[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7948H4YJST228CTR62RWWB8":3,"skill-same:01M7948H4YJST228CTR62RWWB8":67},{"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},"01M7948H4YJST228CTR62RWWB8","repository-development",null,"Edit RF-DETR source while following project contribution, test, style, docs, packaging, model-selection, and CI conventions.","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\u002Frf-detr\u002Fsub-skills\u002Frepository-development\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: repository-development\ndescription: \"Edit RF-DETR source while following project contribution, test,\n  style, docs, packaging, model-selection, and CI conventions.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# RF-DETR Repository Development\n\nUse this sub-skill when you are changing RF-DETR source, tests, docs, packaging,\nor CI. It is for contributor workflows, not for end-user inference, training, or\nexport recipes.\n\n## Start Here\n\n1. Read [Contributor guidance](references\u002Fcontributor-guidance.md) before editing\n   source, tests, docs, package metadata, or workflow files.\n2. Use [Test selection](references\u002Ftest-selection.md) to choose focused checks\n   during development and full gates before handoff.\n3. If a check fails or optional backends are involved, use\n   [Troubleshooting](references\u002Ftroubleshooting.md).\n4. To get a dry recommendation from changed paths, run:\n\n```bash\npython sub-skills\u002Frepository-development\u002Fscripts\u002Fselect_checks.py PATH [PATH ...]\n```\n\nThe script prints commands only; it does not run tests or modify files.\n\n## Routing\n\n- For Python source, tests, examples, docs snippets, or configs, start with\n  [Contributor guidance](references\u002Fcontributor-guidance.md), then choose checks\n  from [Test selection](references\u002Ftest-selection.md).\n- For test helpers, fixtures, parametrization, or markers, read\n  [test style](references\u002Fcontributor-guidance.md#test-style) and the\n  [test tree map](references\u002Ftest-selection.md#test-tree-map).\n- For package metadata, extras, lock\u002Fdependency behavior, or CI install plans,\n  read [optional backend guidance](references\u002Fcontributor-guidance.md#dependencies-and-optional-backends)\n  and [dependency checks](references\u002Ftest-selection.md#dependency-packaging-docs-and-ci-checks).\n- For documentation pages or MkDocs config, read\n  [docs\u002Fbuild guidance](references\u002Fcontributor-guidance.md#docs-builds-and-package-builds)\n  and [docs troubleshooting](references\u002Ftroubleshooting.md#docs-build-failures).\n- For pre-commit, ruff, mypy, license headers, docstrings, or formatting, read\n  [code quality rules](references\u002Fcontributor-guidance.md#code-quality-rules) and\n  [style troubleshooting](references\u002Ftroubleshooting.md#pre-commit-and-style-failures).\n- For CI-only GPU\u002FXLA\u002FCoreML\u002FExecuTorch\u002FTensorRT failures, use the\n  [CI\u002Fbackend split](references\u002Ftest-selection.md#ci-and-backend-split) and\n  [backend troubleshooting](references\u002Ftroubleshooting.md#optional-backend-and-ci-failures).\n\n## Non-Negotiables\n\n- Use TDD: failing test first for bug fixes; comprehensive tests for features.\n- Every new or changed function\u002Fclass needs type hints and a Google-style\n  docstring; do not duplicate types inside docstrings.\n- Python files need the RF-DETR license header.\n- Run `pre-commit run --all-files` before any commit\u002Fhandoff.\n- Default examples\u002Fdocs\u002Ftests to `RFDETRSmall` \u002F `\"rfdetr-small\"`; do not add new\n  `RFDETRBase`, `\"rfdetr-base\"`, segmentation preview, or detection preview usage.\n  Keypoint preview is the only preview variant to use for new material.\n- Keep imports direct and module-scope unless there is a clear optional-dependency,\n  circular-import, import-behavior-test, or startup-side-effect reason.\n- Prefer small visible duplication over a helper that adds indirection without\n  reducing cognitive load.\n","# RF-DETR Repository Development\n\nUse this sub-skill when you are changing RF-DETR source, tests, docs, packaging,\nor CI. It is for contributor workflows, not for end-user inference, training, or\nexport recipes.\n\n## Start Here\n\n1. Read [Contributor guidance](references\u002Fcontributor-guidance.md) before editing\n   source, tests, docs, package metadata, or workflow files.\n2. Use [Test selection](references\u002Ftest-selection.md) to choose focused checks\n   during development and full gates before handoff.\n3. If a check fails or optional backends are involved, use\n   [Troubleshooting](references\u002Ftroubleshooting.md).\n4. To get a dry recommendation from changed paths, run:\n\n```bash\npython sub-skills\u002Frepository-development\u002Fscripts\u002Fselect_checks.py PATH [PATH ...]\n```\n\nThe script prints commands only; it does not run tests or modify files.\n\n## Routing\n\n- For Python source, tests, examples, docs snippets, or configs, start with\n  [Contributor guidance](references\u002Fcontributor-guidance.md), then choose checks\n  from [Test selection](references\u002Ftest-selection.md).\n- For test helpers, fixtures, parametrization, or markers, read\n  [test style](references\u002Fcontributor-guidance.md#test-style) and the\n  [test tree map](references\u002Ftest-selection.md#test-tree-map).\n- For package metadata, extras, lock\u002Fdependency behavior, or CI install plans,\n  read [optional backend guidance](references\u002Fcontributor-guidance.md#dependencies-and-optional-backends)\n  and [dependency checks](references\u002Ftest-selection.md#dependency-packaging-docs-and-ci-checks).\n- For documentation pages or MkDocs config, read\n  [docs\u002Fbuild guidance](references\u002Fcontributor-guidance.md#docs-builds-and-package-builds)\n  and [docs troubleshooting](references\u002Ftroubleshooting.md#docs-build-failures).\n- For pre-commit, ruff, mypy, license headers, docstrings, or formatting, read\n  [code quality rules](references\u002Fcontributor-guidance.md#code-quality-rules) and\n  [style troubleshooting](references\u002Ftroubleshooting.md#pre-commit-and-style-failures).\n- For CI-only GPU\u002FXLA\u002FCoreML\u002FExecuTorch\u002FTensorRT failures, use the\n  [CI\u002Fbackend split](references\u002Ftest-selection.md#ci-and-backend-split) and\n  [backend troubleshooting](references\u002Ftroubleshooting.md#optional-backend-and-ci-failures).\n\n## Non-Negotiables\n\n- Use TDD: failing test first for bug fixes; comprehensive tests for features.\n- Every new or changed function\u002Fclass needs type hints and a Google-style\n  docstring; do not duplicate types inside docstrings.\n- Python files need the RF-DETR license header.\n- Run `pre-commit run --all-files` before any commit\u002Fhandoff.\n- Default examples\u002Fdocs\u002Ftests to `RFDETRSmall` \u002F `\"rfdetr-small\"`; do not add new\n  `RFDETRBase`, `\"rfdetr-base\"`, segmentation preview, or detection preview usage.\n  Keypoint preview is the only preview variant to use for new material.\n- Keep imports direct and module-scope unless there is a clear optional-dependency,\n  circular-import, import-behavior-test, or startup-side-effect reason.\n- Prefer small visible duplication over a helper that adds indirection without\n  reducing cognitive load.\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\u002Frf-detr\u002Fsub-skills\u002Frepository-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":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill repository-development",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill repository-development",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill repository-development","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002Fsub-skills\u002Frepository-development\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcontributor-guidance.md","REFERENCE","参考文档",10302,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002Fsub-skills\u002Frepository-development\u002Freferences\u002Fcontributor-guidance.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftest-selection.md",9329,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002Fsub-skills\u002Frepository-development\u002Freferences\u002Ftest-selection.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",9663,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002Fsub-skills\u002Frepository-development\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fselect_checks.py","SCRIPT","脚本",18326,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frf-detr\u002Fsub-skills\u002Frepository-development\u002Fscripts\u002Fselect_checks.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]