[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7957ASFATWEK4FB0N2W4ZK7":3,"skill-same:01M7957ASFATWEK4FB0N2W4ZK7":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},"01M7957ASFATWEK4FB0N2W4ZK7","snips-nlu",null,"Use Snips NLU for intent parsing, slot filling, dataset\u002Fresource preparation, engine API workflows, CLI training\u002Fparsing, and troubleshooting.","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\u002Fsnips-nlu\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: snips-nlu\ndescription: \"Use Snips NLU for intent parsing, slot filling, dataset\u002Fresource\n  preparation, engine API workflows, CLI training\u002Fparsing, and troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Snips NLU\n\nUse this repo skill when a task involves Snips NLU (`snips-nlu` \u002F `snips_nlu`) for classical natural-language understanding: intent classification, slot filling, YAML\u002FJSON dataset authoring, language resources, Python engine APIs, CLI training\u002Fparsing, metrics, or persisted NLU engine artifacts.\n\nThis skill targets Snips NLU `0.20.2` and model format `0.20.0`.\n\n## Quick setup and health checks\n\nInstall the public package in a compatible Python environment:\n\n```bash\npip install snips-nlu\npython -m snips_nlu --help\npython -m snips_nlu version\npython -m snips_nlu model-version\n```\n\nFor this old release, prefer Python 3.8 when modern Python versions cannot resolve pinned compiled dependencies. Read `references\u002Finstallation-and-resources.md` for install\u002Fresource details and `references\u002Ftroubleshooting.md` for cross-cutting failures.\n\nRun the bundled read-only environment check when diagnosing setup:\n\n```bash\npython scripts\u002Fcheck_snips_nlu_environment.py --json\n```\n\nIf the workflow needs language resources, download or link them explicitly; helpers in this skill do not perform network downloads silently:\n\n```bash\npython -m snips_nlu download en\npython scripts\u002Fcheck_snips_nlu_environment.py --resource en --json\n```\n\n## Route by task\n\n| Task | Read |\n|---|---|\n| Create or validate a Snips NLU YAML\u002FJSON dataset, inspect entity schemas, convert YAML to JSON, or reason about supported languages\u002Fresources. | `sub-skills\u002Fdataset-and-resources\u002FSKILL.md` |\n| Use Python APIs such as `SnipsNLUEngine`, `fit`, `parse`, `get_intents`, `get_slots`, `persist`, `from_path`, configs, random seeds, or result schemas. | `sub-skills\u002Fengine-api\u002FSKILL.md` |\n| Build or troubleshoot `snips-nlu` \u002F `python -m snips_nlu` commands for `generate-dataset`, `train`, `parse`, `download`, `link`, versions, or metrics. | `sub-skills\u002Fcli-workflows\u002FSKILL.md` |\n| Decide whether this generated skill is current for a checkout\u002Fversion. | `references\u002Frepo-provenance.md` |\n\n## Common workflow map\n\n1. **Author data**: use `dataset-and-resources` to write YAML intent\u002Fentity files or JSON datasets.\n2. **Validate\u002Fconvert**: use bundled dataset scripts before training.\n3. **Prepare resources**: use CLI download\u002Flink commands only when network\u002Fresource setup is approved.\n4. **Train and parse**: use either the Python engine API (`engine-api`) or CLI command recipes (`cli-workflows`).\n5. **Persist and reload**: use `engine-api` for artifact layout, model-version compatibility, and safe persistence checks.\n6. **Evaluate**: use `cli-workflows` for metrics commands and optional `snips-nlu-metrics` dependency notes.\n\n## Important API and CLI anchors\n\nVerified public API signatures include:\n\n- `SnipsNLUEngine(config=None, **shared)`\n- `SnipsNLUEngine.fit(dataset, force_retrain=True)`\n- `SnipsNLUEngine.parse(text, intents=None, top_n=None)`\n- `SnipsNLUEngine.get_intents(text)` and `get_slots(text, intent)`\n- `SnipsNLUEngine.persist(path)` and `SnipsNLUEngine.from_path(path, **shared)`\n- `Dataset.from_yaml_files(language, filenames)`\n- `validate_and_format_dataset(dataset)`\n- `load_resources(name, required_resources=None)`\n\nVerified CLI commands include `generate-dataset`, `train`, `parse`, `download`, `download-all-languages`, `download-entity`, `download-language-entities`, `link`, `cross-val-metrics`, `train-test-metrics`, `version`, and `model-version`.\n\n## Boundaries and safety\n\n- Do not treat this as a modern LLM or neural sequence-model training skill; Snips NLU is a classical NLU package for intent\u002Fslot extraction.\n- Do not assume package install success on Python 3.11+ for Snips NLU `0.20.x`; use compatibility troubleshooting first.\n- Do not run network resource downloads, long metrics sweeps, or training against user data unless the user requested those side effects.\n- Do not rely on original repository docs, tests, or sample files at runtime; this skill bundles the needed references and helper scripts.\n","# Snips NLU\n\nUse this repo skill when a task involves Snips NLU (`snips-nlu` \u002F `snips_nlu`) for classical natural-language understanding: intent classification, slot filling, YAML\u002FJSON dataset authoring, language resources, Python engine APIs, CLI training\u002Fparsing, metrics, or persisted NLU engine artifacts.\n\nThis skill targets Snips NLU `0.20.2` and model format `0.20.0`.\n\n## Quick setup and health checks\n\nInstall the public package in a compatible Python environment:\n\n```bash\npip install snips-nlu\npython -m snips_nlu --help\npython -m snips_nlu version\npython -m snips_nlu model-version\n```\n\nFor this old release, prefer Python 3.8 when modern Python versions cannot resolve pinned compiled dependencies. Read `references\u002Finstallation-and-resources.md` for install\u002Fresource details and `references\u002Ftroubleshooting.md` for cross-cutting failures.\n\nRun the bundled read-only environment check when diagnosing setup:\n\n```bash\npython scripts\u002Fcheck_snips_nlu_environment.py --json\n```\n\nIf the workflow needs language resources, download or link them explicitly; helpers in this skill do not perform network downloads silently:\n\n```bash\npython -m snips_nlu download en\npython scripts\u002Fcheck_snips_nlu_environment.py --resource en --json\n```\n\n## Route by task\n\n| Task | Read |\n|---|---|\n| Create or validate a Snips NLU YAML\u002FJSON dataset, inspect entity schemas, convert YAML to JSON, or reason about supported languages\u002Fresources. | `sub-skills\u002Fdataset-and-resources\u002FSKILL.md` |\n| Use Python APIs such as `SnipsNLUEngine`, `fit`, `parse`, `get_intents`, `get_slots`, `persist`, `from_path`, configs, random seeds, or result schemas. | `sub-skills\u002Fengine-api\u002FSKILL.md` |\n| Build or troubleshoot `snips-nlu` \u002F `python -m snips_nlu` commands for `generate-dataset`, `train`, `parse`, `download`, `link`, versions, or metrics. | `sub-skills\u002Fcli-workflows\u002FSKILL.md` |\n| Decide whether this generated skill is current for a checkout\u002Fversion. | `references\u002Frepo-provenance.md` |\n\n## Common workflow map\n\n1. **Author data**: use `dataset-and-resources` to write YAML intent\u002Fentity files or JSON datasets.\n2. **Validate\u002Fconvert**: use bundled dataset scripts before training.\n3. **Prepare resources**: use CLI download\u002Flink commands only when network\u002Fresource setup is approved.\n4. **Train and parse**: use either the Python engine API (`engine-api`) or CLI command recipes (`cli-workflows`).\n5. **Persist and reload**: use `engine-api` for artifact layout, model-version compatibility, and safe persistence checks.\n6. **Evaluate**: use `cli-workflows` for metrics commands and optional `snips-nlu-metrics` dependency notes.\n\n## Important API and CLI anchors\n\nVerified public API signatures include:\n\n- `SnipsNLUEngine(config=None, **shared)`\n- `SnipsNLUEngine.fit(dataset, force_retrain=True)`\n- `SnipsNLUEngine.parse(text, intents=None, top_n=None)`\n- `SnipsNLUEngine.get_intents(text)` and `get_slots(text, intent)`\n- `SnipsNLUEngine.persist(path)` and `SnipsNLUEngine.from_path(path, **shared)`\n- `Dataset.from_yaml_files(language, filenames)`\n- `validate_and_format_dataset(dataset)`\n- `load_resources(name, required_resources=None)`\n\nVerified CLI commands include `generate-dataset`, `train`, `parse`, `download`, `download-all-languages`, `download-entity`, `download-language-entities`, `link`, `cross-val-metrics`, `train-test-metrics`, `version`, and `model-version`.\n\n## Boundaries and safety\n\n- Do not treat this as a modern LLM or neural sequence-model training skill; Snips NLU is a classical NLU package for intent\u002Fslot extraction.\n- Do not assume package install success on Python 3.11+ for Snips NLU `0.20.x`; use compatibility troubleshooting first.\n- Do not run network resource downloads, long metrics sweeps, or training against user data unless the user requested those side effects.\n- Do not rely on original repository docs, tests, or sample files at runtime; this skill bundles the needed references and helper scripts.\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\u002Fsnips-nlu",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 snips-nlu",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill snips-nlu",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill snips-nlu","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsnips-nlu\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Finstallation-and-resources.md","REFERENCE","参考文档",4545,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsnips-nlu\u002Freferences\u002Finstallation-and-resources.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-provenance.md",2777,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsnips-nlu\u002Freferences\u002Frepo-provenance.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-routing-metadata.json",432,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsnips-nlu\u002Freferences\u002Frepo-routing-metadata.json",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",4655,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsnips-nlu\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fcheck_snips_nlu_environment.py","SCRIPT","脚本",5958,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsnips-nlu\u002Fscripts\u002Fcheck_snips_nlu_environment.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",[],[]]