[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78YVX9T06K9GCZ2VH9P1NFQ":3,"skill-same:01M78YVX9T06K9GCZ2VH9P1NFQ":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},"01M78YVX9T06K9GCZ2VH9P1NFQ","contexts-and-retrievers",null,"Choose and validate LaVague provider contexts, credentials, custom model objects, cache contexts, and retriever pipelines without making live provider or browser calls by default.","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\u002Fla-vague\u002Fsub-skills\u002Fcontexts-and-retrievers\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: contexts-and-retrievers\ndescription: \"Choose and validate LaVague provider contexts, credentials, custom\n  model objects, cache contexts, and retriever pipelines without making live\n  provider or browser calls by default.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# LaVague Contexts and Retrievers\n\nUse this sub-skill when a LaVague task needs provider\u002Fmodel selection, API-key checks, custom LlamaIndex `llm`\u002F`embedding`\u002F`mm_llm` wiring, cache-backed contexts, WorldModel knowledge examples, task `user_data`, or ActionEngine\u002FNavigationEngine retriever selection.\n\n## Route first\n\n- Provider context, credentials, custom models, cache, Cohere rerank, or `RetrieversPipeline`: stay here.\n- Browser construction, Selenium\u002FPlaywright profiles, browser binaries, screenshots, tabs, iframes, or CAPTCHA\u002Fsession handling: route to `..\u002Fbrowser-drivers\u002FSKILL.md`.\n- Full `WebAgent`, `WorldModel`, `ActionEngine`, logs, token counts, or agent run\u002Fdebug loops: route to `..\u002Fcore-web-agent\u002FSKILL.md` after choosing the context or retriever here.\n- Gradio, Chrome extension server, `AgentServer`, or `lavague-serve`: route to `..\u002Fserver-extension-gradio\u002FSKILL.md`.\n- `lavague-qa` and `lavague-test`: route to `..\u002Fqa-and-test-runner\u002FSKILL.md`.\n\n## Fast workflow\n\n1. Pick the provider context from `references\u002Fprovider-contexts.md`; install the matching optional package if its import is missing.\n2. Check required environment variables without printing secret values. For Anthropic and Fireworks, remember that default components still require `OPENAI_API_KEY` for OpenAI embedding or multimodal pieces.\n3. Prefer `WorldModel.from_context(context)` and `ActionEngine.from_context(context, driver=driver)` when all three context models should travel together. Pass individual custom LlamaIndex objects only when mixing providers deliberately.\n4. Pick a retriever from `references\u002Fretriever-reference.md`. Keep the default retriever unless retrieval logs show missing target nodes or a page has unusual markup.\n5. Run the bundled safe probe before live work:\n\n```bash\npython sub-skills\u002Fcontexts-and-retrievers\u002Fscripts\u002Flavague_context_retriever_probe.py --context all --retriever all --check-env\n```\n\nThe probe imports modules, inspects constructor signatures, and reports whether required credential variables are present. It does not instantiate providers, contact model APIs, launch browsers, download data, or start servers.\n\n## Common recipes\n\n- OpenAI default: ensure `OPENAI_API_KEY`, then use `OpenaiContext()` or rely on LaVague's default context.\n- Azure OpenAI: pass explicit `llm`, `mm_llm`, `deployment`, `endpoint`, and `embedding_deployment`; do not rely on defaults for deployment names.\n- Anthropic planning\u002Faction with OpenAI embeddings: set both `ANTHROPIC_API_KEY` and `OPENAI_API_KEY`, then use `AnthropicContext()`.\n- Gemini all-in-one: set `GOOGLE_API_KEY`, then use `GeminiContext()`.\n- Fireworks action\u002Fembedding with OpenAI multimodal world model: set `FIREWORKS_API_KEY` and `OPENAI_API_KEY`, then use `FireworksContext()`.\n- Cache-driven dry recovery: use `ContextCache` only when prompt\u002Fembedding stores are intentionally local and versioned for the run; understand fallback behavior before assuming it is offline.\n- Retriever pipeline: compose `InteractiveXPathRetriever(driver)`, `SyntaxicRetriever()`, and `XPathedChunkRetriever()` when you need deterministic XPath marking plus lightweight syntax filtering; add Cohere only when `COHERE_API_KEY` and network\u002FAPI use are explicitly permitted.\n\n## References\n\n- `references\u002Fprovider-contexts.md` — provider packages, signatures, environment variables, default-model caveats, and cache stores.\n- `references\u002Fretriever-reference.md` — retriever classes, default pipeline, Cohere rerank behavior, and selection rules.\n- `references\u002Fcustomization-workflows.md` — mixed-provider contexts, `from_context`, `add_knowledge`, task `user_data`, and template snippets.\n- `references\u002Ftroubleshooting.md` — optional-package, API-key, Azure, embedding, cache, Cohere, and NLTK\u002Fimport issues.\n\n## Safety defaults\n\nKeep provider calls and browser launches opt-in. The examples distilled into this sub-skill originally run live web objectives, but the bundled helper only performs local import\u002Fsignature\u002Fenv checks and prints runnable templates. Never store API keys in generated files, logs, or prompt caches.\n","# LaVague Contexts and Retrievers\n\nUse this sub-skill when a LaVague task needs provider\u002Fmodel selection, API-key checks, custom LlamaIndex `llm`\u002F`embedding`\u002F`mm_llm` wiring, cache-backed contexts, WorldModel knowledge examples, task `user_data`, or ActionEngine\u002FNavigationEngine retriever selection.\n\n## Route first\n\n- Provider context, credentials, custom models, cache, Cohere rerank, or `RetrieversPipeline`: stay here.\n- Browser construction, Selenium\u002FPlaywright profiles, browser binaries, screenshots, tabs, iframes, or CAPTCHA\u002Fsession handling: route to `..\u002Fbrowser-drivers\u002FSKILL.md`.\n- Full `WebAgent`, `WorldModel`, `ActionEngine`, logs, token counts, or agent run\u002Fdebug loops: route to `..\u002Fcore-web-agent\u002FSKILL.md` after choosing the context or retriever here.\n- Gradio, Chrome extension server, `AgentServer`, or `lavague-serve`: route to `..\u002Fserver-extension-gradio\u002FSKILL.md`.\n- `lavague-qa` and `lavague-test`: route to `..\u002Fqa-and-test-runner\u002FSKILL.md`.\n\n## Fast workflow\n\n1. Pick the provider context from `references\u002Fprovider-contexts.md`; install the matching optional package if its import is missing.\n2. Check required environment variables without printing secret values. For Anthropic and Fireworks, remember that default components still require `OPENAI_API_KEY` for OpenAI embedding or multimodal pieces.\n3. Prefer `WorldModel.from_context(context)` and `ActionEngine.from_context(context, driver=driver)` when all three context models should travel together. Pass individual custom LlamaIndex objects only when mixing providers deliberately.\n4. Pick a retriever from `references\u002Fretriever-reference.md`. Keep the default retriever unless retrieval logs show missing target nodes or a page has unusual markup.\n5. Run the bundled safe probe before live work:\n\n```bash\npython sub-skills\u002Fcontexts-and-retrievers\u002Fscripts\u002Flavague_context_retriever_probe.py --context all --retriever all --check-env\n```\n\nThe probe imports modules, inspects constructor signatures, and reports whether required credential variables are present. It does not instantiate providers, contact model APIs, launch browsers, download data, or start servers.\n\n## Common recipes\n\n- OpenAI default: ensure `OPENAI_API_KEY`, then use `OpenaiContext()` or rely on LaVague's default context.\n- Azure OpenAI: pass explicit `llm`, `mm_llm`, `deployment`, `endpoint`, and `embedding_deployment`; do not rely on defaults for deployment names.\n- Anthropic planning\u002Faction with OpenAI embeddings: set both `ANTHROPIC_API_KEY` and `OPENAI_API_KEY`, then use `AnthropicContext()`.\n- Gemini all-in-one: set `GOOGLE_API_KEY`, then use `GeminiContext()`.\n- Fireworks action\u002Fembedding with OpenAI multimodal world model: set `FIREWORKS_API_KEY` and `OPENAI_API_KEY`, then use `FireworksContext()`.\n- Cache-driven dry recovery: use `ContextCache` only when prompt\u002Fembedding stores are intentionally local and versioned for the run; understand fallback behavior before assuming it is offline.\n- Retriever pipeline: compose `InteractiveXPathRetriever(driver)`, `SyntaxicRetriever()`, and `XPathedChunkRetriever()` when you need deterministic XPath marking plus lightweight syntax filtering; add Cohere only when `COHERE_API_KEY` and network\u002FAPI use are explicitly permitted.\n\n## References\n\n- `references\u002Fprovider-contexts.md` — provider packages, signatures, environment variables, default-model caveats, and cache stores.\n- `references\u002Fretriever-reference.md` — retriever classes, default pipeline, Cohere rerank behavior, and selection rules.\n- `references\u002Fcustomization-workflows.md` — mixed-provider contexts, `from_context`, `add_knowledge`, task `user_data`, and template snippets.\n- `references\u002Ftroubleshooting.md` — optional-package, API-key, Azure, embedding, cache, Cohere, and NLTK\u002Fimport issues.\n\n## Safety defaults\n\nKeep provider calls and browser launches opt-in. The examples distilled into this sub-skill originally run live web objectives, but the bundled helper only performs local import\u002Fsignature\u002Fenv checks and prints runnable templates. Never store API keys in generated files, logs, or prompt caches.\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\u002Fla-vague\u002Fsub-skills\u002Fcontexts-and-retrievers",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 contexts-and-retrievers",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill contexts-and-retrievers",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill contexts-and-retrievers","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fla-vague\u002Fsub-skills\u002Fcontexts-and-retrievers\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcustomization-workflows.md","REFERENCE","参考文档",5768,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fla-vague\u002Fsub-skills\u002Fcontexts-and-retrievers\u002Freferences\u002Fcustomization-workflows.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fprovider-contexts.md",6703,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fla-vague\u002Fsub-skills\u002Fcontexts-and-retrievers\u002Freferences\u002Fprovider-contexts.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fretriever-reference.md",6589,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fla-vague\u002Fsub-skills\u002Fcontexts-and-retrievers\u002Freferences\u002Fretriever-reference.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",6916,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fla-vague\u002Fsub-skills\u002Fcontexts-and-retrievers\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Flavague_context_retriever_probe.py","SCRIPT","脚本",14401,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fla-vague\u002Fsub-skills\u002Fcontexts-and-retrievers\u002Fscripts\u002Flavague_context_retriever_probe.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",[],[]]