[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7970CWG80TFCJH842ADYVFE":3,"skill-same:01M7970CWG80TFCJH842ADYVFE":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},"01M7970CWG80TFCJH842ADYVFE","partitioning",null,"Partition local files, file-like objects, URLs, text, HTML, PDF\u002Fimage, Office, tabular, JSON\u002FNDJSON, XML, RST\u002FMD\u002FEPUB, email, and audio inputs into unstructured Element objects.","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\u002Fpartitioning\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: partitioning\ndescription: \"Partition local files, file-like objects, URLs, text, HTML,\n  PDF\u002Fimage, Office, tabular, JSON\u002FNDJSON, XML, RST\u002FMD\u002FEPUB, email, and audio\n  inputs into unstructured Element objects.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Partitioning\n\nUse this sub-skill when a task asks an agent to turn source documents into `unstructured.documents.elements.Element` objects or to diagnose why a document type cannot be partitioned. Route serialization\u002Fexport of elements to `elements-and-metadata`, post-partition chunking to `chunking`, embeddings to `embeddings`, and extraction-quality scoring to `evaluation`.\n\n## Start Here\n\n- Prefer `unstructured.partition.auto.partition()` when the corpus has mixed file types or when MIME\u002Fextension detection is acceptable.\n- Prefer document-specific `partition_*` APIs when a format has important knobs, such as PDF\u002Fimage strategy, HTML parser options, email attachment handling, or spreadsheet\u002Ftable behavior.\n- Run `python -m unstructured.cli doctor` or `unstructured doctor` before debugging optional dependency failures; use `--for pdf`, `--for image`, `--for doc`, `--for audio`, or `--file PATH` for targeted checks.\n- Use local partition APIs for offline processing. Treat API workflows as network\u002Fcredential-dependent and do not assume they are available in a normal local agent session.\n\n## Core Local API\n\n```python\nfrom unstructured.partition.auto import partition\n\nelements = partition(filename=\"docs\u002Freport.pdf\", strategy=\"auto\")\n```\n\n`partition()` accepts exactly one of `filename`, `file`, or `url`. For file-like objects, open in binary mode and pass `metadata_filename` when extension-based detection or element metadata should reflect a logical name:\n\n```python\nwith open(\"docs\u002Freport.pdf\", \"rb\") as file:\n    elements = partition(file=file, metadata_filename=\"report.pdf\", strategy=\"fast\")\n```\n\nImportant options:\n\n- `content_type`: overrides or supplements detection when the MIME type is known.\n- `encoding`: resolves non-UTF text\u002FHTML\u002FJSON decoding issues.\n- `headers`, `ssl_verify`, `request_timeout`: apply only when `url` is used; set a timeout explicitly for unreliable endpoints.\n- `languages`: preferred language\u002FOCR hint list, e.g. `languages=[\"eng\", \"spa\"]` or ISO codes that can map to Tesseract codes.\n- `detect_language_per_element`: stores language metadata per element instead of once per document.\n- `skip_infer_table_types`: controls table structure inference by file type; default skips PDF and common image types.\n- `starting_page_number`: shifts page metadata when partitioning a PDF section.\n\n## Format Routes\n\n- Text: `from unstructured.partition.text import partition_text`; accepts exactly one of `filename`, `file`, or `text`, plus `paragraph_grouper`.\n- HTML: `from unstructured.partition.html import partition_html`; accepts `filename`, `file`, `text`, or `url`; useful knobs include `skip_headers_and_footers`, `html_parser_version`, `image_alt_mode`, and URL request options.\n- PDF: `from unstructured.partition.pdf import partition_pdf`; choose `strategy`, table\u002Fimage\u002Fform options, page numbering, password, and pdfminer margins.\n- Image: `from unstructured.partition.image import partition_image`; use `strategy=\"hi_res\"` or `\"ocr_only\"`; `\"fast\"` is invalid for images.\n- Office: use `partition_docx`, `partition_doc`, `partition_pptx`, `partition_ppt`, `partition_xlsx`, and `partition_odt` for format-specific controls.\n- Email: use `partition_email` for `.eml` and `partition_msg` for Outlook `.msg`; inspect attachment options before recursively partitioning attachments.\n- Tabular: use `partition_csv`, `partition_tsv`, or `partition_xlsx`; table elements can contain `metadata.text_as_html` when table structure is inferred.\n- Markup\u002Fbooks: use `partition_md`, `partition_rst`, `partition_org`, `partition_xml`, and `partition_epub` for explicit handling.\n- JSON streams: `partition_json` expects an unstructured-style JSON array of element dictionaries; `partition_ndjson` handles newline-delimited element records.\n- Audio: `partition_audio` transcribes audio to elements and requires the audio extra plus `ffmpeg`.\n\nSee `references\u002Fapi-reference.md` for a compact API and dependency matrix.\n\n## PDF\u002FImage Strategy Rules\n\nUse `strategy=\"fast\"` for extractable PDF text when layout detection, OCR, image blocks, forms, or table HTML are not needed. Use `strategy=\"hi_res\"` when table structure, coordinates, images, layout segmentation, or form extraction matters. Use `strategy=\"ocr_only\"` for scanned PDFs\u002Fimages when OCR text is enough and layout segmentation is unnecessary. Use `strategy=\"auto\"` when the agent should let unstructured pick and fallback based on text extractability and installed dependencies.\n\n`auto` chooses PDF `hi_res` if table\u002Fimage extraction is requested, PDF `fast` when text is extractable, PDF `ocr_only` when text is not extractable, and image `hi_res` by default. If `unstructured_inference` or `unstructured_pytesseract` is missing, unstructured may warn and fall back between `hi_res`, `ocr_only`, and `fast`; if no viable path exists for a non-extractable PDF, it raises an error.\n\nPrefer `languages` over deprecated `ocr_languages`. Prefer `hi_res_model_name` over deprecated `model_name`. Prefer `skip_infer_table_types` over deprecated `pdf_infer_table_structure`.\n\n## Diagnostics Scripts\n\nBundled helpers live under this sub-skill's `scripts\u002F` directory:\n\n```bash\npython scripts\u002Fpartition_diagnostics.py --for pdf\npython scripts\u002Fpartition_diagnostics.py --file docs\u002Freport.pdf\npython scripts\u002Fpartition_diagnostics.py --partition docs\u002Freport.pdf --strategy fast --limit 5\npython scripts\u002Finspect_tables.py output\u002Felements.json --out-dir tables --index\n```\n\n`partition_diagnostics.py` wraps the public doctor\u002Fcapability APIs and can run a small local partition preview when the environment supports the target format. `inspect_tables.py` extracts `Table` element `metadata.text_as_html` values from exported JSON into standalone HTML files; it is a portable Python adaptation of the repository's user table-inspection shell script.\n\n## Workflow Pointers\n\n- For mixed corpora, inventory extensions first, install only required extras, run doctor for risky families, then partition with `partition()` and per-format overrides only where needed.\n- For PDF table extraction, use `strategy=\"hi_res\"` and set `skip_infer_table_types=[]` or call `partition_pdf(..., infer_table_structure=True)`; inspect table HTML with `scripts\u002Finspect_tables.py` after serializing elements.\n- For URL partitioning, always set `request_timeout`; for HTML pages prefer `partition_html(url=...)` if the URL is known to return HTML.\n- For API partitioning, require an endpoint, credentials, and network access; do not embed credentials in scripts or skill content.\n\n## Evidence\n\nThis sub-skill is grounded in the package metadata, public README guidance, partitioning modules, file type utilities, doctor\u002FCLI diagnostics, partition behavior tests, example document fixtures, and user helper scripts distilled into this bundled guidance.\n","# Partitioning\n\nUse this sub-skill when a task asks an agent to turn source documents into `unstructured.documents.elements.Element` objects or to diagnose why a document type cannot be partitioned. Route serialization\u002Fexport of elements to `elements-and-metadata`, post-partition chunking to `chunking`, embeddings to `embeddings`, and extraction-quality scoring to `evaluation`.\n\n## Start Here\n\n- Prefer `unstructured.partition.auto.partition()` when the corpus has mixed file types or when MIME\u002Fextension detection is acceptable.\n- Prefer document-specific `partition_*` APIs when a format has important knobs, such as PDF\u002Fimage strategy, HTML parser options, email attachment handling, or spreadsheet\u002Ftable behavior.\n- Run `python -m unstructured.cli doctor` or `unstructured doctor` before debugging optional dependency failures; use `--for pdf`, `--for image`, `--for doc`, `--for audio`, or `--file PATH` for targeted checks.\n- Use local partition APIs for offline processing. Treat API workflows as network\u002Fcredential-dependent and do not assume they are available in a normal local agent session.\n\n## Core Local API\n\n```python\nfrom unstructured.partition.auto import partition\n\nelements = partition(filename=\"docs\u002Freport.pdf\", strategy=\"auto\")\n```\n\n`partition()` accepts exactly one of `filename`, `file`, or `url`. For file-like objects, open in binary mode and pass `metadata_filename` when extension-based detection or element metadata should reflect a logical name:\n\n```python\nwith open(\"docs\u002Freport.pdf\", \"rb\") as file:\n    elements = partition(file=file, metadata_filename=\"report.pdf\", strategy=\"fast\")\n```\n\nImportant options:\n\n- `content_type`: overrides or supplements detection when the MIME type is known.\n- `encoding`: resolves non-UTF text\u002FHTML\u002FJSON decoding issues.\n- `headers`, `ssl_verify`, `request_timeout`: apply only when `url` is used; set a timeout explicitly for unreliable endpoints.\n- `languages`: preferred language\u002FOCR hint list, e.g. `languages=[\"eng\", \"spa\"]` or ISO codes that can map to Tesseract codes.\n- `detect_language_per_element`: stores language metadata per element instead of once per document.\n- `skip_infer_table_types`: controls table structure inference by file type; default skips PDF and common image types.\n- `starting_page_number`: shifts page metadata when partitioning a PDF section.\n\n## Format Routes\n\n- Text: `from unstructured.partition.text import partition_text`; accepts exactly one of `filename`, `file`, or `text`, plus `paragraph_grouper`.\n- HTML: `from unstructured.partition.html import partition_html`; accepts `filename`, `file`, `text`, or `url`; useful knobs include `skip_headers_and_footers`, `html_parser_version`, `image_alt_mode`, and URL request options.\n- PDF: `from unstructured.partition.pdf import partition_pdf`; choose `strategy`, table\u002Fimage\u002Fform options, page numbering, password, and pdfminer margins.\n- Image: `from unstructured.partition.image import partition_image`; use `strategy=\"hi_res\"` or `\"ocr_only\"`; `\"fast\"` is invalid for images.\n- Office: use `partition_docx`, `partition_doc`, `partition_pptx`, `partition_ppt`, `partition_xlsx`, and `partition_odt` for format-specific controls.\n- Email: use `partition_email` for `.eml` and `partition_msg` for Outlook `.msg`; inspect attachment options before recursively partitioning attachments.\n- Tabular: use `partition_csv`, `partition_tsv`, or `partition_xlsx`; table elements can contain `metadata.text_as_html` when table structure is inferred.\n- Markup\u002Fbooks: use `partition_md`, `partition_rst`, `partition_org`, `partition_xml`, and `partition_epub` for explicit handling.\n- JSON streams: `partition_json` expects an unstructured-style JSON array of element dictionaries; `partition_ndjson` handles newline-delimited element records.\n- Audio: `partition_audio` transcribes audio to elements and requires the audio extra plus `ffmpeg`.\n\nSee `references\u002Fapi-reference.md` for a compact API and dependency matrix.\n\n## PDF\u002FImage Strategy Rules\n\nUse `strategy=\"fast\"` for extractable PDF text when layout detection, OCR, image blocks, forms, or table HTML are not needed. Use `strategy=\"hi_res\"` when table structure, coordinates, images, layout segmentation, or form extraction matters. Use `strategy=\"ocr_only\"` for scanned PDFs\u002Fimages when OCR text is enough and layout segmentation is unnecessary. Use `strategy=\"auto\"` when the agent should let unstructured pick and fallback based on text extractability and installed dependencies.\n\n`auto` chooses PDF `hi_res` if table\u002Fimage extraction is requested, PDF `fast` when text is extractable, PDF `ocr_only` when text is not extractable, and image `hi_res` by default. If `unstructured_inference` or `unstructured_pytesseract` is missing, unstructured may warn and fall back between `hi_res`, `ocr_only`, and `fast`; if no viable path exists for a non-extractable PDF, it raises an error.\n\nPrefer `languages` over deprecated `ocr_languages`. Prefer `hi_res_model_name` over deprecated `model_name`. Prefer `skip_infer_table_types` over deprecated `pdf_infer_table_structure`.\n\n## Diagnostics Scripts\n\nBundled helpers live under this sub-skill's `scripts\u002F` directory:\n\n```bash\npython scripts\u002Fpartition_diagnostics.py --for pdf\npython scripts\u002Fpartition_diagnostics.py --file docs\u002Freport.pdf\npython scripts\u002Fpartition_diagnostics.py --partition docs\u002Freport.pdf --strategy fast --limit 5\npython scripts\u002Finspect_tables.py output\u002Felements.json --out-dir tables --index\n```\n\n`partition_diagnostics.py` wraps the public doctor\u002Fcapability APIs and can run a small local partition preview when the environment supports the target format. `inspect_tables.py` extracts `Table` element `metadata.text_as_html` values from exported JSON into standalone HTML files; it is a portable Python adaptation of the repository's user table-inspection shell script.\n\n## Workflow Pointers\n\n- For mixed corpora, inventory extensions first, install only required extras, run doctor for risky families, then partition with `partition()` and per-format overrides only where needed.\n- For PDF table extraction, use `strategy=\"hi_res\"` and set `skip_infer_table_types=[]` or call `partition_pdf(..., infer_table_structure=True)`; inspect table HTML with `scripts\u002Finspect_tables.py` after serializing elements.\n- For URL partitioning, always set `request_timeout`; for HTML pages prefer `partition_html(url=...)` if the URL is known to return HTML.\n- For API partitioning, require an endpoint, credentials, and network access; do not embed credentials in scripts or skill content.\n\n## Evidence\n\nThis sub-skill is grounded in the package metadata, public README guidance, partitioning modules, file type utilities, doctor\u002FCLI diagnostics, partition behavior tests, example document fixtures, and user helper scripts distilled into this bundled guidance.\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\u002Fpartitioning",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 partitioning",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill partitioning",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill partitioning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funstructured\u002Fsub-skills\u002Fpartitioning\u002FSKILL.md",[47,53,57,61,67],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",9175,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funstructured\u002Fsub-skills\u002Fpartitioning\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",5732,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funstructured\u002Fsub-skills\u002Fpartitioning\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",5935,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funstructured\u002Fsub-skills\u002Fpartitioning\u002Freferences\u002Fworkflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Finspect_tables.py","SCRIPT","脚本",6315,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funstructured\u002Fsub-skills\u002Fpartitioning\u002Fscripts\u002Finspect_tables.py",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fpartition_diagnostics.py",7040,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funstructured\u002Fsub-skills\u002Fpartitioning\u002Fscripts\u002Fpartition_diagnostics.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",[],[]]