[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796ZWMJVZRTQJKT37D7WPZ5":3,"skill-same:01M796ZWMJVZRTQJKT37D7WPZ5":67},{"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},"01M796ZWMJVZRTQJKT37D7WPZ5","chunking",null,"Configure and validate Unstructured post-partition chunking for RAG, embedding, and downstream processing. Use when an agent needs chunk_elements(), chunk_by_title(), partition-integrated chunking kwargs, character\u002Ftoken limits, overlap, table chunking behavior, or orig_elements metadata decisions.","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\u002Funstructured\u002Fsub-skills\u002Fchunking\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: chunking\ndescription: \"Configure and validate Unstructured post-partition chunking for\n  RAG, embedding, and downstream processing. Use when an agent needs\n  chunk_elements(), chunk_by_title(), partition-integrated chunking kwargs,\n  character\u002Ftoken limits, overlap, table chunking behavior, or orig_elements\n  metadata decisions.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Chunking\n\nUse this sub-skill after a document has been partitioned into Unstructured elements, or when a partition call should return chunks directly via `chunking_strategy`.\n\n## Start Here\n\n1. Choose the entry point:\n   - Use `unstructured.chunking.basic.chunk_elements(elements, ...)` when you already have elements and want sequential size-based chunks.\n   - Use `unstructured.chunking.title.chunk_by_title(elements, ...)` when `Title` elements should start sections and optional page boundaries should split sections.\n   - Use `partition(..., chunking_strategy=\"basic\" | \"by_title\", ...)` when the partitioner supports integrated chunking and you want one call.\n2. Pick one sizing mode:\n   - Character mode: `max_characters` is the hard maximum, `new_after_n_chars` is the soft preferred boundary.\n   - Token mode: `max_tokens` is the hard maximum, `new_after_n_tokens` is the soft preferred boundary, and `tokenizer` is required.\n3. Decide table handling before overlap:\n   - Default `isolate_table=True` keeps `Table` and `TableChunk` separate from surrounding text.\n   - Default `repeat_table_headers=True` repeats detected headers on continuation table chunks.\n   - Use `skip_table_chunking=True` only when oversized tables must pass through unchanged.\n4. Decide metadata weight:\n   - Default `include_orig_elements=True` preserves original elements in `metadata.orig_elements`.\n   - Set `include_orig_elements=False` for lighter JSON payloads when original metadata is not needed.\n\n## Key References\n\n- `references\u002Fapi-reference.md`: public functions, parameters, defaults, output element types, and validation rules.\n- `references\u002Fworkflows.md`: RAG, table-heavy, integrated partitioning, token-based, and validation workflows.\n- `references\u002Ftroubleshooting.md`: common `ValueError`s, token extra issues, overlap pollution, table edge cases, and metadata size trade-offs.\n- `scripts\u002Fchunk_elements_preview.py`: preview chunking behavior from element JSON and summarize chunk types, lengths, table metadata, and `orig_elements` counts.\n\n## Routing Boundaries\n\n- Route element creation, file parsing, strategies like OCR\u002Ftable extraction, and partition signatures to the `partitioning` sub-skill.\n- Route JSON schema interpretation, `elements_to_json()`, `elements_from_json()`, and serialized metadata payload design to the `elements-and-metadata` sub-skill.\n- Keep this sub-skill focused on chunking already-created elements or partition-integrated chunking arguments.\n\n## Quick Patterns\n\n```python\nfrom unstructured.chunking.title import chunk_by_title\n\nchunks = chunk_by_title(\n    elements,\n    max_characters=1200,\n    new_after_n_chars=900,\n    overlap=80,\n    overlap_all=False,\n    include_orig_elements=False,\n)\n```\n\n```python\nfrom unstructured.partition.auto import partition\n\nchunks = partition(\n    filename=\"report.pdf\",\n    chunking_strategy=\"by_title\",\n    max_characters=1500,\n    new_after_n_chars=1000,\n    combine_text_under_n_chars=200,\n    multipage_sections=False,\n)\n```\n\n## Review Checklist\n\n- Confirm the request uses one sizing mode, not both character and token limits.\n- Explain hard maximum versus soft maximum when recommending values.\n- State whether tables remain isolated, split into `TableChunk`, or pass through unchanged.\n- State whether `metadata.orig_elements` is retained and how that affects serialized size.\n- Warn before using `overlap_all=True`, because it can duplicate text across semantic chunk boundaries.\n","# Chunking\n\nUse this sub-skill after a document has been partitioned into Unstructured elements, or when a partition call should return chunks directly via `chunking_strategy`.\n\n## Start Here\n\n1. Choose the entry point:\n   - Use `unstructured.chunking.basic.chunk_elements(elements, ...)` when you already have elements and want sequential size-based chunks.\n   - Use `unstructured.chunking.title.chunk_by_title(elements, ...)` when `Title` elements should start sections and optional page boundaries should split sections.\n   - Use `partition(..., chunking_strategy=\"basic\" | \"by_title\", ...)` when the partitioner supports integrated chunking and you want one call.\n2. Pick one sizing mode:\n   - Character mode: `max_characters` is the hard maximum, `new_after_n_chars` is the soft preferred boundary.\n   - Token mode: `max_tokens` is the hard maximum, `new_after_n_tokens` is the soft preferred boundary, and `tokenizer` is required.\n3. Decide table handling before overlap:\n   - Default `isolate_table=True` keeps `Table` and `TableChunk` separate from surrounding text.\n   - Default `repeat_table_headers=True` repeats detected headers on continuation table chunks.\n   - Use `skip_table_chunking=True` only when oversized tables must pass through unchanged.\n4. Decide metadata weight:\n   - Default `include_orig_elements=True` preserves original elements in `metadata.orig_elements`.\n   - Set `include_orig_elements=False` for lighter JSON payloads when original metadata is not needed.\n\n## Key References\n\n- `references\u002Fapi-reference.md`: public functions, parameters, defaults, output element types, and validation rules.\n- `references\u002Fworkflows.md`: RAG, table-heavy, integrated partitioning, token-based, and validation workflows.\n- `references\u002Ftroubleshooting.md`: common `ValueError`s, token extra issues, overlap pollution, table edge cases, and metadata size trade-offs.\n- `scripts\u002Fchunk_elements_preview.py`: preview chunking behavior from element JSON and summarize chunk types, lengths, table metadata, and `orig_elements` counts.\n\n## Routing Boundaries\n\n- Route element creation, file parsing, strategies like OCR\u002Ftable extraction, and partition signatures to the `partitioning` sub-skill.\n- Route JSON schema interpretation, `elements_to_json()`, `elements_from_json()`, and serialized metadata payload design to the `elements-and-metadata` sub-skill.\n- Keep this sub-skill focused on chunking already-created elements or partition-integrated chunking arguments.\n\n## Quick Patterns\n\n```python\nfrom unstructured.chunking.title import chunk_by_title\n\nchunks = chunk_by_title(\n    elements,\n    max_characters=1200,\n    new_after_n_chars=900,\n    overlap=80,\n    overlap_all=False,\n    include_orig_elements=False,\n)\n```\n\n```python\nfrom unstructured.partition.auto import partition\n\nchunks = partition(\n    filename=\"report.pdf\",\n    chunking_strategy=\"by_title\",\n    max_characters=1500,\n    new_after_n_chars=1000,\n    combine_text_under_n_chars=200,\n    multipage_sections=False,\n)\n```\n\n## Review Checklist\n\n- Confirm the request uses one sizing mode, not both character and token limits.\n- Explain hard maximum versus soft maximum when recommending values.\n- State whether tables remain isolated, split into `TableChunk`, or pass through unchanged.\n- State whether `metadata.orig_elements` is retained and how that affects serialized size.\n- Warn before using `overlap_all=True`, because it can duplicate text across semantic chunk boundaries.\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\u002Funstructured\u002Fsub-skills\u002Fchunking",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 chunking",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill chunking",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill chunking","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funstructured\u002Fsub-skills\u002Fchunking\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",5846,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funstructured\u002Fsub-skills\u002Fchunking\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",5147,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funstructured\u002Fsub-skills\u002Fchunking\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",5383,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funstructured\u002Fsub-skills\u002Fchunking\u002Freferences\u002Fworkflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fchunk_elements_preview.py","SCRIPT","脚本",6376,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funstructured\u002Fsub-skills\u002Fchunking\u002Fscripts\u002Fchunk_elements_preview.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]