[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78VTRMB0KXEQZCVSAHM0FA5":3,"skill-same:01M78VTRMB0KXEQZCVSAHM0FA5":70},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M78VTRMB0KXEQZCVSAHM0FA5","deepke",null,"Route DeepKE knowledge extraction workflows across supervised extraction, data prep, triples, LLMs, and MCP tools.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeepke\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: deepke\ndescription: \"Route DeepKE knowledge extraction workflows across supervised\n  extraction, data prep, triples, LLMs, and MCP tools.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# DeepKE repo skill\n\nUse this skill when a task asks how to use, configure, validate, or troubleshoot DeepKE for knowledge extraction: named entity recognition, relation extraction, attribute extraction, event extraction, relational triple extraction, instruction\u002FLLM knowledge graph construction, data conversion, weak\u002Fdistant supervision, or the local DeepKE MCP wrapper.\n\n## First route the request\n\n| User intent | Read\u002Fuse |\n| --- | --- |\n| Standard\u002Ffew-shot\u002Fmultimodal\u002Fcross-domain NER, standard\u002Ffew-shot\u002Fdocument\u002Fmultimodal RE, AE, EE, or cnSchema quick-load extraction | [sub-skills\u002Fsupervised-extraction\u002FSKILL.md](sub-skills\u002Fsupervised-extraction\u002FSKILL.md) |\n| Annotation export conversion, NER BIO files, RE\u002FAE CSV files, weak NER dictionary labeling, or distant RE labeling | [sub-skills\u002Fdata-preparation\u002FSKILL.md](sub-skills\u002Fdata-preparation\u002FSKILL.md) |\n| PRGC, PURE, ASP, MT5\u002FCCKS, cnSchema triple workflows, or MT5 prediction-to-`kg` conversion | [sub-skills\u002Ftriple-extraction\u002FSKILL.md](sub-skills\u002Ftriple-extraction\u002FSKILL.md) |\n| DeepKE-LLM, InstructKGC, OneKE, LLMICL\u002FAPI prompting, UnleashLLMRE, CodeKGC, CPM-Bee, LoRA\u002FP-tuning\u002FOpenDelta | [sub-skills\u002Fllm-workflows\u002FSKILL.md](sub-skills\u002Fllm-workflows\u002FSKILL.md) |\n| DeepKE MCP server\u002Fclient wrapper, local tool exposure, stdio server diagnostics, or MCP TSV conversion | [sub-skills\u002Fmcp-tools\u002FSKILL.md](sub-skills\u002Fmcp-tools\u002FSKILL.md) |\n| Unsure whether DeepKE is installed or which broad area is available | Run [scripts\u002Fcheck_deepke_core.py](scripts\u002Fcheck_deepke_core.py), then route to a focused sub-skill. |\n\n## Core operating rules\n\n1. **Classify the task before running anything**: data conversion, training, prediction, post-processing, API\u002FLLM call, MCP deployment, or troubleshooting each has a different safety profile.\n2. **Use bundled references\u002Fscripts instead of the original checkout**: this generated skill is self-contained. Do not require the original repository tree just to answer workflow questions or run safe converters\u002Fcheckers.\n3. **Treat long runs as explicit operations**: BERT\u002FCLIP\u002FT5\u002FMT5\u002FOneKE fine-tuning, DeepSpeed, Apex, multimodal training, and API calls need user approval for compute, downloads, credentials, and runtime.\n4. **Validate data before blaming models**: check filenames, JSONL versus JSON array shape, labels, offsets, schema size, train\u002Fdev\u002Ftest splits, and parsed outputs.\n5. **Keep credentials and private paths out of shared files**: API keys, endpoint tokens, local checkpoint paths, and environment prefixes belong in local runtime configuration only.\n6. **Report backend limits honestly**: CPU diagnostics can prove import and converter behavior, but not CUDA\u002FApex\u002FDeepSpeed\u002Flarge-model runtime readiness.\n\n## Safe top-level diagnostic\n\nFrom this skill directory, run:\n\n```bash\npython scripts\u002Fcheck_deepke_core.py --json\n```\n\nThis imports representative DeepKE modules and common dependencies and reports CUDA visibility. It does not train, download, load model weights, call APIs, or mutate configs. Use focused checkers in the sub-skills for task-specific path and dependency checks.\n\n## Focused bundled scripts\n\n- `sub-skills\u002Fsupervised-extraction\u002Fscripts\u002Fcheck_supervised_env.py`: safe import\u002Fdata\u002Fcheckpoint diagnostics for NER\u002FRE\u002FAE\u002FEE\u002FcnSchema workflows.\n- `sub-skills\u002Fdata-preparation\u002Fscripts\u002Fconvert_supervised_data.py`: labeled JSON\u002FDOCX\u002FXLSX to DeepKE NER TXT or RE\u002FAE CSV.\n- `sub-skills\u002Fdata-preparation\u002Fscripts\u002Fprepare_weaksupervised_data.py`: dictionary-based NER weak supervision.\n- `sub-skills\u002Fdata-preparation\u002Fscripts\u002Fds_label_data.py`: RE distant supervision from triples.\n- `sub-skills\u002Ftriple-extraction\u002Fscripts\u002Fcheck_triple_env.py`: safe PRGC\u002FPURE\u002FASP\u002FMT5\u002FcnSchema dependency\u002Fpath diagnostic.\n- `sub-skills\u002Ftriple-extraction\u002Fscripts\u002Fconvert_mt5_predictions.py`: MT5\u002FCCKS prediction conversion into JSONL records with parsed `kg` triples.\n- `sub-skills\u002Fllm-workflows\u002Fscripts\u002Fcheck_llm_workflow_env.py`: safe DeepKE-LLM package\u002FAPI\u002FCUDA\u002Fpath diagnostic.\n- `sub-skills\u002Fllm-workflows\u002Fscripts\u002Fconvert_ie_instruction.py`: simple standalone IE\u002FKG record to instruction JSONL converter.\n- `sub-skills\u002Fmcp-tools\u002Fscripts\u002Fcheck_mcp_env.py`: MCP wrapper import\u002Fenv diagnostic without launching the server.\n- `sub-skills\u002Fmcp-tools\u002Fscripts\u002Fconvert_text_to_tsv.py`: event-extraction text-to-TSV helper adapted from the MCP tools.\n\n## Repo-level references\n\n- [references\u002Frepo-overview.md](references\u002Frepo-overview.md): capability map, environment families, and known coverage limits.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md): cross-cutting dependency, backend, data, and safety troubleshooting.\n- [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md): source evidence, version, verification baseline, and refresh notes.\n","# DeepKE repo skill\n\nUse this skill when a task asks how to use, configure, validate, or troubleshoot DeepKE for knowledge extraction: named entity recognition, relation extraction, attribute extraction, event extraction, relational triple extraction, instruction\u002FLLM knowledge graph construction, data conversion, weak\u002Fdistant supervision, or the local DeepKE MCP wrapper.\n\n## First route the request\n\n| User intent | Read\u002Fuse |\n| --- | --- |\n| Standard\u002Ffew-shot\u002Fmultimodal\u002Fcross-domain NER, standard\u002Ffew-shot\u002Fdocument\u002Fmultimodal RE, AE, EE, or cnSchema quick-load extraction | [sub-skills\u002Fsupervised-extraction\u002FSKILL.md](sub-skills\u002Fsupervised-extraction\u002FSKILL.md) |\n| Annotation export conversion, NER BIO files, RE\u002FAE CSV files, weak NER dictionary labeling, or distant RE labeling | [sub-skills\u002Fdata-preparation\u002FSKILL.md](sub-skills\u002Fdata-preparation\u002FSKILL.md) |\n| PRGC, PURE, ASP, MT5\u002FCCKS, cnSchema triple workflows, or MT5 prediction-to-`kg` conversion | [sub-skills\u002Ftriple-extraction\u002FSKILL.md](sub-skills\u002Ftriple-extraction\u002FSKILL.md) |\n| DeepKE-LLM, InstructKGC, OneKE, LLMICL\u002FAPI prompting, UnleashLLMRE, CodeKGC, CPM-Bee, LoRA\u002FP-tuning\u002FOpenDelta | [sub-skills\u002Fllm-workflows\u002FSKILL.md](sub-skills\u002Fllm-workflows\u002FSKILL.md) |\n| DeepKE MCP server\u002Fclient wrapper, local tool exposure, stdio server diagnostics, or MCP TSV conversion | [sub-skills\u002Fmcp-tools\u002FSKILL.md](sub-skills\u002Fmcp-tools\u002FSKILL.md) |\n| Unsure whether DeepKE is installed or which broad area is available | Run [scripts\u002Fcheck_deepke_core.py](scripts\u002Fcheck_deepke_core.py), then route to a focused sub-skill. |\n\n## Core operating rules\n\n1. **Classify the task before running anything**: data conversion, training, prediction, post-processing, API\u002FLLM call, MCP deployment, or troubleshooting each has a different safety profile.\n2. **Use bundled references\u002Fscripts instead of the original checkout**: this generated skill is self-contained. Do not require the original repository tree just to answer workflow questions or run safe converters\u002Fcheckers.\n3. **Treat long runs as explicit operations**: BERT\u002FCLIP\u002FT5\u002FMT5\u002FOneKE fine-tuning, DeepSpeed, Apex, multimodal training, and API calls need user approval for compute, downloads, credentials, and runtime.\n4. **Validate data before blaming models**: check filenames, JSONL versus JSON array shape, labels, offsets, schema size, train\u002Fdev\u002Ftest splits, and parsed outputs.\n5. **Keep credentials and private paths out of shared files**: API keys, endpoint tokens, local checkpoint paths, and environment prefixes belong in local runtime configuration only.\n6. **Report backend limits honestly**: CPU diagnostics can prove import and converter behavior, but not CUDA\u002FApex\u002FDeepSpeed\u002Flarge-model runtime readiness.\n\n## Safe top-level diagnostic\n\nFrom this skill directory, run:\n\n```bash\npython scripts\u002Fcheck_deepke_core.py --json\n```\n\nThis imports representative DeepKE modules and common dependencies and reports CUDA visibility. It does not train, download, load model weights, call APIs, or mutate configs. Use focused checkers in the sub-skills for task-specific path and dependency checks.\n\n## Focused bundled scripts\n\n- `sub-skills\u002Fsupervised-extraction\u002Fscripts\u002Fcheck_supervised_env.py`: safe import\u002Fdata\u002Fcheckpoint diagnostics for NER\u002FRE\u002FAE\u002FEE\u002FcnSchema workflows.\n- `sub-skills\u002Fdata-preparation\u002Fscripts\u002Fconvert_supervised_data.py`: labeled JSON\u002FDOCX\u002FXLSX to DeepKE NER TXT or RE\u002FAE CSV.\n- `sub-skills\u002Fdata-preparation\u002Fscripts\u002Fprepare_weaksupervised_data.py`: dictionary-based NER weak supervision.\n- `sub-skills\u002Fdata-preparation\u002Fscripts\u002Fds_label_data.py`: RE distant supervision from triples.\n- `sub-skills\u002Ftriple-extraction\u002Fscripts\u002Fcheck_triple_env.py`: safe PRGC\u002FPURE\u002FASP\u002FMT5\u002FcnSchema dependency\u002Fpath diagnostic.\n- `sub-skills\u002Ftriple-extraction\u002Fscripts\u002Fconvert_mt5_predictions.py`: MT5\u002FCCKS prediction conversion into JSONL records with parsed `kg` triples.\n- `sub-skills\u002Fllm-workflows\u002Fscripts\u002Fcheck_llm_workflow_env.py`: safe DeepKE-LLM package\u002FAPI\u002FCUDA\u002Fpath diagnostic.\n- `sub-skills\u002Fllm-workflows\u002Fscripts\u002Fconvert_ie_instruction.py`: simple standalone IE\u002FKG record to instruction JSONL converter.\n- `sub-skills\u002Fmcp-tools\u002Fscripts\u002Fcheck_mcp_env.py`: MCP wrapper import\u002Fenv diagnostic without launching the server.\n- `sub-skills\u002Fmcp-tools\u002Fscripts\u002Fconvert_text_to_tsv.py`: event-extraction text-to-TSV helper adapted from the MCP tools.\n\n## Repo-level references\n\n- [references\u002Frepo-overview.md](references\u002Frepo-overview.md): capability map, environment families, and known coverage limits.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md): cross-cutting dependency, backend, data, and safety troubleshooting.\n- [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md): source evidence, version, verification baseline, and refresh notes.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fdeepke",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill deepke",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill deepke",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill deepke","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeepke\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Frepo-overview.md","REFERENCE","参考文档",4091,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeepke\u002Freferences\u002Frepo-overview.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",3642,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeepke\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",509,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeepke\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",4033,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeepke\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_deepke_core.py","SCRIPT","脚本",5301,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeepke\u002Fscripts\u002Fcheck_deepke_core.py",[71,79,86,93,100,107],{"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":75,"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.","Apache-2.0","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":75,"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":75,"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":75,"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":75,"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":75,"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",[],[]]