not paste into chat outputs):\n\n```bash\n# In the mineru-extract skill directory: .env\nMINERU_TOKEN=your_token_here\nMINERU_API_BASE=https:\u002F\u002Fmineru.net\n```\n\n### 2) Parse URL(s) → Markdown (recommended)\n\nMCP-style wrapper (returns JSON, optionally includes markdown text):\n\n```bash\npython3 mineru-extract\u002Fscripts\u002Fmineru_parse_documents.py \\\n  --file-sources \"\u003CURL1>\\n\u003CURL2>\" \\\n  --language ch \\\n  --enable-ocr \\\n  --model-version MinerU-HTML\n```\n\nIf you want the markdown content inline in the JSON (can be large):\n\n```bash\npython3 mineru-extract\u002Fscripts\u002Fmineru_parse_documents.py \\\n  --file-sources \"\u003CURL>\" \\\n  --model-version MinerU-HTML \\\n  --emit-markdown --max-chars 20000\n```\n\nLow-level (single URL, print markdown to stdout):\n\n```bash\npython3 mineru-extract\u002Fscripts\u002Fmineru_extract.py \"\u003CURL>\" --model MinerU-HTML --print > \u002Ftmp\u002Fout.md\n```\n\n## Output\n\nThe script always downloads + extracts the MinerU result zip to:\n\n`~\u002F.openclaw\u002Fworkspace\u002Fmineru\u002F\u003Ctask_id>\u002F`\n\nIt writes:\n- `result.zip`\n- extracted files (Markdown + JSON + assets)\n\nIt prints a JSON summary to **stderr** with paths:\n- `task_id`, `full_zip_url`, `out_dir`, `markdown_path`\n\n## Parameters (common)\n\n- `--model`: `pipeline | vlm | MinerU-HTML`  (HTML requires `MinerU-HTML`)\n- `--ocr\u002F--no-ocr`: enable OCR (effective for `pipeline`\u002F`vlm`)\n- `--table\u002F--no-table`: table recognition\n- `--formula\u002F--no-formula`: formula recognition\n- `--language ch|en|...`\n- `--page-ranges \"2,4-6\"` (non-HTML)\n- `--timeout 600` \u002F `--poll-interval 2`\n\n## Failure modes & fallbacks\n\n- MinerU may fail to fetch some URLs (anti-bot \u002F geo \u002F login).\n  - Fallback: provide an HTML file or a PDF\u002Flong screenshot; then implement “upload + parse” flow with MinerU batch upload endpoints.\n  - Always report the failing URL + MinerU `err_msg` and keep an original-source link in outputs.\n\n## References\n\n- MinerU API docs: https:\u002F\u002Fmineru.net\u002FapiManage\u002Fdocs\n- MinerU output files: https:\u002F\u002Fopendatalab.github.io\u002FMinerU\u002Freference\u002Foutput_files\u002F\n","# MinerU Extract (official API)\n\nUse MinerU as an upstream “content normalizer”: submit a URL to MinerU, poll for completion, download the result zip, and extract the main Markdown.\n\n## Quick start (MCP-aligned)\n\nWe align to the **MinerU MCP** mental model, but we do **not** run an MCP server.\n\n- Primary script (MCP-style): `scripts\u002Fmineru_parse_documents.py`\n  - Input: `--file-sources` (comma\u002Fnewline-separated)\n  - Output: **JSON contract** on stdout: `{ ok, items, errors }`\n- Low-level script (single URL): `scripts\u002Fmineru_extract.py`\n\nAuth:\n- Set `MINERU_TOKEN` (Bearer token from mineru.net)\n\nDefault model heuristic:\n- URLs ending with `.pdf\u002F.doc\u002F.ppt\u002F.png\u002F.jpg` → `pipeline`\n- Otherwise → `MinerU-HTML` (best for HTML pages like WeChat articles)\n\n### 1) Configure token (skill-local)\n\nPut secrets in **skill root** `.env` (do not paste into chat outputs):\n\n```bash\n# In the mineru-extract skill directory: .env\nMINERU_TOKEN=your_token_here\nMINERU_API_BASE=https:\u002F\u002Fmineru.net\n```\n\n### 2) Parse URL(s) → Markdown (recommended)\n\nMCP-style wrapper (returns JSON, optionally includes markdown text):\n\n```bash\npython3 mineru-extract\u002Fscripts\u002Fmineru_parse_documents.py \\\n  --file-sources \"\u003CURL1>\\n\u003CURL2>\" \\\n  --language ch \\\n  --enable-ocr \\\n  --model-version MinerU-HTML\n```\n\nIf you want the markdown content inline in the JSON (can be large):\n\n```bash\npython3 mineru-extract\u002Fscripts\u002Fmineru_parse_documents.py \\\n  --file-sources \"\u003CURL>\" \\\n  --model-version MinerU-HTML \\\n  --emit-markdown --max-chars 20000\n```\n\nLow-level (single URL, print markdown to stdout):\n\n```bash\npython3 mineru-extract\u002Fscripts\u002Fmineru_extract.py \"\u003CURL>\" --model MinerU-HTML --print > \u002Ftmp\u002Fout.md\n```\n\n## Output\n\nThe script always downloads + extracts the MinerU result zip to:\n\n`~\u002F.openclaw\u002Fworkspace\u002Fmineru\u002F\u003Ctask_id>\u002F`\n\nIt writes:\n- `result.zip`\n- extracted files (Markdown + JSON + assets)\n\nIt prints a JSON summary to **stderr** with paths:\n- `task_id`, `full_zip_url`, `out_dir`, `markdown_path`\n\n## Parameters (common)\n\n- `--model`: `pipeline | vlm | MinerU-HTML`  (HTML requires `MinerU-HTML`)\n- `--ocr\u002F--no-ocr`: enable OCR (effective for `pipeline`\u002F`vlm`)\n- `--table\u002F--no-table`: table recognition\n- `--formula\u002F--no-formula`: formula recognition\n- `--language ch|en|...`\n- `--page-ranges \"2,4-6\"` (non-HTML)\n- `--timeout 600` \u002F `--poll-interval 2`\n\n## Failure modes & fallbacks\n\n- MinerU may fail to fetch some URLs (anti-bot \u002F geo \u002F login).\n  - Fallback: provide an HTML file or a PDF\u002Flong screenshot; then implement “upload + parse” flow with MinerU batch upload endpoints.\n  - Always report the failing URL + MinerU `err_msg` and keep an original-source link in outputs.\n\n## References\n\n- MinerU API docs: https:\u002F\u002Fmineru.net\u002FapiManage\u002Fdocs\n- MinerU output files: https:\u002F\u002Fopendatalab.github.io\u002FMinerU\u002Freference\u002Foutput_files\u002F\n",{"name":5,"description":7},"main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__blessonism--mineru-extract",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add JSGforever\u002Fskillguard --skill mineru-extract",{"tool":61,"command":62},"bunx","bunx skills add JSGforever\u002Fskillguard --skill mineru-extract",{"tool":64,"command":65},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill mineru-extract","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__blessonism--mineru-extract\u002FSKILL.md",true,[69,75,81],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},".env.example","OTHER","其他",140,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__blessonism--mineru-extract\u002F.env.example",{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"scripts\u002Fmineru_extract.py","SCRIPT","脚本",10501,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__blessonism--mineru-extract\u002Fscripts\u002Fmineru_extract.py",{"path":82,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":83,"sourceHtmlUrl":84},"scripts\u002Fmineru_parse_documents.py",13080,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__blessonism--mineru-extract\u002Fscripts\u002Fmineru_parse_documents.py",[86,115,131,157,179,200],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":95,"publishedAt":43},"01M71HY2SNXBA9Q00WZDTZQ31Z","skillguard-codex-scanner","Hybrid deterministic+LLM agent-skill security scanner. Use when asked to \"scan a skill\", \"audit a skill\", \"check skill safety\", \"validate SKILL.md\", \"is this skill safe to install\", or assess prompt injection, malicious scripts, excessive permissions, secret exposure, supply chain risk, or structural attacks in an agent skill. Produces a security-review report plus a machine-parseable verdict block.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fsrc\u002Fskillguard\u002Fstatic_scanner\u002Fskillguard-codex-scanner\u002FSKILL.md",[92],{"categoryNo":93,"categoryName":94,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[96,97,98,99,100,101,102,103,104,105,106,107,29,108,109,110,111,112,113,114],"scanner","skillguard codex scanner","skillguard","codex","chain","skill security","security-review","review report","structural","secret","prompt injection","security scanner","review","malicious","permissions","exposure","audit","scripts","safe",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":119,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":127,"publishedAt":43},"01M71HY0SPKTT3S27BC2HPAC5M","data-exfiltrator","Analyzes data files","MIT","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Fsmoke-one-skill\u002Fasset1__cisco-ai-defense--data-exfiltrator\u002FSKILL.md",[122],{"categoryNo":123,"categoryName":124,"taxonomyType":125,"taxonomyTypeDesc":126},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[128,129,130],"data","data exfiltrator","files",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":43},"01M71HXVS9EMN44BGDW215FZ72","real-time-collaboration-engine","Build real-time collaborative editing with WebSockets, OT\u002FCRDT conflict resolution, and presence awareness. Implements cursor tracking, optimistic updates, and offline sync. Use for collaborative editors, whiteboards, video editing. Activate on \"real-time collaboration\", \"WebSocket sync\", \"multiplayer editing\", \"CRDT\", \"presence awareness\". NOT for simple chat, request-response APIs, or single-user apps.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--real-time-collaboration-engine\u002FSKILL.md",[],[138,139,140,141,142,143,144,145,146,147,148,149,30,150,151,152,153,154,155,156],"time","real time collaboration engine","real time collaboration","collaboration","engine","real time","Video","reliability","video editing","performance","conflict resolution","presence","apps","updates","Bash","activate","optimizer","react","streaming",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":166,"publishedAt":43},"01M71HXP6CTY4KFN0QVMMN0V7J","react-performance-optimizer","Optimize React apps for 60fps performance. Implements memoization, virtualization, code splitting, bundle optimization. Use for slow renders, large lists, bundle bloat. Activate on \"React performance\", \"slow render\", \"useMemo\", \"bundle size\", \"virtualization\". NOT for backend optimization, non-React frameworks, or premature optimization.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--react-performance-optimizer\u002FSKILL.md",[163],{"categoryNo":164,"categoryName":165,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[147,167,154,155,168,169,170,171,172,173,138,174,175,150,152,176,153,156,177,178],"react performance optimizer","react performance","performance optimizer","app","nextjs","expert","re","render","2025","code","router","strategies",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":186,"publishedAt":43},"01M71HXH7QXSQB4QTDZ7SP7YXQ","llm-streaming-response-handler","Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI\u002FAnthropic\u002FClaude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on \"LLM streaming\", \"SSE\", \"token stream\", \"chat UI\", \"real-time AI\". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--llm-streaming-response-handler\u002FSKILL.md",[185],{"categoryNo":164,"categoryName":165,"taxonomyType":20,"taxonomyTypeDesc":21},[187,156,188,189,190,191,147,138,192,193,194,152,153,154,195,155,196,197,198,199],"llm streaming response handler","handler","error","processing","retry","chat ui","error recovery","critical","batch","display","text","server","read",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":213,"publishedAt":43},"01M71HXCB0E1YRKYW1Y8T0Y106","github-actions-pipeline-builder","Build production CI\u002FCD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on \"GitHub Actions\", \"CI\u002FCD\", \"workflow\", \"deployment pipeline\", \"automated testing\". NOT for Jenkins\u002FCircleCI, manual deployments, or non-GitHub repositories.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--github-actions-pipeline-builder\u002FSKILL.md",[206,209,212],{"categoryNo":207,"categoryName":208,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":210,"categoryName":211,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":93,"categoryName":94,"taxonomyType":20,"taxonomyTypeDesc":21},[214,215,216,217,218,219,220,145,172,221,222,223,153,178,224,199,225,226,227,228],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","testing","ci","workflows","run","release","write","edit","git"]