[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78YZ0KG4582XYZPWK8GZHVC":3,"skill-same:01M78YZ0KG4582XYZPWK8GZHVC":66},{"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},"01M78YZ0KG4582XYZPWK8GZHVC","monorepo-development",null,"Navigate LangChain's Python monorepo packages, package-local uv workflows, validation commands, API stability checks, PR conventions, and docs\u002Fmodel-reference guidance.","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\u002Fsub-skills\u002Fmonorepo-development\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: monorepo-development\ndescription: \"Navigate LangChain's Python monorepo packages, package-local uv\n  workflows, validation commands, API stability checks, PR conventions, and\n  docs\u002Fmodel-reference guidance.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# LangChain Monorepo Development\n\nUse this sub-skill when a task changes repository structure, package metadata, public Python APIs, tests, lint\u002Ftype workflows, documentation examples, or contributor-facing conventions in the LangChain Python monorepo.\n\n## Start Here\n\n1. Identify the package that owns the change with [package-map.md](references\u002Fpackage-map.md).\n2. Inspect package metadata safely with [inspect_langchain_package.py](scripts\u002Finspect_langchain_package.py) when you need the package name, version, dependency groups, Python range, local editable sources, or optional extras.\n3. Run commands from the package directory, not from the repository root, unless [development-workflows.md](references\u002Fdevelopment-workflows.md) explicitly describes a cross-package command.\n4. Validate with the narrowest package-local target first, then broaden only if the changed area requires it.\n5. Use [troubleshooting.md](references\u002Ftroubleshooting.md) when `uv`, package roots, dependency groups, public API checks, model IDs, or optional dependencies are unclear.\n\n## Package Routing\n\n- `libs\u002Fcore`: Core primitives and abstractions in `langchain-core`; use for base interfaces, schemas, messages, tools, runnables, callbacks, serialization, and API contracts shared across packages.\n- `libs\u002Flangchain_v1`: Actively maintained `langchain` package; use for high-level public utilities and agent\u002Fapplication APIs that depend on `langchain-core` and LangGraph.\n- `libs\u002Flangchain`: `langchain-classic`; treat as legacy\u002Fclassic surface and avoid new feature work unless the user specifically targets classic behavior or compatibility.\n- `libs\u002Ftext-splitters`: `langchain-text-splitters`; use for text chunking utilities and splitter-specific tests.\n- `libs\u002Fpartners\u002F\u003Cprovider>`: Team-maintained integration packages such as OpenAI, Anthropic, Ollama, DeepSeek, xAI, and others; keep provider-specific behavior here and route deeper provider implementation to the integrations sub-skill if present at `..\u002Fintegrations\u002FSKILL.md`.\n- `libs\u002Fstandard-tests`: `langchain-tests`; use for standardized conformance tests shared by integrations.\n- `libs\u002Fmodel-profiles`: `langchain-model-profiles`; use for model profile data tooling and profile refresh operations.\n\n## Default Workflow\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\nAdjust groups by package metadata: use `--group lint` for lint-only commands, `--group typing` or `--all-groups` when mypy needs optional typing dependencies, and add `--group test_integration` only for explicitly requested integration tests. Do not use `pip`, `poetry`, `conda`, or ad-hoc virtual environments for LangChain package development.\n\n## Public API Guardrails\n\nBefore changing a public function, class, method, or exported symbol:\n\n- Check whether it is exported from a package `__init__.py` or documented as public.\n- Search existing tests and examples for positional and keyword usage.\n- Preserve existing argument names, positions, defaults, and return types whenever possible.\n- Add new parameters as keyword-only, for example `*, new_option: str | None = None`.\n- Add or update deterministic unit tests under the owning package's `tests\u002Funit_tests\u002F` tree.\n- Use Google-style docstrings for public APIs with Args\u002FReturns\u002FRaises where relevant, single backticks for inline code, and type hints in signatures.\n\nWarn the user before making a signature change that could break code written against last week's release.\n\n## Validation Signals\n\nPrefer package-local validation from the owning directory:\n\n- Unit tests: `uv run --group test pytest tests\u002Funit_tests\u002F...` or `make test TEST_FILE=tests\u002Funit_tests\u002F...`.\n- Lint and formatting check: `make lint_package`, `make lint_tests`, or `make lint_diff` when the package Makefile supports them.\n- Formatting fix: `make format` or `make format_diff` only after confirming it is appropriate for the task.\n- Type checking: `make type` or the package's mypy command through `uv run`.\n- Import checks: `make check_imports` where available; package scripts load source files to catch import-time failures.\n- Version checks: `make check_version` where available; these compare package metadata with package-specific version artifacts.\n\nSkip or defer integration tests when they need network credentials, provider services, Docker services, or heavy optional dependencies and the user did not ask for them. Record the skip condition in the handoff.\n\n## Documentation and Model References\n\n- Use current generally available model names in docs and examples; verify against provider documentation before introducing or updating model IDs.\n- Do not change shipped default model parameters casually because defaults are public behavior.\n- For profile data, use the model-profiles workflow in [development-workflows.md](references\u002Fdevelopment-workflows.md) rather than manually editing generated profile data.\n- Keep documentation examples minimal, deterministic, and aligned with the package that owns the API.\n\n## Maintainer-Level Package Changes\n\nFor adding packages or integrations, keep work at an operational level unless the user explicitly asks for provider-specific implementation:\n\n- Add or update package-local `pyproject.toml`, `uv.lock`, package Makefile, tests, and scripts following existing package patterns.\n- Wire local editable sources through `[tool.uv.sources]` for in-repo dependencies.\n- Update contributor-facing package labels, release\u002Fchange detection, and issue dropdown configuration as required by maintainer guidance, but do not deep-link future agents to source workflow files from this skill.\n- Route provider-specific behavior, credentials, standard integration tests, and model feature details to the integrations sub-skill if available.\n\n## Required References\n\n- [Package map](references\u002Fpackage-map.md)\n- [Development workflows](references\u002Fdevelopment-workflows.md)\n- [Troubleshooting](references\u002Ftroubleshooting.md)\n- [Package metadata inspector](scripts\u002Finspect_langchain_package.py)\n","# LangChain Monorepo Development\n\nUse this sub-skill when a task changes repository structure, package metadata, public Python APIs, tests, lint\u002Ftype workflows, documentation examples, or contributor-facing conventions in the LangChain Python monorepo.\n\n## Start Here\n\n1. Identify the package that owns the change with [package-map.md](references\u002Fpackage-map.md).\n2. Inspect package metadata safely with [inspect_langchain_package.py](scripts\u002Finspect_langchain_package.py) when you need the package name, version, dependency groups, Python range, local editable sources, or optional extras.\n3. Run commands from the package directory, not from the repository root, unless [development-workflows.md](references\u002Fdevelopment-workflows.md) explicitly describes a cross-package command.\n4. Validate with the narrowest package-local target first, then broaden only if the changed area requires it.\n5. Use [troubleshooting.md](references\u002Ftroubleshooting.md) when `uv`, package roots, dependency groups, public API checks, model IDs, or optional dependencies are unclear.\n\n## Package Routing\n\n- `libs\u002Fcore`: Core primitives and abstractions in `langchain-core`; use for base interfaces, schemas, messages, tools, runnables, callbacks, serialization, and API contracts shared across packages.\n- `libs\u002Flangchain_v1`: Actively maintained `langchain` package; use for high-level public utilities and agent\u002Fapplication APIs that depend on `langchain-core` and LangGraph.\n- `libs\u002Flangchain`: `langchain-classic`; treat as legacy\u002Fclassic surface and avoid new feature work unless the user specifically targets classic behavior or compatibility.\n- `libs\u002Ftext-splitters`: `langchain-text-splitters`; use for text chunking utilities and splitter-specific tests.\n- `libs\u002Fpartners\u002F\u003Cprovider>`: Team-maintained integration packages such as OpenAI, Anthropic, Ollama, DeepSeek, xAI, and others; keep provider-specific behavior here and route deeper provider implementation to the integrations sub-skill if present at `..\u002Fintegrations\u002FSKILL.md`.\n- `libs\u002Fstandard-tests`: `langchain-tests`; use for standardized conformance tests shared by integrations.\n- `libs\u002Fmodel-profiles`: `langchain-model-profiles`; use for model profile data tooling and profile refresh operations.\n\n## Default Workflow\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\nAdjust groups by package metadata: use `--group lint` for lint-only commands, `--group typing` or `--all-groups` when mypy needs optional typing dependencies, and add `--group test_integration` only for explicitly requested integration tests. Do not use `pip`, `poetry`, `conda`, or ad-hoc virtual environments for LangChain package development.\n\n## Public API Guardrails\n\nBefore changing a public function, class, method, or exported symbol:\n\n- Check whether it is exported from a package `__init__.py` or documented as public.\n- Search existing tests and examples for positional and keyword usage.\n- Preserve existing argument names, positions, defaults, and return types whenever possible.\n- Add new parameters as keyword-only, for example `*, new_option: str | None = None`.\n- Add or update deterministic unit tests under the owning package's `tests\u002Funit_tests\u002F` tree.\n- Use Google-style docstrings for public APIs with Args\u002FReturns\u002FRaises where relevant, single backticks for inline code, and type hints in signatures.\n\nWarn the user before making a signature change that could break code written against last week's release.\n\n## Validation Signals\n\nPrefer package-local validation from the owning directory:\n\n- Unit tests: `uv run --group test pytest tests\u002Funit_tests\u002F...` or `make test TEST_FILE=tests\u002Funit_tests\u002F...`.\n- Lint and formatting check: `make lint_package`, `make lint_tests`, or `make lint_diff` when the package Makefile supports them.\n- Formatting fix: `make format` or `make format_diff` only after confirming it is appropriate for the task.\n- Type checking: `make type` or the package's mypy command through `uv run`.\n- Import checks: `make check_imports` where available; package scripts load source files to catch import-time failures.\n- Version checks: `make check_version` where available; these compare package metadata with package-specific version artifacts.\n\nSkip or defer integration tests when they need network credentials, provider services, Docker services, or heavy optional dependencies and the user did not ask for them. Record the skip condition in the handoff.\n\n## Documentation and Model References\n\n- Use current generally available model names in docs and examples; verify against provider documentation before introducing or updating model IDs.\n- Do not change shipped default model parameters casually because defaults are public behavior.\n- For profile data, use the model-profiles workflow in [development-workflows.md](references\u002Fdevelopment-workflows.md) rather than manually editing generated profile data.\n- Keep documentation examples minimal, deterministic, and aligned with the package that owns the API.\n\n## Maintainer-Level Package Changes\n\nFor adding packages or integrations, keep work at an operational level unless the user explicitly asks for provider-specific implementation:\n\n- Add or update package-local `pyproject.toml`, `uv.lock`, package Makefile, tests, and scripts following existing package patterns.\n- Wire local editable sources through `[tool.uv.sources]` for in-repo dependencies.\n- Update contributor-facing package labels, release\u002Fchange detection, and issue dropdown configuration as required by maintainer guidance, but do not deep-link future agents to source workflow files from this skill.\n- Route provider-specific behavior, credentials, standard integration tests, and model feature details to the integrations sub-skill if available.\n\n## Required References\n\n- [Package map](references\u002Fpackage-map.md)\n- [Development workflows](references\u002Fdevelopment-workflows.md)\n- [Troubleshooting](references\u002Ftroubleshooting.md)\n- [Package metadata inspector](scripts\u002Finspect_langchain_package.py)\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\u002Fsub-skills\u002Fmonorepo-development",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 monorepo-development",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill monorepo-development",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill monorepo-development","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangchain\u002Fsub-skills\u002Fmonorepo-development\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdevelopment-workflows.md","REFERENCE","参考文档",6723,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangchain\u002Fsub-skills\u002Fmonorepo-development\u002Freferences\u002Fdevelopment-workflows.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fpackage-map.md",5395,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangchain\u002Fsub-skills\u002Fmonorepo-development\u002Freferences\u002Fpackage-map.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",5434,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangchain\u002Fsub-skills\u002Fmonorepo-development\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Finspect_langchain_package.py","SCRIPT","脚本",5222,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flangchain\u002Fsub-skills\u002Fmonorepo-development\u002Fscripts\u002Finspect_langchain_package.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]