[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78XRSMJMWVMR1RJBJSFCZ09":3,"skill-same:01M78XRSMJMWVMR1RJBJSFCZ09":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},"01M78XRSMJMWVMR1RJBJSFCZ09","configuration-data",null,"Initialize, inspect, and troubleshoot GraphRAG settings, environment interpolation, auth, input readers, storage\u002Fcache\u002Ftable providers, vector stores, and offline data readiness before indexing or querying.","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\u002Fgraphrag\u002Fsub-skills\u002Fconfiguration-data\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: configuration-data\ndescription: \"Initialize, inspect, and troubleshoot GraphRAG settings,\n  environment interpolation, auth, input readers, storage\u002Fcache\u002Ftable providers,\n  vector stores, and offline data readiness before indexing or querying.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# GraphRAG Configuration and Data\n\nUse this sub-skill when a task mentions `settings.yaml`, `.env`, `GraphRagConfig`, Azure\u002FOpenAI auth, LiteLLM model settings, input file schemas, `input_storage`, `output_storage`, `cache`, `table_provider`, `vector_store`, LanceDB, Azure AI Search, Cosmos DB, or safe checks before running an index.\n\n## Route Boundaries\n\n- Stay here for initialization, config loading, schema validation, provider selection, secret-safe summaries, and offline input reader checks.\n- Route full index execution, update runs, workflow selection, and interpreting `PipelineRunResult` outputs to `..\u002Findexing\u002F`.\n- Route completed-index DataFrame loading and search calls to `..\u002Fquerying\u002F`.\n- Route prompt generation and `graphrag prompt-tune` usage to `..\u002Fprompt-tuning\u002F`.\n- Route custom reader\u002Fprovider implementation, factory registration, and package-extension design to `..\u002Fpackage-extensions\u002F`.\n\n## Fast Workflow\n\n1. Create or locate a project root containing `settings.yaml`, `settings.yml`, or `settings.json`; `graphrag init --root \u003Cproject>` generates the default `settings.yaml` and `.env` skeleton.\n2. Fill `completion_models` and `embedding_models` with LiteLLM-compatible `model_provider`, `model`, `auth_method`, and either `api_key` or Azure managed identity fields.\n3. Set `input.type` and reader columns, then match `input_storage.type` and `input_storage.base_dir` or remote storage settings to the data source.\n4. Choose local or remote `output_storage`, `cache.storage`, `table_provider`, and `vector_store` providers before indexing.\n5. Validate without network calls:\n   ```bash\n   python scripts\u002Finspect_config.py --root \u003Cproject>\n   python scripts\u002Fsmoke_input_readers.py\n   ```\n6. If config and readers pass, continue with indexing in `..\u002Findexing\u002F`; do not run indexing just to validate settings.\n\n## Key APIs and Commands\n\n- `from graphrag.config.load_config import load_config` loads `settings.[yaml|yml|json]` from a root and returns `GraphRagConfig`.\n- `load_config(root_dir, cli_overrides={...})` recursively overlays CLI-style nested dictionaries before Pydantic validation.\n- `GraphRagConfig` validates file base directories, resolves file paths, expands LanceDB `db_uri`, and overlays default vector schemas for GraphRAG embeddings.\n- `graphrag init --root \u003Cproject>` writes default config content with `${GRAPHRAG_API_KEY}` interpolation and common prompt file paths.\n- `graphrag index --root \u003Cproject>` belongs to `..\u002Findexing\u002F` after this sub-skill has checked prerequisites.\n\n## Provider Matrix\n\n- Inputs: `text`, `csv`, `json`, `jsonl`, `markitdown`, and `parquet` through `graphrag_input.create_input_reader`.\n- Storage: `file`, `memory`, `blob`, and `cosmosdb` via `StorageConfig`, depending on the section using it.\n- Cache: `json`, `memory`, and `none`; JSON cache uses a nested `storage` block.\n- Tables: `parquet`, `csv`, and `cosmosdb` through `table_provider.type`.\n- Vectors: `lancedb`, `azure_ai_search`, and `cosmosdb` through `vector_store.type`.\n\n## References\n\n- See `references\u002Fconfig-schema-and-env.md` for `GraphRagConfig`, model auth, `.env`, and validation behavior.\n- See `references\u002Finput-storage-cache-vector.md` for reader schemas and storage\u002Fcache\u002Ftable\u002Fvector provider settings.\n- See `references\u002Ftroubleshooting.md` for common validation failures and doc\u002Fcode drift traps.\n\n## Bundled Offline Checks\n\n- `scripts\u002Finspect_config.py` loads a project config and prints a JSON summary with secret-like values redacted.\n- `scripts\u002Fsmoke_input_readers.py` creates tiny temporary `text`, `csv`, `json`, `jsonl`, and optional `parquet` inputs and reports local reader readiness without credentials or network access.\n","# GraphRAG Configuration and Data\n\nUse this sub-skill when a task mentions `settings.yaml`, `.env`, `GraphRagConfig`, Azure\u002FOpenAI auth, LiteLLM model settings, input file schemas, `input_storage`, `output_storage`, `cache`, `table_provider`, `vector_store`, LanceDB, Azure AI Search, Cosmos DB, or safe checks before running an index.\n\n## Route Boundaries\n\n- Stay here for initialization, config loading, schema validation, provider selection, secret-safe summaries, and offline input reader checks.\n- Route full index execution, update runs, workflow selection, and interpreting `PipelineRunResult` outputs to `..\u002Findexing\u002F`.\n- Route completed-index DataFrame loading and search calls to `..\u002Fquerying\u002F`.\n- Route prompt generation and `graphrag prompt-tune` usage to `..\u002Fprompt-tuning\u002F`.\n- Route custom reader\u002Fprovider implementation, factory registration, and package-extension design to `..\u002Fpackage-extensions\u002F`.\n\n## Fast Workflow\n\n1. Create or locate a project root containing `settings.yaml`, `settings.yml`, or `settings.json`; `graphrag init --root \u003Cproject>` generates the default `settings.yaml` and `.env` skeleton.\n2. Fill `completion_models` and `embedding_models` with LiteLLM-compatible `model_provider`, `model`, `auth_method`, and either `api_key` or Azure managed identity fields.\n3. Set `input.type` and reader columns, then match `input_storage.type` and `input_storage.base_dir` or remote storage settings to the data source.\n4. Choose local or remote `output_storage`, `cache.storage`, `table_provider`, and `vector_store` providers before indexing.\n5. Validate without network calls:\n   ```bash\n   python scripts\u002Finspect_config.py --root \u003Cproject>\n   python scripts\u002Fsmoke_input_readers.py\n   ```\n6. If config and readers pass, continue with indexing in `..\u002Findexing\u002F`; do not run indexing just to validate settings.\n\n## Key APIs and Commands\n\n- `from graphrag.config.load_config import load_config` loads `settings.[yaml|yml|json]` from a root and returns `GraphRagConfig`.\n- `load_config(root_dir, cli_overrides={...})` recursively overlays CLI-style nested dictionaries before Pydantic validation.\n- `GraphRagConfig` validates file base directories, resolves file paths, expands LanceDB `db_uri`, and overlays default vector schemas for GraphRAG embeddings.\n- `graphrag init --root \u003Cproject>` writes default config content with `${GRAPHRAG_API_KEY}` interpolation and common prompt file paths.\n- `graphrag index --root \u003Cproject>` belongs to `..\u002Findexing\u002F` after this sub-skill has checked prerequisites.\n\n## Provider Matrix\n\n- Inputs: `text`, `csv`, `json`, `jsonl`, `markitdown`, and `parquet` through `graphrag_input.create_input_reader`.\n- Storage: `file`, `memory`, `blob`, and `cosmosdb` via `StorageConfig`, depending on the section using it.\n- Cache: `json`, `memory`, and `none`; JSON cache uses a nested `storage` block.\n- Tables: `parquet`, `csv`, and `cosmosdb` through `table_provider.type`.\n- Vectors: `lancedb`, `azure_ai_search`, and `cosmosdb` through `vector_store.type`.\n\n## References\n\n- See `references\u002Fconfig-schema-and-env.md` for `GraphRagConfig`, model auth, `.env`, and validation behavior.\n- See `references\u002Finput-storage-cache-vector.md` for reader schemas and storage\u002Fcache\u002Ftable\u002Fvector provider settings.\n- See `references\u002Ftroubleshooting.md` for common validation failures and doc\u002Fcode drift traps.\n\n## Bundled Offline Checks\n\n- `scripts\u002Finspect_config.py` loads a project config and prints a JSON summary with secret-like values redacted.\n- `scripts\u002Fsmoke_input_readers.py` creates tiny temporary `text`, `csv`, `json`, `jsonl`, and optional `parquet` inputs and reports local reader readiness without credentials or network access.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fgraphrag\u002Fsub-skills\u002Fconfiguration-data",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 configuration-data",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill configuration-data",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill configuration-data","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphrag\u002Fsub-skills\u002Fconfiguration-data\u002FSKILL.md",[46,52,56,60,66],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fconfig-schema-and-env.md","REFERENCE","参考文档",4243,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphrag\u002Fsub-skills\u002Fconfiguration-data\u002Freferences\u002Fconfig-schema-and-env.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Finput-storage-cache-vector.md",4817,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphrag\u002Fsub-skills\u002Fconfiguration-data\u002Freferences\u002Finput-storage-cache-vector.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",5838,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphrag\u002Fsub-skills\u002Fconfiguration-data\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Finspect_config.py","SCRIPT","脚本",5512,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphrag\u002Fsub-skills\u002Fconfiguration-data\u002Fscripts\u002Finspect_config.py",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fsmoke_input_readers.py",6076,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphrag\u002Fsub-skills\u002Fconfiguration-data\u002Fscripts\u002Fsmoke_input_readers.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",[],[]]