[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796SN9QJB48MGCZKW4SQERY":3,"skill-same:01M796SN9QJB48MGCZKW4SQERY":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},"01M796SN9QJB48MGCZKW4SQERY","txtai",null,"Use txtai for semantic search, embeddings databases, RAG, LLM orchestration, agents, deterministic workflows, and API deployment.","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\u002Ftxtai\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: txtai\ndescription: \"Use txtai for semantic search, embeddings databases, RAG, LLM\n  orchestration, agents, deterministic workflows, and API deployment.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# txtai\n\ntxtai is an all-in-one Python AI framework for semantic search, embeddings databases, retrieval augmented generation (RAG), LLM orchestration, agents, deterministic workflows, and FastAPI\u002FOpenAI-compatible services.\n\nUse this root skill to choose the right txtai sub-skill, install the correct optional extras, and run safe environment checks. Keep detailed workflows in the linked sub-skills and references.\n\n## Start Here\n\n1. Confirm the package import and version.\n   ```bash\n   python - \u003C\u003C'PY'\n   import importlib.metadata\n   import txtai\n   print(importlib.metadata.version(\"txtai\"))\n   print(txtai.Embeddings, txtai.Application, txtai.Workflow)\n   PY\n   ```\n2. Read [references\u002Finstallation-and-extras.md](references\u002Finstallation-and-extras.md) before installing optional dependencies.\n3. Run `python scripts\u002Fcheck_txtai_environment.py --help` to inspect imports and optional capabilities without downloading models.\n4. Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when imports, model backends, optional extras, config files, API startup, or offline runs fail.\n5. Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before deciding whether this skill is current for a source checkout.\n\n## Route By Task\n\n| User task | Read |\n| --- | --- |\n| Build an embeddings index, semantic search, SQL search, hybrid sparse+dense search, graph search, object storage, subindexes, save\u002Fload, or index maintenance | [sub-skills\u002Fembeddings-search\u002FSKILL.md](sub-skills\u002Fembeddings-search\u002FSKILL.md) |\n| Compose deterministic pipelines\u002Fworkflows for extraction, chunking, summarization, translation, transcription, image\u002Faudio\u002Fdata processing, YAML task chains, schedules, or lazy generator debugging | [sub-skills\u002Fpipelines-and-workflows\u002FSKILL.md](sub-skills\u002Fpipelines-and-workflows\u002FSKILL.md) |\n| Build RAG, direct LLM calls, txtai `Agent` tools, embeddings-backed tools, agent teams, prompt templates, or backend selection for hosted\u002Flocal models | [sub-skills\u002Fagents-and-llm-orchestration\u002FSKILL.md](sub-skills\u002Fagents-and-llm-orchestration\u002FSKILL.md) |\n| Configure `Application`, serve FastAPI\u002FUvicorn APIs, OpenAI-compatible endpoints, MCP, auth, custom endpoints, clustering, Docker\u002Fcloud\u002Fserverless, observability, or console usage | [sub-skills\u002Fapi-and-deployment\u002FSKILL.md](sub-skills\u002Fapi-and-deployment\u002FSKILL.md) |\n\n## Installation Choices\n\nInstall the smallest dependency set that matches the task:\n\n```bash\npip install txtai\npip install \"txtai[api]\"       # FastAPI, OpenAI-compatible API, MCP\u002Fservice routes\npip install \"txtai[agent]\"     # Agent support and smolagents integration\npip install \"txtai[pipeline]\"  # broad pipeline extras; prefer narrower groups when possible\npip install \"txtai[workflow]\"  # scheduling, file\u002Fdata workflow extras\npip install \"txtai[graph]\"     # graph\u002Fnetwork search extras\npip install \"txtai[database]\"  # DuckDB\u002FSQLAlchemy database extras\n```\n\nAvoid `txtai[all]` unless the user explicitly needs nearly every optional subsystem. txtai optional groups can pull large ML, audio, image, database, API, cloud, or CUDA-adjacent packages. See [references\u002Finstallation-and-extras.md](references\u002Finstallation-and-extras.md) for the full group map.\n\n## Public API Anchors\n\n- `txtai.Embeddings(config=None, models=None, **kwargs)` builds and queries embeddings databases.\n- `txtai.Application(config, loaddata=True)` loads YAML\u002Fdict application config for APIs, pipelines, workflows, agents, and embeddings.\n- `txtai.Workflow(tasks, batch=100, workers=None, name=None, stream=None)` chains callable tasks and yields lazy generator output.\n- `txtai.LLM(path=None, method=None, **kwargs)` runs local, hosted, or custom generation backends.\n- `txtai.RAG(similarity, path, ..., template=None, context=None, output=\"default\", system=None, **kwargs)` joins retrieval with generation.\n- `txtai.Agent(model=..., tools=[...], max_steps=...)` requires the agent extra; without it, imports can resolve to a placeholder that raises when constructed.\n\n## Common Routing Pitfalls\n\n- If a prompt asks for a chatbot that answers from documents, split the work: use `embeddings-search` to build the store, then `agents-and-llm-orchestration` for `RAG` templates and generation.\n- If a prompt asks for repeatable extraction\u002Fsummarization\u002Ftranslation over many items, prefer `pipelines-and-workflows`; use agents only when tool choice or multi-step reasoning is required.\n- If a prompt asks for a service endpoint, route to `api-and-deployment` even when the underlying route calls embeddings, workflows, or RAG.\n- If a prompt names SQL, `similar(...)`, metadata filtering, graph traversal, or object retrieval, route to `embeddings-search` first.\n- If a prompt names `CONFIG=app.yml`, `uvicorn`, `\u002Fv1\u002Fchat\u002Fcompletions`, `\u002Fmcp`, `TOKEN`, Docker, cloud, or console commands, route to `api-and-deployment`.\n\n## Validation Helpers\n\n- `python scripts\u002Fcheck_txtai_environment.py` checks core imports, package version, optional modules, and top-level constructor signatures.\n- `python sub-skills\u002Fembeddings-search\u002Fscripts\u002Fsemantic_search_smoke.py --run --sql` runs a no-download embeddings smoke check with external vectors.\n- `python sub-skills\u002Fpipelines-and-workflows\u002Fscripts\u002Fworkflow_smoke.py --mode all` runs no-download deterministic workflow checks.\n- `python sub-skills\u002Fagents-and-llm-orchestration\u002Fscripts\u002Frag_config_template.py --check` validates generated RAG template placeholders without calling a model.\n- `python sub-skills\u002Fapi-and-deployment\u002Fscripts\u002Fapi_config_template.py --list` lists safe API config templates without starting a server.\n\n## Self-Containment Rules\n\n- Do not tell future users to open txtai source docs, examples, tests, Docker files, or notebooks from a checkout. Runtime guidance must come from this skill tree.\n- If a task needs a reusable helper, use the bundled scripts above or create user project files from the references.\n- Keep credentials, tokens, model cache paths, API keys, and local environment paths out of generated configs and answers.\n- Treat model downloads, web tools, cloud APIs, GPU acceleration, audio\u002Fimage system dependencies, and server startup as explicit user-environment decisions.\n","# txtai\n\ntxtai is an all-in-one Python AI framework for semantic search, embeddings databases, retrieval augmented generation (RAG), LLM orchestration, agents, deterministic workflows, and FastAPI\u002FOpenAI-compatible services.\n\nUse this root skill to choose the right txtai sub-skill, install the correct optional extras, and run safe environment checks. Keep detailed workflows in the linked sub-skills and references.\n\n## Start Here\n\n1. Confirm the package import and version.\n   ```bash\n   python - \u003C\u003C'PY'\n   import importlib.metadata\n   import txtai\n   print(importlib.metadata.version(\"txtai\"))\n   print(txtai.Embeddings, txtai.Application, txtai.Workflow)\n   PY\n   ```\n2. Read [references\u002Finstallation-and-extras.md](references\u002Finstallation-and-extras.md) before installing optional dependencies.\n3. Run `python scripts\u002Fcheck_txtai_environment.py --help` to inspect imports and optional capabilities without downloading models.\n4. Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when imports, model backends, optional extras, config files, API startup, or offline runs fail.\n5. Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before deciding whether this skill is current for a source checkout.\n\n## Route By Task\n\n| User task | Read |\n| --- | --- |\n| Build an embeddings index, semantic search, SQL search, hybrid sparse+dense search, graph search, object storage, subindexes, save\u002Fload, or index maintenance | [sub-skills\u002Fembeddings-search\u002FSKILL.md](sub-skills\u002Fembeddings-search\u002FSKILL.md) |\n| Compose deterministic pipelines\u002Fworkflows for extraction, chunking, summarization, translation, transcription, image\u002Faudio\u002Fdata processing, YAML task chains, schedules, or lazy generator debugging | [sub-skills\u002Fpipelines-and-workflows\u002FSKILL.md](sub-skills\u002Fpipelines-and-workflows\u002FSKILL.md) |\n| Build RAG, direct LLM calls, txtai `Agent` tools, embeddings-backed tools, agent teams, prompt templates, or backend selection for hosted\u002Flocal models | [sub-skills\u002Fagents-and-llm-orchestration\u002FSKILL.md](sub-skills\u002Fagents-and-llm-orchestration\u002FSKILL.md) |\n| Configure `Application`, serve FastAPI\u002FUvicorn APIs, OpenAI-compatible endpoints, MCP, auth, custom endpoints, clustering, Docker\u002Fcloud\u002Fserverless, observability, or console usage | [sub-skills\u002Fapi-and-deployment\u002FSKILL.md](sub-skills\u002Fapi-and-deployment\u002FSKILL.md) |\n\n## Installation Choices\n\nInstall the smallest dependency set that matches the task:\n\n```bash\npip install txtai\npip install \"txtai[api]\"       # FastAPI, OpenAI-compatible API, MCP\u002Fservice routes\npip install \"txtai[agent]\"     # Agent support and smolagents integration\npip install \"txtai[pipeline]\"  # broad pipeline extras; prefer narrower groups when possible\npip install \"txtai[workflow]\"  # scheduling, file\u002Fdata workflow extras\npip install \"txtai[graph]\"     # graph\u002Fnetwork search extras\npip install \"txtai[database]\"  # DuckDB\u002FSQLAlchemy database extras\n```\n\nAvoid `txtai[all]` unless the user explicitly needs nearly every optional subsystem. txtai optional groups can pull large ML, audio, image, database, API, cloud, or CUDA-adjacent packages. See [references\u002Finstallation-and-extras.md](references\u002Finstallation-and-extras.md) for the full group map.\n\n## Public API Anchors\n\n- `txtai.Embeddings(config=None, models=None, **kwargs)` builds and queries embeddings databases.\n- `txtai.Application(config, loaddata=True)` loads YAML\u002Fdict application config for APIs, pipelines, workflows, agents, and embeddings.\n- `txtai.Workflow(tasks, batch=100, workers=None, name=None, stream=None)` chains callable tasks and yields lazy generator output.\n- `txtai.LLM(path=None, method=None, **kwargs)` runs local, hosted, or custom generation backends.\n- `txtai.RAG(similarity, path, ..., template=None, context=None, output=\"default\", system=None, **kwargs)` joins retrieval with generation.\n- `txtai.Agent(model=..., tools=[...], max_steps=...)` requires the agent extra; without it, imports can resolve to a placeholder that raises when constructed.\n\n## Common Routing Pitfalls\n\n- If a prompt asks for a chatbot that answers from documents, split the work: use `embeddings-search` to build the store, then `agents-and-llm-orchestration` for `RAG` templates and generation.\n- If a prompt asks for repeatable extraction\u002Fsummarization\u002Ftranslation over many items, prefer `pipelines-and-workflows`; use agents only when tool choice or multi-step reasoning is required.\n- If a prompt asks for a service endpoint, route to `api-and-deployment` even when the underlying route calls embeddings, workflows, or RAG.\n- If a prompt names SQL, `similar(...)`, metadata filtering, graph traversal, or object retrieval, route to `embeddings-search` first.\n- If a prompt names `CONFIG=app.yml`, `uvicorn`, `\u002Fv1\u002Fchat\u002Fcompletions`, `\u002Fmcp`, `TOKEN`, Docker, cloud, or console commands, route to `api-and-deployment`.\n\n## Validation Helpers\n\n- `python scripts\u002Fcheck_txtai_environment.py` checks core imports, package version, optional modules, and top-level constructor signatures.\n- `python sub-skills\u002Fembeddings-search\u002Fscripts\u002Fsemantic_search_smoke.py --run --sql` runs a no-download embeddings smoke check with external vectors.\n- `python sub-skills\u002Fpipelines-and-workflows\u002Fscripts\u002Fworkflow_smoke.py --mode all` runs no-download deterministic workflow checks.\n- `python sub-skills\u002Fagents-and-llm-orchestration\u002Fscripts\u002Frag_config_template.py --check` validates generated RAG template placeholders without calling a model.\n- `python sub-skills\u002Fapi-and-deployment\u002Fscripts\u002Fapi_config_template.py --list` lists safe API config templates without starting a server.\n\n## Self-Containment Rules\n\n- Do not tell future users to open txtai source docs, examples, tests, Docker files, or notebooks from a checkout. Runtime guidance must come from this skill tree.\n- If a task needs a reusable helper, use the bundled scripts above or create user project files from the references.\n- Keep credentials, tokens, model cache paths, API keys, and local environment paths out of generated configs and answers.\n- Treat model downloads, web tools, cloud APIs, GPU acceleration, audio\u002Fimage system dependencies, and server startup as explicit user-environment decisions.\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\u002Ftxtai",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 txtai",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill txtai",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill txtai","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftxtai\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Finstallation-and-extras.md","REFERENCE","参考文档",4849,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftxtai\u002Freferences\u002Finstallation-and-extras.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-provenance.md",2293,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftxtai\u002Freferences\u002Frepo-provenance.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-routing-metadata.json",480,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftxtai\u002Freferences\u002Frepo-routing-metadata.json",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",4188,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftxtai\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fcheck_txtai_environment.py","SCRIPT","脚本",4037,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftxtai\u002Fscripts\u002Fcheck_txtai_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",[],[]]