[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78YZFSX96XHHWWFSWQSMP10":3,"skill-same:01M78YZFSX96XHHWWFSWQSMP10":63},{"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},"01M78YZFSX96XHHWWFSWQSMP10","visualization",null,"Use LangExtract visualization to save, reload, inspect, and render AnnotatedDocument JSONL outputs without model inference.","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\u002Flangextract\u002Fsub-skills\u002Fvisualization\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: visualization\ndescription: \"Use LangExtract visualization to save, reload, inspect, and render\n  AnnotatedDocument JSONL outputs without model inference.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# LangExtract Visualization\n\nUse this sub-skill when the user already has LangExtract `AnnotatedDocument`\nobjects or saved JSONL output and wants to persist, reload, inspect, or render an\ninteractive HTML visualization without calling a model.\n\n## Route first\n\n- To create new extraction results with `lx.extract()`, read\n  `..\u002Fextraction\u002FSKILL.md` first.\n- For model IDs, API keys, Vertex\u002FOpenAI batch settings, Ollama, or provider\n  credentials, read `..\u002Fproviders\u002FSKILL.md`.\n- For frontend code changes beyond the HTML generated by LangExtract, treat the\n  request as unsupported by this repo skill and explain that custom UI work is a\n  gap.\n\n## Common workflows\n\n1. **Save one or more annotated documents to JSONL.** Use\n   `lx.io.save_annotated_documents([doc], output_dir=..., output_name=..., show_progress=...)`.\n   The default filename is `data.jsonl`; when `output_dir=None`, LangExtract\n   writes under a relative `test_output\u002F` directory. Prefer an explicit output\n   directory in agent-written code.\n2. **Reload JSONL for later inspection.** Use\n   `lx.io.load_annotated_documents_jsonl(path, show_progress=...)` and\n   materialize the iterator only when the file is small enough. Use\n   `langextract.data_lib` conversions when you need JSON dictionaries rather\n   than dataclass objects.\n3. **Visualize a document or JSONL file.** Use `lx.visualize(doc_or_jsonl_path)`\n   or `langextract.visualization.visualize(...)` with\n   `animation_speed`, `show_legend`, and `gif_optimized` as needed. A JSONL path\n   visualizes the first document in the file; load and select a document\n   yourself for multi-document outputs.\n4. **Write HTML safely.** In a notebook, the return value may be an\n   `IPython.display.HTML` object with `.data`; in plain Python it is a string.\n   Use `payload = html.data if hasattr(html, \"data\") else html` before writing.\n5. **Check grounding before blaming visualization.** Only extractions with a\n   usable `char_interval` can be highlighted. Missing or invalid intervals\n   usually mean the extraction was ungrounded or manually constructed with bad\n   offsets.\n\nRead `references\u002Fworkflows.md` for verified signatures, JSONL round trips,\nselection patterns, and HTML writing details. Read\n`references\u002Ftroubleshooting.md` for save\u002Fload\u002Fvisualization failures and their\nfixes.\n\n## Bundled helper\n\nRun `scripts\u002Fsave_and_visualize.py` when you need a no-model smoke helper that\ncreates a handcrafted `AnnotatedDocument`, saves JSONL, reloads it, generates\nHTML, and writes all outputs under a caller-selected directory:\n\n```bash\npython scripts\u002Fsave_and_visualize.py --output-dir .\u002Flx-viz-demo\n```\n\nThe helper does not require API keys, provider credentials, network access, or\nsource-repository files.\n\n## Verification anchors\n\nThis guidance is based on the public README save\u002Fvisualization snippets,\nlong-document and medication visualization examples, implementation behavior in\n`langextract\u002Fio.py`, `langextract\u002Fvisualization.py`, `langextract\u002Fdata_lib.py`,\n`langextract\u002Fprogress.py`, and `langextract\u002Fcore\u002Fdata.py`, installed-package\nsignature inspection, and the safe native candidate families `io_test.py`,\n`data_lib_test.py`, `visualization_test.py`, and `progress_test.py`.\n","# LangExtract Visualization\n\nUse this sub-skill when the user already has LangExtract `AnnotatedDocument`\nobjects or saved JSONL output and wants to persist, reload, inspect, or render an\ninteractive HTML visualization without calling a model.\n\n## Route first\n\n- To create new extraction results with `lx.extract()`, read\n  `..\u002Fextraction\u002FSKILL.md` first.\n- For model IDs, API keys, Vertex\u002FOpenAI batch settings, Ollama, or provider\n  credentials, read `..\u002Fproviders\u002FSKILL.md`.\n- For frontend code changes beyond the HTML generated by LangExtract, treat the\n  request as unsupported by this repo skill and explain that custom UI work is a\n  gap.\n\n## Common workflows\n\n1. **Save one or more annotated documents to JSONL.** Use\n   `lx.io.save_annotated_documents([doc], output_dir=..., output_name=..., show_progress=...)`.\n   The default filename is `data.jsonl`; when `output_dir=None`, LangExtract\n   writes under a relative `test_output\u002F` directory. Prefer an explicit output\n   directory in agent-written code.\n2. **Reload JSONL for later inspection.** Use\n   `lx.io.load_annotated_documents_jsonl(path, show_progress=...)` and\n   materialize the iterator only when the file is small enough. Use\n   `langextract.data_lib` conversions when you need JSON dictionaries rather\n   than dataclass objects.\n3. **Visualize a document or JSONL file.** Use `lx.visualize(doc_or_jsonl_path)`\n   or `langextract.visualization.visualize(...)` with\n   `animation_speed`, `show_legend`, and `gif_optimized` as needed. A JSONL path\n   visualizes the first document in the file; load and select a document\n   yourself for multi-document outputs.\n4. **Write HTML safely.** In a notebook, the return value may be an\n   `IPython.display.HTML` object with `.data`; in plain Python it is a string.\n   Use `payload = html.data if hasattr(html, \"data\") else html` before writing.\n5. **Check grounding before blaming visualization.** Only extractions with a\n   usable `char_interval` can be highlighted. Missing or invalid intervals\n   usually mean the extraction was ungrounded or manually constructed with bad\n   offsets.\n\nRead `references\u002Fworkflows.md` for verified signatures, JSONL round trips,\nselection patterns, and HTML writing details. Read\n`references\u002Ftroubleshooting.md` for save\u002Fload\u002Fvisualization failures and their\nfixes.\n\n## Bundled helper\n\nRun `scripts\u002Fsave_and_visualize.py` when you need a no-model smoke helper that\ncreates a handcrafted `AnnotatedDocument`, saves JSONL, reloads it, generates\nHTML, and writes all outputs under a caller-selected directory:\n\n```bash\npython scripts\u002Fsave_and_visualize.py --output-dir .\u002Flx-viz-demo\n```\n\nThe helper does not require API keys, provider credentials, network access, or\nsource-repository files.\n\n## Verification anchors\n\nThis guidance is based on the public README save\u002Fvisualization snippets,\nlong-document and medication visualization examples, implementation behavior in\n`langextract\u002Fio.py`, `langextract\u002Fvisualization.py`, `langextract\u002Fdata_lib.py`,\n`langextract\u002Fprogress.py`, and `langextract\u002Fcore\u002Fdata.py`, installed-package\nsignature inspection, and the safe native candidate families `io_test.py`,\n`data_lib_test.py`, `visualization_test.py`, and `progress_test.py`.\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\u002Flangextract\u002Fsub-skills\u002Fvisualization",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 visualization",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill visualization",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill visualization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangextract\u002Fsub-skills\u002Fvisualization\u002FSKILL.md",[47,53,57],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Ftroubleshooting.md","REFERENCE","参考文档",6403,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangextract\u002Fsub-skills\u002Fvisualization\u002Freferences\u002Ftroubleshooting.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fworkflows.md",7378,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangextract\u002Fsub-skills\u002Fvisualization\u002Freferences\u002Fworkflows.md",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Fsave_and_visualize.py","SCRIPT","脚本",8309,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangextract\u002Fsub-skills\u002Fvisualization\u002Fscripts\u002Fsave_and_visualize.py",[64,71,78,85,92,99],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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",[],[]]