[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78YYFY7MMC7ZQHE3SDFDJY0":3,"skill-same:01M78YYFY7MMC7ZQHE3SDFDJY0":74},{"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},"01M78YYFY7MMC7ZQHE3SDFDJY0","langchain",null,"Work on the LangChain Python monorepo: package routing, core primitives, v1 agents and middleware, classic APIs, partner integrations, standard tests, model profiles, and safe validation workflows.","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\u002Flangchain\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: langchain\ndescription: \"Work on the LangChain Python monorepo: package routing, core\n  primitives, v1 agents and middleware, classic APIs, partner integrations,\n  standard tests, model profiles, and safe validation workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# LangChain Python Monorepo\n\nUse this skill when a task targets the LangChain Python repository, its package-local development workflow, or one of its maintained Python packages.\n\n## Start Here\n\n1. Identify the package and workflow with [repository-map.md](references\u002Frepository-map.md).\n2. Use the sub-skill that owns the change instead of scanning the whole monorepo.\n3. Follow [development-commands.md](references\u002Fdevelopment-commands.md) for package-local `uv`, pytest, lint, type, import, and version checks.\n4. Use [troubleshooting.md](references\u002Ftroubleshooting.md) for environment, import, optional dependency, integration-test, and source-layout failures.\n5. Check [repo-provenance.md](references\u002Frepo-provenance.md) when deciding whether this skill is stale relative to the current checkout.\n\n## Route by Task\n\n- Monorepo navigation, package metadata, validation commands, public API guardrails, PR conventions, and docs\u002Fmodel-reference rules: use [monorepo-development](sub-skills\u002Fmonorepo-development\u002FSKILL.md).\n- `langchain-core` primitives such as runnables, messages, prompts, tools, documents, embeddings, vector stores, model interfaces, callbacks, parsers, serialization, and deprecation utilities: use [core-primitives](sub-skills\u002Fcore-primitives\u002FSKILL.md).\n- Actively maintained `langchain` v1 APIs such as `init_chat_model`, `create_agent`, structured output, tools, middleware, embeddings, provider routing, and agent runtime customization: use [agents-and-middleware](sub-skills\u002Fagents-and-middleware\u002FSKILL.md).\n- `langchain-classic` chains, retrievers, document loaders\u002Ftransformers, memory, indexes, classic agents, evaluation, and legacy maintenance or migration: use [classic-chains](sub-skills\u002Fclassic-chains\u002FSKILL.md).\n- Partner packages under `libs\u002Fpartners`, provider SDK dependencies, credentials, unit\u002Fintegration test split, cassettes, vector-store services, and provider model profile data: use [integrations](sub-skills\u002Fintegrations\u002FSKILL.md).\n- `langchain-tests`, native verification selection, pytest marker\u002Fsnapshot safety, model-profile CLI internals, and safe test\u002Fprofile command planning: use [testing-and-profiles](sub-skills\u002Ftesting-and-profiles\u002FSKILL.md).\n\n## Package Boundaries\n\n- `libs\u002Fcore` publishes `langchain-core`, the stable abstraction layer used by other packages.\n- `libs\u002Flangchain_v1` publishes `langchain`, the actively maintained high-level package.\n- `libs\u002Flangchain` publishes `langchain-classic`, a legacy compatibility package; avoid new feature work there unless explicitly requested.\n- `libs\u002Ftext-splitters` publishes `langchain-text-splitters`, focused on chunking documents and text.\n- `libs\u002Fpartners\u002F\u003Cprovider>` publish maintained provider integrations such as OpenAI, Anthropic, Ollama, Qdrant, Chroma, DeepSeek, Fireworks, Groq, Hugging Face, MistralAI, Nomic, Perplexity, OpenRouter, xAI, and Exa.\n- `libs\u002Fstandard-tests` publishes `langchain-tests`, shared conformance tests for integrations.\n- `libs\u002Fmodel-profiles` contains the model profile refresh CLI and provider profile tooling.\n\n## Default Development Workflow\n\nRun commands from the owning package directory unless a package reference says otherwise:\n\n```bash\ncd libs\u002F\u003Cpackage>\nuv sync --group test\nuv run --group test pytest tests\u002Funit_tests\u002Fpath\u002Fto\u002Ftest_file.py\nmake lint_package\nmake type\n```\n\nUse narrower commands first. Add `--group lint`, `--group typing`, `--group test_integration`, or `--all-groups` only when the package metadata and task require those dependencies. Do not use `pip`, `poetry`, `conda`, or ad-hoc virtual environments for normal LangChain development.\n\n## Safety and Validation\n\n- Preserve public function\u002Fclass signatures, argument order, names, defaults, and exported symbols unless the user accepts a breaking change.\n- Add deterministic unit tests for bug fixes and feature changes; avoid network, credentials, provider services, or long-running checks by default.\n- Use integration tests only when explicitly requested and credentials\u002Fservices are available.\n- For provider model examples in docs, verify current generally available model IDs against provider docs before updating examples.\n- Use bundled scripts only as local helpers; they are read-only smoke\u002Finspection utilities and do not replace package test suites.\n\n## Bundled References and Scripts\n\n- [Repository map](references\u002Frepository-map.md) gives the capability-to-package map and sub-skill ownership.\n- [Development commands](references\u002Fdevelopment-commands.md) gives command patterns and validation escalation rules.\n- [Troubleshooting](references\u002Ftroubleshooting.md) covers cross-cutting failures and recovery decisions.\n- [Repo provenance](references\u002Frepo-provenance.md) records the source snapshot and evidence paths.\n- [Skill health check](scripts\u002Fcheck_skill_links.py) validates generated skill links and common leakage patterns.\n","# LangChain Python Monorepo\n\nUse this skill when a task targets the LangChain Python repository, its package-local development workflow, or one of its maintained Python packages.\n\n## Start Here\n\n1. Identify the package and workflow with [repository-map.md](references\u002Frepository-map.md).\n2. Use the sub-skill that owns the change instead of scanning the whole monorepo.\n3. Follow [development-commands.md](references\u002Fdevelopment-commands.md) for package-local `uv`, pytest, lint, type, import, and version checks.\n4. Use [troubleshooting.md](references\u002Ftroubleshooting.md) for environment, import, optional dependency, integration-test, and source-layout failures.\n5. Check [repo-provenance.md](references\u002Frepo-provenance.md) when deciding whether this skill is stale relative to the current checkout.\n\n## Route by Task\n\n- Monorepo navigation, package metadata, validation commands, public API guardrails, PR conventions, and docs\u002Fmodel-reference rules: use [monorepo-development](sub-skills\u002Fmonorepo-development\u002FSKILL.md).\n- `langchain-core` primitives such as runnables, messages, prompts, tools, documents, embeddings, vector stores, model interfaces, callbacks, parsers, serialization, and deprecation utilities: use [core-primitives](sub-skills\u002Fcore-primitives\u002FSKILL.md).\n- Actively maintained `langchain` v1 APIs such as `init_chat_model`, `create_agent`, structured output, tools, middleware, embeddings, provider routing, and agent runtime customization: use [agents-and-middleware](sub-skills\u002Fagents-and-middleware\u002FSKILL.md).\n- `langchain-classic` chains, retrievers, document loaders\u002Ftransformers, memory, indexes, classic agents, evaluation, and legacy maintenance or migration: use [classic-chains](sub-skills\u002Fclassic-chains\u002FSKILL.md).\n- Partner packages under `libs\u002Fpartners`, provider SDK dependencies, credentials, unit\u002Fintegration test split, cassettes, vector-store services, and provider model profile data: use [integrations](sub-skills\u002Fintegrations\u002FSKILL.md).\n- `langchain-tests`, native verification selection, pytest marker\u002Fsnapshot safety, model-profile CLI internals, and safe test\u002Fprofile command planning: use [testing-and-profiles](sub-skills\u002Ftesting-and-profiles\u002FSKILL.md).\n\n## Package Boundaries\n\n- `libs\u002Fcore` publishes `langchain-core`, the stable abstraction layer used by other packages.\n- `libs\u002Flangchain_v1` publishes `langchain`, the actively maintained high-level package.\n- `libs\u002Flangchain` publishes `langchain-classic`, a legacy compatibility package; avoid new feature work there unless explicitly requested.\n- `libs\u002Ftext-splitters` publishes `langchain-text-splitters`, focused on chunking documents and text.\n- `libs\u002Fpartners\u002F\u003Cprovider>` publish maintained provider integrations such as OpenAI, Anthropic, Ollama, Qdrant, Chroma, DeepSeek, Fireworks, Groq, Hugging Face, MistralAI, Nomic, Perplexity, OpenRouter, xAI, and Exa.\n- `libs\u002Fstandard-tests` publishes `langchain-tests`, shared conformance tests for integrations.\n- `libs\u002Fmodel-profiles` contains the model profile refresh CLI and provider profile tooling.\n\n## Default Development Workflow\n\nRun commands from the owning package directory unless a package reference says otherwise:\n\n```bash\ncd libs\u002F\u003Cpackage>\nuv sync --group test\nuv run --group test pytest tests\u002Funit_tests\u002Fpath\u002Fto\u002Ftest_file.py\nmake lint_package\nmake type\n```\n\nUse narrower commands first. Add `--group lint`, `--group typing`, `--group test_integration`, or `--all-groups` only when the package metadata and task require those dependencies. Do not use `pip`, `poetry`, `conda`, or ad-hoc virtual environments for normal LangChain development.\n\n## Safety and Validation\n\n- Preserve public function\u002Fclass signatures, argument order, names, defaults, and exported symbols unless the user accepts a breaking change.\n- Add deterministic unit tests for bug fixes and feature changes; avoid network, credentials, provider services, or long-running checks by default.\n- Use integration tests only when explicitly requested and credentials\u002Fservices are available.\n- For provider model examples in docs, verify current generally available model IDs against provider docs before updating examples.\n- Use bundled scripts only as local helpers; they are read-only smoke\u002Finspection utilities and do not replace package test suites.\n\n## Bundled References and Scripts\n\n- [Repository map](references\u002Frepository-map.md) gives the capability-to-package map and sub-skill ownership.\n- [Development commands](references\u002Fdevelopment-commands.md) gives command patterns and validation escalation rules.\n- [Troubleshooting](references\u002Ftroubleshooting.md) covers cross-cutting failures and recovery decisions.\n- [Repo provenance](references\u002Frepo-provenance.md) records the source snapshot and evidence paths.\n- [Skill health check](scripts\u002Fcheck_skill_links.py) validates generated skill links and common leakage patterns.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Flangchain",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 langchain",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill langchain",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill langchain","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangchain\u002FSKILL.md",[46,52,56,60,64,68],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdevelopment-commands.md","REFERENCE","参考文档",1949,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangchain\u002Freferences\u002Fdevelopment-commands.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",2005,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangchain\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",487,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangchain\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Frepository-map.md",2246,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangchain\u002Freferences\u002Frepository-map.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Ftroubleshooting.md",2024,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangchain\u002Freferences\u002Ftroubleshooting.md",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fcheck_skill_links.py","SCRIPT","脚本",1954,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangchain\u002Fscripts\u002Fcheck_skill_links.py",[75,83,90,97,104,111],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]