[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78XRYF3MP1PDAF1KYAQA3EE":3,"skill-same:01M78XRYF3MP1PDAF1KYAQA3EE":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},"01M78XRYF3MP1PDAF1KYAQA3EE","package-extensions",null,"Build and diagnose GraphRAG lower-level package extensions: custom caches, storage and table providers, input readers, chunkers, vector stores and filters, LLM completion\u002Fembedding providers, tokenizers, metrics\u002Fretry\u002Frate-limit\u002Ftemplate factories, graph helpers, and indexing workflow factories.","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\u002Fpackage-extensions\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: package-extensions\ndescription: \"Build and diagnose GraphRAG lower-level package extensions: custom\n  caches, storage and table providers, input readers, chunkers, vector stores\n  and filters, LLM completion\u002Fembedding providers, tokenizers,\n  metrics\u002Fretry\u002Frate-limit\u002Ftemplate factories, graph helpers, and indexing\n  workflow factories.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# GraphRAG Package Extensions\n\nUse this sub-skill when the task mentions custom providers, factory registration, extension points, offline mocks, graph helper validation, vector-store filters, timestamp\u002Fdate fields, chunkers, or low-level package diagnostics.\n\nFor user-facing YAML\u002Fconfig selection, route to `..\u002Fconfiguration-data\u002F`. For indexing orchestration or running pipelines, route to `..\u002Findexing\u002F`. For query APIs and result-table requirements, route to `..\u002Fquerying\u002F`.\n\n## Core Pattern\n\nGraphRAG package extensions usually follow the same pattern:\n\n1. Implement the package interface or subclass the base class.\n2. Register it under a stable string key with the package `register_*` function.\n3. Use the matching config model or `create_*` helper so GraphRAG instantiates it.\n4. Keep optional services behind explicit dependency and credential checks.\n\nThe shared factory base supports `scope=\"transient\"` and `scope=\"singleton\"`. `create()` removes init args whose value is `None`, so use a sentinel or explicit default if an initializer must distinguish \"unset\" from `None`. Singleton instances are cached by strategy plus init args; avoid singleton scope for mutable per-run state unless the init args fully identify the state.\n\n## Common Extension Points\n\n- **Cache**: implement `graphrag_cache.Cache`, register with `register_cache(type, initializer, scope=\"transient\")`, create with `create_cache(CacheConfig(...), storage=...)`.\n- **Storage**: implement `graphrag_storage.Storage`, register with `register_storage(type, initializer)`, create with `create_storage(StorageConfig(...))`.\n- **Table provider**: implement `graphrag_storage.tables.TableProvider`, register with `register_table_provider(type, initializer)`, create with `create_table_provider(TableProviderConfig(...), storage=...)`.\n- **Input reader**: subclass or implement `graphrag_input.InputReader`, register with `register_input_reader(type, initializer)`, create with `create_input_reader(InputConfig(...), storage)`.\n- **Chunker**: implement `graphrag_chunking.Chunker`, register with `register_chunker(type, initializer)`, create with `create_chunker(ChunkingConfig(...), encode=..., decode=...)`.\n- **Vector store**: subclass `graphrag_vectors.VectorStore`, register with `register_vector_store(type, initializer)`, create with `create_vector_store(VectorStoreConfig(...), IndexSchema(...))`.\n- **LLM providers**: implement completion or embedding interfaces, register with `register_completion` or `register_embedding`; model config `model_extra` fields are passed through to initializers.\n- **LLM utilities**: tokenizer, retry, rate-limit, metrics store\u002Fprocessor\u002Fwriter, template manager\u002Fengine factories have analogous `register_*` and `create_*` helpers.\n- **Index workflows**: register workflow callables with `PipelineFactory.register(name, workflow)` and methods with `PipelineFactory.register_pipeline(name, [workflow_names...])`.\n- **Graph helpers**: use deterministic DataFrame helpers such as `compute_degree`, `connected_components`, `largest_connected_component`, and `stable_lcc` for offline graph checks.\n\n## Recommended Workflow\n\n1. Identify the package boundary first: storage\u002Fcache\u002Finput\u002Fchunking\u002Fvector\u002FLLM\u002Fgraph\u002Fworkflow.\n2. Inspect the initializer signature of the target base or built-in implementation.\n3. Decide factory scope: transient for fresh state, singleton only for shareable clients keyed by complete init args.\n4. Register a unique key before calling `create_*`; duplicate keys overwrite the previous initializer in the process.\n5. Create a tiny offline mock before adding optional cloud\u002Fdatabase dependencies.\n6. Add a smoke check for `--help`, factory registration, and one deterministic operation.\n7. If wiring through GraphRAG config, move user-facing config guidance to `..\u002Fconfiguration-data\u002F`.\n\n## Bundled Scripts\n\n- `scripts\u002Fregister_mock_extensions.py` demonstrates offline custom storage, cache, input reader, vector store, and direct factory patterns.\n- `scripts\u002Fvalidate_graph_helpers.py` checks degree, connected components, stable LCC normalization\u002Forder, timestamp explosion, and filter expressions on deterministic in-memory data.\n\nBoth scripts are examples for future agents to copy or adapt inside their own workspace. They do not require external services.\n\n## References\n\n- `references\u002Ffactory-extension-recipes.md` for concrete registration recipes and design notes.\n- `references\u002Fpackage-optional-dependencies.md` for guarded dependency and service guidance.\n- `references\u002Ftroubleshooting.md` for factory, config, service, vector filter, and graph-helper failures.\n","# GraphRAG Package Extensions\n\nUse this sub-skill when the task mentions custom providers, factory registration, extension points, offline mocks, graph helper validation, vector-store filters, timestamp\u002Fdate fields, chunkers, or low-level package diagnostics.\n\nFor user-facing YAML\u002Fconfig selection, route to `..\u002Fconfiguration-data\u002F`. For indexing orchestration or running pipelines, route to `..\u002Findexing\u002F`. For query APIs and result-table requirements, route to `..\u002Fquerying\u002F`.\n\n## Core Pattern\n\nGraphRAG package extensions usually follow the same pattern:\n\n1. Implement the package interface or subclass the base class.\n2. Register it under a stable string key with the package `register_*` function.\n3. Use the matching config model or `create_*` helper so GraphRAG instantiates it.\n4. Keep optional services behind explicit dependency and credential checks.\n\nThe shared factory base supports `scope=\"transient\"` and `scope=\"singleton\"`. `create()` removes init args whose value is `None`, so use a sentinel or explicit default if an initializer must distinguish \"unset\" from `None`. Singleton instances are cached by strategy plus init args; avoid singleton scope for mutable per-run state unless the init args fully identify the state.\n\n## Common Extension Points\n\n- **Cache**: implement `graphrag_cache.Cache`, register with `register_cache(type, initializer, scope=\"transient\")`, create with `create_cache(CacheConfig(...), storage=...)`.\n- **Storage**: implement `graphrag_storage.Storage`, register with `register_storage(type, initializer)`, create with `create_storage(StorageConfig(...))`.\n- **Table provider**: implement `graphrag_storage.tables.TableProvider`, register with `register_table_provider(type, initializer)`, create with `create_table_provider(TableProviderConfig(...), storage=...)`.\n- **Input reader**: subclass or implement `graphrag_input.InputReader`, register with `register_input_reader(type, initializer)`, create with `create_input_reader(InputConfig(...), storage)`.\n- **Chunker**: implement `graphrag_chunking.Chunker`, register with `register_chunker(type, initializer)`, create with `create_chunker(ChunkingConfig(...), encode=..., decode=...)`.\n- **Vector store**: subclass `graphrag_vectors.VectorStore`, register with `register_vector_store(type, initializer)`, create with `create_vector_store(VectorStoreConfig(...), IndexSchema(...))`.\n- **LLM providers**: implement completion or embedding interfaces, register with `register_completion` or `register_embedding`; model config `model_extra` fields are passed through to initializers.\n- **LLM utilities**: tokenizer, retry, rate-limit, metrics store\u002Fprocessor\u002Fwriter, template manager\u002Fengine factories have analogous `register_*` and `create_*` helpers.\n- **Index workflows**: register workflow callables with `PipelineFactory.register(name, workflow)` and methods with `PipelineFactory.register_pipeline(name, [workflow_names...])`.\n- **Graph helpers**: use deterministic DataFrame helpers such as `compute_degree`, `connected_components`, `largest_connected_component`, and `stable_lcc` for offline graph checks.\n\n## Recommended Workflow\n\n1. Identify the package boundary first: storage\u002Fcache\u002Finput\u002Fchunking\u002Fvector\u002FLLM\u002Fgraph\u002Fworkflow.\n2. Inspect the initializer signature of the target base or built-in implementation.\n3. Decide factory scope: transient for fresh state, singleton only for shareable clients keyed by complete init args.\n4. Register a unique key before calling `create_*`; duplicate keys overwrite the previous initializer in the process.\n5. Create a tiny offline mock before adding optional cloud\u002Fdatabase dependencies.\n6. Add a smoke check for `--help`, factory registration, and one deterministic operation.\n7. If wiring through GraphRAG config, move user-facing config guidance to `..\u002Fconfiguration-data\u002F`.\n\n## Bundled Scripts\n\n- `scripts\u002Fregister_mock_extensions.py` demonstrates offline custom storage, cache, input reader, vector store, and direct factory patterns.\n- `scripts\u002Fvalidate_graph_helpers.py` checks degree, connected components, stable LCC normalization\u002Forder, timestamp explosion, and filter expressions on deterministic in-memory data.\n\nBoth scripts are examples for future agents to copy or adapt inside their own workspace. They do not require external services.\n\n## References\n\n- `references\u002Ffactory-extension-recipes.md` for concrete registration recipes and design notes.\n- `references\u002Fpackage-optional-dependencies.md` for guarded dependency and service guidance.\n- `references\u002Ftroubleshooting.md` for factory, config, service, vector filter, and graph-helper failures.\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\u002Fpackage-extensions",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 package-extensions",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill package-extensions",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill package-extensions","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphrag\u002Fsub-skills\u002Fpackage-extensions\u002FSKILL.md",[46,52,56,60,66],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Ffactory-extension-recipes.md","REFERENCE","参考文档",7187,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphrag\u002Fsub-skills\u002Fpackage-extensions\u002Freferences\u002Ffactory-extension-recipes.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fpackage-optional-dependencies.md",4613,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphrag\u002Fsub-skills\u002Fpackage-extensions\u002Freferences\u002Fpackage-optional-dependencies.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",6011,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphrag\u002Fsub-skills\u002Fpackage-extensions\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fregister_mock_extensions.py","SCRIPT","脚本",11273,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphrag\u002Fsub-skills\u002Fpackage-extensions\u002Fscripts\u002Fregister_mock_extensions.py",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fvalidate_graph_helpers.py",3444,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphrag\u002Fsub-skills\u002Fpackage-extensions\u002Fscripts\u002Fvalidate_graph_helpers.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",[],[]]