[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792SMKH86Z18VRTYFSR97SG":3,"skill-same:01M792SMKH86Z18VRTYFSR97SG":71},{"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},"01M792SMKH86Z18VRTYFSR97SG","index-build",null,"Use PixelRAG to build visual retrieval indexes from rendered documents, tile chunks, embeddings, FAISS, or Qdrant.","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\u002Fsub-skills\u002Findex-build\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: index-build\ndescription: \"Use PixelRAG to build visual retrieval indexes from rendered\n  documents, tile chunks, embeddings, FAISS, or Qdrant.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# PixelRAG Index Build\n\nUse this sub-skill when a task asks to make documents searchable with PixelRAG, build a local visual index, debug `pixelrag.yaml`, run chunk\u002Fembed\u002Fbuild-index stages, or choose FAISS versus Qdrant.\n\n## Start Here\n\n1. If the user only has URLs, PDFs, HTML, or images and no tiles yet, first read `..\u002Frender-capture\u002FSKILL.md`.\n2. Pick an orchestration level:\n   - End-to-end: `pixelrag index build --config pixelrag.yaml`.\n   - Stage-by-stage: `pixelrag chunk`, `pixelrag embed`, and `pixelrag build-index`.\n3. Decide device and backend:\n   - `device: auto` chooses CUDA, MPS, then CPU in the local embedder path.\n   - CPU\u002FMPS is suitable for small demos; full Qwen embedding on CPU is slow.\n   - FAISS is the default local backend; Qdrant is for server-backed or disk\u002Fquantized vector storage.\n4. Validate generated artifacts before serving: `tiles\u002F`, `embeddings\u002Fshard_*.npz`, `index.faiss` or Qdrant `summary.json`, `metadata.npz`, and `articles.json`.\n\n## Read or Run\n\n- Read [workflows.md](references\u002Fworkflows.md) for end-to-end and stage-by-stage recipes.\n- Read [config-and-data-formats.md](references\u002Fconfig-and-data-formats.md) for `pixelrag.yaml`, source adapters, chunk manifests, embeddings, and index layouts.\n- Read [cli-reference.md](references\u002Fcli-reference.md) for flags and command selection.\n- Read [troubleshooting.md](references\u002Ftroubleshooting.md) for stale tiles, article IDs, Qdrant modes, GPU\u002Fmodel issues, and local-source surprises.\n- Run [pixelrag_tiny_index_config.py](scripts\u002Fpixelrag_tiny_index_config.py) to generate a tiny local-source config without downloading models.\n\n## Common Routes\n\n| Request | Action |\n| --- | --- |\n| \"Index this folder of PDFs\u002FMarkdown\u002Fimages\" | Generate a local-source `pixelrag.yaml`; use `pixelrag index build --device auto` for small runs or CUDA for production. |\n| \"Use Qdrant instead of FAISS\" | Set `index.backend: qdrant` and provide URL\u002Fcollection\u002Fclient\u002Fquantization config as needed. |\n| \"Re-run after source files changed\" | Trust the source-stamped tile manifests; use `--force` only for a clean rebuild. |\n| \"Department-filter search\" | Preserve subdirectory layout under the local source; `articles.json` stores the first subdirectory as `department`. |\n| \"I already have embeddings\" | Use `pixelrag build-index build --embeddings-dir ... --output-dir ...`. |\n| \"Now query this index\" | Route to `..\u002Fserve-search\u002FSKILL.md`. |\n\n## Validation Checklist\n\n- `pixelrag index build --help` lists `--device {auto,cpu,mps,cuda}`.\n- Local source only includes `.pdf`, `.html`, `.htm`, `.png`, `.jpg`, `.jpeg`, `.md`, and `.txt`.\n- Wide tiles are chunked into columns no wider than 875 px and rows of 1024 px where applicable.\n- `article_id` is propagated into `chunks.json` and embedding metadata.\n- `articles.json` titles, URLs\u002Fpaths, and department fields match the source set.\n- Qdrant `append` and `recreate` are explicit choices, never accidental overwrites.\n","# PixelRAG Index Build\n\nUse this sub-skill when a task asks to make documents searchable with PixelRAG, build a local visual index, debug `pixelrag.yaml`, run chunk\u002Fembed\u002Fbuild-index stages, or choose FAISS versus Qdrant.\n\n## Start Here\n\n1. If the user only has URLs, PDFs, HTML, or images and no tiles yet, first read `..\u002Frender-capture\u002FSKILL.md`.\n2. Pick an orchestration level:\n   - End-to-end: `pixelrag index build --config pixelrag.yaml`.\n   - Stage-by-stage: `pixelrag chunk`, `pixelrag embed`, and `pixelrag build-index`.\n3. Decide device and backend:\n   - `device: auto` chooses CUDA, MPS, then CPU in the local embedder path.\n   - CPU\u002FMPS is suitable for small demos; full Qwen embedding on CPU is slow.\n   - FAISS is the default local backend; Qdrant is for server-backed or disk\u002Fquantized vector storage.\n4. Validate generated artifacts before serving: `tiles\u002F`, `embeddings\u002Fshard_*.npz`, `index.faiss` or Qdrant `summary.json`, `metadata.npz`, and `articles.json`.\n\n## Read or Run\n\n- Read [workflows.md](references\u002Fworkflows.md) for end-to-end and stage-by-stage recipes.\n- Read [config-and-data-formats.md](references\u002Fconfig-and-data-formats.md) for `pixelrag.yaml`, source adapters, chunk manifests, embeddings, and index layouts.\n- Read [cli-reference.md](references\u002Fcli-reference.md) for flags and command selection.\n- Read [troubleshooting.md](references\u002Ftroubleshooting.md) for stale tiles, article IDs, Qdrant modes, GPU\u002Fmodel issues, and local-source surprises.\n- Run [pixelrag_tiny_index_config.py](scripts\u002Fpixelrag_tiny_index_config.py) to generate a tiny local-source config without downloading models.\n\n## Common Routes\n\n| Request | Action |\n| --- | --- |\n| \"Index this folder of PDFs\u002FMarkdown\u002Fimages\" | Generate a local-source `pixelrag.yaml`; use `pixelrag index build --device auto` for small runs or CUDA for production. |\n| \"Use Qdrant instead of FAISS\" | Set `index.backend: qdrant` and provide URL\u002Fcollection\u002Fclient\u002Fquantization config as needed. |\n| \"Re-run after source files changed\" | Trust the source-stamped tile manifests; use `--force` only for a clean rebuild. |\n| \"Department-filter search\" | Preserve subdirectory layout under the local source; `articles.json` stores the first subdirectory as `department`. |\n| \"I already have embeddings\" | Use `pixelrag build-index build --embeddings-dir ... --output-dir ...`. |\n| \"Now query this index\" | Route to `..\u002Fserve-search\u002FSKILL.md`. |\n\n## Validation Checklist\n\n- `pixelrag index build --help` lists `--device {auto,cpu,mps,cuda}`.\n- Local source only includes `.pdf`, `.html`, `.htm`, `.png`, `.jpg`, `.jpeg`, `.md`, and `.txt`.\n- Wide tiles are chunked into columns no wider than 875 px and rows of 1024 px where applicable.\n- `article_id` is propagated into `chunks.json` and embedding metadata.\n- `articles.json` titles, URLs\u002Fpaths, and department fields match the source set.\n- Qdrant `append` and `recreate` are explicit choices, never accidental overwrites.\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\u002Fsub-skills\u002Findex-build",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 index-build",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill index-build",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill index-build","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpixelrag\u002Fsub-skills\u002Findex-build\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcli-reference.md","REFERENCE","参考文档",2708,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpixelrag\u002Fsub-skills\u002Findex-build\u002Freferences\u002Fcli-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fconfig-and-data-formats.md",2719,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpixelrag\u002Fsub-skills\u002Findex-build\u002Freferences\u002Fconfig-and-data-formats.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",2508,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpixelrag\u002Fsub-skills\u002Findex-build\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fworkflows.md",2846,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpixelrag\u002Fsub-skills\u002Findex-build\u002Freferences\u002Fworkflows.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fpixelrag_tiny_index_config.py","SCRIPT","脚本",2436,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpixelrag\u002Fsub-skills\u002Findex-build\u002Fscripts\u002Fpixelrag_tiny_index_config.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":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":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]