[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792SFDCFT62TM761ATW8WJF":3,"skill-same:01M792SFDCFT62TM761ATW8WJF":79},{"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":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M792SFDCFT62TM761ATW8WJF","pixelrag",null,"Use PixelRAG for visual document RAG: screenshot capture, visual index building, FAISS\u002FQdrant serving, evaluation reproduction, and LoRA training\u002Fdata workflows.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpixelrag\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pixelrag\ndescription: \"Use PixelRAG for visual document RAG: screenshot capture, visual\n  index building, FAISS\u002FQdrant serving, evaluation reproduction, and LoRA\n  training\u002Fdata workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# PixelRAG\n\nUse this skill when a task names PixelRAG, `pixelshot`, `pixelrag`, visual RAG over screenshots, document screenshot tiles, Qwen3-VL visual embeddings, FAISS\u002FQdrant visual indexes, PixelRAG search APIs, paper reproduction, or the PixelRAG LoRA training data pipeline.\n\n## First Checks\n\n- **Check staleness**: Read [repo-provenance.md](references\u002Frepo-provenance.md) before using this skill with a checkout; refresh if the commit, package version, or evidence paths changed.\n- **Install minimally**: Base capture is `pip install pixelrag`. Add only the needed extra: `pixelrag[index]`, `pixelrag[serve]`, `pixelrag[qdrant]`, `pixelrag[pdf]`, or `pixelrag[dev]`.\n- **Verify commands**:\n  ```bash\n  python -c \"import pixelrag, pixelrag_render; print('ok')\"\n  pixelshot --help\n  pixelrag --help\n  ```\n- **Run diagnostics**: Use [pixelrag_doctor.py](scripts\u002Fpixelrag_doctor.py) before deeper debugging.\n- **Read troubleshooting**: Use [troubleshooting.md](references\u002Ftroubleshooting.md) for install, optional dependency, CUDA, Chrome, model-download, data\u002Fconfig, and stale-skill failures.\n\n## Route by Task\n\n| User request | Use this route |\n| --- | --- |\n| Capture URLs, authenticated browser pages, PDFs, HTML, text, or images into screenshot tiles | [render-capture](sub-skills\u002Frender-capture\u002FSKILL.md) |\n| Build a local visual index from documents, debug `pixelrag.yaml`, chunk\u002Fembed\u002Fbuild FAISS or Qdrant indexes | [index-build](sub-skills\u002Findex-build\u002FSKILL.md) |\n| Start or query `pixelrag serve`, call `\u002Fsearch`, use FAISS\u002FQdrant backends, fetch tile images, debug departments | [serve-search](sub-skills\u002Fserve-search\u002FSKILL.md) |\n| Reproduce paper benchmark cells, configure reader\u002Fsearch serves, run eval graders, debug low scores | [evaluation-reproduction](sub-skills\u002Fevaluation-reproduction\u002FSKILL.md) |\n| Use the released LoRA adapter, prepare synthetic data, run or debug the separate training project | [training-and-data](sub-skills\u002Ftraining-and-data\u002FSKILL.md) |\n\n## Minimal Patterns\n\nRender a page or local file:\n\n```bash\npixelshot https:\u002F\u002Fexample.org --output .\u002Ftiles\npixelshot paper.pdf --output .\u002Ftiles --dpi 200\n```\n\nBuild an index from local documents:\n\n```yaml\nsource:\n  type: local\n  path: .\u002Fmy_docs\nembed:\n  model: Qwen\u002FQwen3-VL-Embedding-2B\n  device: auto\noutput: .\u002Fmy_index\n```\n\n```bash\npixelrag index build --config pixelrag.yaml --limit 10\n```\n\nServe and search:\n\n```bash\npixelrag serve --index-dir .\u002Fmy_index --articles-json .\u002Fmy_index\u002Farticles.json --tiles-dir .\u002Fmy_index\u002Ftiles --port 30001\ncurl -s -X POST http:\u002F\u002Flocalhost:30001\u002Fsearch \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"queries\":[{\"text\":\"overview diagram\"}],\"n_docs\":5}'\n```\n\n## References\n\n- [install-and-routing.md](references\u002Finstall-and-routing.md) covers package extras, CLI dispatch, and workflow selection.\n- [agent-integration.md](references\u002Fagent-integration.md) covers hosted API use, pixelbrowse, and agent\u002Ftool integration boundaries.\n- [deployment-and-operations.md](references\u002Fdeployment-and-operations.md) covers production topology and safe blue-green deployment concepts.\n- [repo-routing-metadata.json](references\u002Frepo-routing-metadata.json) is structured router metadata for managed repo-skill import.\n\n## Important Boundaries\n\n- Do not treat full embedding, benchmark reproduction, or training as cheap: they may download large Qwen\u002FHF assets, load huge FAISS indexes, start long-running services, require GPUs, and consume paid API keys.\n- The `train\u002F` workflow is a separate uv project. Do not install it into the root PixelRAG package environment unless the task explicitly asks for training.\n- Do not run deploy scripts, systemd units, or nginx switch scripts unless the user confirms they are on the deploy host and wants operational changes.\n- Do not depend on original repo examples, docs, or tests at runtime; this skill bundles distilled references and safe helper scripts.\n","# PixelRAG\n\nUse this skill when a task names PixelRAG, `pixelshot`, `pixelrag`, visual RAG over screenshots, document screenshot tiles, Qwen3-VL visual embeddings, FAISS\u002FQdrant visual indexes, PixelRAG search APIs, paper reproduction, or the PixelRAG LoRA training data pipeline.\n\n## First Checks\n\n- **Check staleness**: Read [repo-provenance.md](references\u002Frepo-provenance.md) before using this skill with a checkout; refresh if the commit, package version, or evidence paths changed.\n- **Install minimally**: Base capture is `pip install pixelrag`. Add only the needed extra: `pixelrag[index]`, `pixelrag[serve]`, `pixelrag[qdrant]`, `pixelrag[pdf]`, or `pixelrag[dev]`.\n- **Verify commands**:\n  ```bash\n  python -c \"import pixelrag, pixelrag_render; print('ok')\"\n  pixelshot --help\n  pixelrag --help\n  ```\n- **Run diagnostics**: Use [pixelrag_doctor.py](scripts\u002Fpixelrag_doctor.py) before deeper debugging.\n- **Read troubleshooting**: Use [troubleshooting.md](references\u002Ftroubleshooting.md) for install, optional dependency, CUDA, Chrome, model-download, data\u002Fconfig, and stale-skill failures.\n\n## Route by Task\n\n| User request | Use this route |\n| --- | --- |\n| Capture URLs, authenticated browser pages, PDFs, HTML, text, or images into screenshot tiles | [render-capture](sub-skills\u002Frender-capture\u002FSKILL.md) |\n| Build a local visual index from documents, debug `pixelrag.yaml`, chunk\u002Fembed\u002Fbuild FAISS or Qdrant indexes | [index-build](sub-skills\u002Findex-build\u002FSKILL.md) |\n| Start or query `pixelrag serve`, call `\u002Fsearch`, use FAISS\u002FQdrant backends, fetch tile images, debug departments | [serve-search](sub-skills\u002Fserve-search\u002FSKILL.md) |\n| Reproduce paper benchmark cells, configure reader\u002Fsearch serves, run eval graders, debug low scores | [evaluation-reproduction](sub-skills\u002Fevaluation-reproduction\u002FSKILL.md) |\n| Use the released LoRA adapter, prepare synthetic data, run or debug the separate training project | [training-and-data](sub-skills\u002Ftraining-and-data\u002FSKILL.md) |\n\n## Minimal Patterns\n\nRender a page or local file:\n\n```bash\npixelshot https:\u002F\u002Fexample.org --output .\u002Ftiles\npixelshot paper.pdf --output .\u002Ftiles --dpi 200\n```\n\nBuild an index from local documents:\n\n```yaml\nsource:\n  type: local\n  path: .\u002Fmy_docs\nembed:\n  model: Qwen\u002FQwen3-VL-Embedding-2B\n  device: auto\noutput: .\u002Fmy_index\n```\n\n```bash\npixelrag index build --config pixelrag.yaml --limit 10\n```\n\nServe and search:\n\n```bash\npixelrag serve --index-dir .\u002Fmy_index --articles-json .\u002Fmy_index\u002Farticles.json --tiles-dir .\u002Fmy_index\u002Ftiles --port 30001\ncurl -s -X POST http:\u002F\u002Flocalhost:30001\u002Fsearch \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"queries\":[{\"text\":\"overview diagram\"}],\"n_docs\":5}'\n```\n\n## References\n\n- [install-and-routing.md](references\u002Finstall-and-routing.md) covers package extras, CLI dispatch, and workflow selection.\n- [agent-integration.md](references\u002Fagent-integration.md) covers hosted API use, pixelbrowse, and agent\u002Ftool integration boundaries.\n- [deployment-and-operations.md](references\u002Fdeployment-and-operations.md) covers production topology and safe blue-green deployment concepts.\n- [repo-routing-metadata.json](references\u002Frepo-routing-metadata.json) is structured router metadata for managed repo-skill import.\n\n## Important Boundaries\n\n- Do not treat full embedding, benchmark reproduction, or training as cheap: they may download large Qwen\u002FHF assets, load huge FAISS indexes, start long-running services, require GPUs, and consume paid API keys.\n- The `train\u002F` workflow is a separate uv project. Do not install it into the root PixelRAG package environment unless the task explicitly asks for training.\n- Do not run deploy scripts, systemd units, or nginx switch scripts unless the user confirms they are on the deploy host and wants operational changes.\n- Do not depend on original repo examples, docs, or tests at runtime; this skill bundles distilled references and safe helper scripts.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fpixelrag",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill pixelrag",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill pixelrag",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill pixelrag","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpixelrag\u002FSKILL.md",[47,53,57,61,65,69,73],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fagent-integration.md","REFERENCE","参考文档",1791,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpixelrag\u002Freferences\u002Fagent-integration.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fdeployment-and-operations.md",1796,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpixelrag\u002Freferences\u002Fdeployment-and-operations.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Finstall-and-routing.md",2611,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpixelrag\u002Freferences\u002Finstall-and-routing.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Frepo-provenance.md",1629,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpixelrag\u002Freferences\u002Frepo-provenance.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Frepo-routing-metadata.json",517,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpixelrag\u002Freferences\u002Frepo-routing-metadata.json",{"path":70,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Ftroubleshooting.md",2636,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpixelrag\u002Freferences\u002Ftroubleshooting.md",{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Fpixelrag_doctor.py","SCRIPT","脚本",2693,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpixelrag\u002Fscripts\u002Fpixelrag_doctor.py",[80,87,94,101,108,115],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"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":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]