[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78WVDCW2Z8P2Y2T55MB0NJP":3,"skill-same:01M78WVDCW2Z8P2Y2T55MB0NJP":86},{"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},"01M78WVDCW2Z8P2Y2T55MB0NJP","face-recognition",null,"Use face_recognition to detect faces, extract landmarks and encodings, compare identities, run the face_recognition and face_detection CLIs, and troubleshoot dlib\u002Fmodel installation.","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\u002Fface-recognition\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: face-recognition\ndescription: \"Use face_recognition to detect faces, extract landmarks and\n  encodings, compare identities, run the face_recognition and face_detection\n  CLIs, and troubleshoot dlib\u002Fmodel installation.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Face Recognition Repo Skill\n\n## Purpose\n\nUse this skill when the task involves the `face_recognition` Python package or\nits installed console tools:\n\n- detecting faces in photos or image folders;\n- extracting face landmarks or 128-dimensional encodings;\n- comparing known and unknown faces with distances or tolerance thresholds;\n- running the `face_recognition` or `face_detection` command-line tools;\n- adapting the repository's image, webcam\u002Fvideo, KNN\u002FSVM, Flask, Raspberry Pi,\n  Docker, or CUDA guidance without depending on the original checkout;\n- debugging `dlib`, `face_recognition_models`, model-file, CLI, optional\n  dependency, or headless-display failures.\n\nRead [repo provenance](references\u002Frepo-provenance.md) before relying on\nversion-sensitive facts or refreshing this skill for a newer checkout.\n\n## Install and quick checks\n\nFor normal package use, install the public distribution and verify imports:\n\n```bash\npython -m pip install face_recognition\npython - \u003C\u003C'PY'\nimport face_recognition\nprint(face_recognition.__version__)\nPY\n```\n\nFor editable repository development, install the checkout with its package\nmetadata (`python -m pip install -e .`) and match a Python version supported by\nthe current repo\u002Ftests when practical. The core runtime dependencies are\n`dlib`, `face_recognition_models`, `numpy`, `Pillow`, and `Click`.\n\nRun [scripts\u002Fcheck_install.py](scripts\u002Fcheck_install.py) when installation,\nmodel loading, or console scripts are uncertain:\n\n```bash\npython scripts\u002Fcheck_install.py\n```\n\nIf imports fail, or if `face_recognition_models` warns about `pkg_resources`,\nread [troubleshooting](references\u002Ftroubleshooting.md) before changing package\nversions.\n\n## Route by task\n\n| If the user needs to... | Read or run |\n| --- | --- |\n| Use Python functions (`load_image_file`, `face_locations`, `face_landmarks`, `face_encodings`, `compare_faces`, `face_distance`, `batch_face_locations`) | [API reference](references\u002Fapi-reference.md) and [workflows](references\u002Fworkflows.md) |\n| Try a safe headless API demo on user-provided images | [scripts\u002Fshowcase_api.py](scripts\u002Fshowcase_api.py) |\n| Recognize identities or detect face boxes from the shell | [CLI reference](references\u002Fcli-reference.md) |\n| Adapt optional image, video\u002Fwebcam, KNN\u002FSVM, Flask, Raspberry Pi, or batch\u002FCNN patterns | [workflows](references\u002Fworkflows.md) |\n| Package or deploy an app using Docker, CUDA, cloud hosts, or PyInstaller | [deployment notes](references\u002Fdeployment.md) |\n| Diagnose install\u002Fimport\u002Fruntime problems | [troubleshooting](references\u002Ftroubleshooting.md) and then `scripts\u002Fcheck_install.py` |\n| Decide whether this skill is stale for a checkout | [repo provenance](references\u002Frepo-provenance.md) |\n\n## Operating rules\n\n- Do not assume the original repository's `examples\u002F`, `docs\u002F`, `tests\u002F`, or\n  image fixtures exist. Use user-provided images or the bundled scripts and\n  references in this skill.\n- Always guard calls like `face_recognition.face_encodings(image)[0]`; no face\n  means an empty list, not a usable encoding.\n- Treat coordinates as `(top, right, bottom, left)`. Crop with\n  `image[top:bottom, left:right]`.\n- The default face detector is CPU-friendly HOG. The CNN detector and\n  `batch_face_locations` are useful for accuracy\u002Fbatch workflows, but CUDA is\n  only an optional acceleration path, not a requirement for the core API.\n- Use `face_distance` or CLI `--show-distance` to tune tolerance; lower\n  tolerance is stricter and can reduce false positives at the cost of more\n  false negatives.\n- For known-person folders, the CLI uses the image file basename as the label\n  and expects one usable face per known image.\n- Optional examples that need OpenCV, Flask, scikit-learn, scipy, Raspberry Pi\n  camera hardware, GUI display, network streams, or Docker should stay optional\n  unless the user explicitly asks for that workflow.\n- Face recognition has fairness, age, privacy, consent, and legal constraints.\n  The repository documents poorer performance on children and variation across\n  demographic groups; surface these caveats in user-facing applications.\n\n## Evidence-backed helper scripts\n\n- [scripts\u002Fcheck_install.py](scripts\u002Fcheck_install.py) checks importability,\n  installed versions, core API smoke behavior, and CLI help availability.\n- [scripts\u002Fshowcase_api.py](scripts\u002Fshowcase_api.py) is a headless adaptation of\n  the image detection, landmark, distance, comparison, and batch example\n  patterns. It accepts image paths supplied by the user and never reads the\n  original repository examples.\n","# Face Recognition Repo Skill\n\n## Purpose\n\nUse this skill when the task involves the `face_recognition` Python package or\nits installed console tools:\n\n- detecting faces in photos or image folders;\n- extracting face landmarks or 128-dimensional encodings;\n- comparing known and unknown faces with distances or tolerance thresholds;\n- running the `face_recognition` or `face_detection` command-line tools;\n- adapting the repository's image, webcam\u002Fvideo, KNN\u002FSVM, Flask, Raspberry Pi,\n  Docker, or CUDA guidance without depending on the original checkout;\n- debugging `dlib`, `face_recognition_models`, model-file, CLI, optional\n  dependency, or headless-display failures.\n\nRead [repo provenance](references\u002Frepo-provenance.md) before relying on\nversion-sensitive facts or refreshing this skill for a newer checkout.\n\n## Install and quick checks\n\nFor normal package use, install the public distribution and verify imports:\n\n```bash\npython -m pip install face_recognition\npython - \u003C\u003C'PY'\nimport face_recognition\nprint(face_recognition.__version__)\nPY\n```\n\nFor editable repository development, install the checkout with its package\nmetadata (`python -m pip install -e .`) and match a Python version supported by\nthe current repo\u002Ftests when practical. The core runtime dependencies are\n`dlib`, `face_recognition_models`, `numpy`, `Pillow`, and `Click`.\n\nRun [scripts\u002Fcheck_install.py](scripts\u002Fcheck_install.py) when installation,\nmodel loading, or console scripts are uncertain:\n\n```bash\npython scripts\u002Fcheck_install.py\n```\n\nIf imports fail, or if `face_recognition_models` warns about `pkg_resources`,\nread [troubleshooting](references\u002Ftroubleshooting.md) before changing package\nversions.\n\n## Route by task\n\n| If the user needs to... | Read or run |\n| --- | --- |\n| Use Python functions (`load_image_file`, `face_locations`, `face_landmarks`, `face_encodings`, `compare_faces`, `face_distance`, `batch_face_locations`) | [API reference](references\u002Fapi-reference.md) and [workflows](references\u002Fworkflows.md) |\n| Try a safe headless API demo on user-provided images | [scripts\u002Fshowcase_api.py](scripts\u002Fshowcase_api.py) |\n| Recognize identities or detect face boxes from the shell | [CLI reference](references\u002Fcli-reference.md) |\n| Adapt optional image, video\u002Fwebcam, KNN\u002FSVM, Flask, Raspberry Pi, or batch\u002FCNN patterns | [workflows](references\u002Fworkflows.md) |\n| Package or deploy an app using Docker, CUDA, cloud hosts, or PyInstaller | [deployment notes](references\u002Fdeployment.md) |\n| Diagnose install\u002Fimport\u002Fruntime problems | [troubleshooting](references\u002Ftroubleshooting.md) and then `scripts\u002Fcheck_install.py` |\n| Decide whether this skill is stale for a checkout | [repo provenance](references\u002Frepo-provenance.md) |\n\n## Operating rules\n\n- Do not assume the original repository's `examples\u002F`, `docs\u002F`, `tests\u002F`, or\n  image fixtures exist. Use user-provided images or the bundled scripts and\n  references in this skill.\n- Always guard calls like `face_recognition.face_encodings(image)[0]`; no face\n  means an empty list, not a usable encoding.\n- Treat coordinates as `(top, right, bottom, left)`. Crop with\n  `image[top:bottom, left:right]`.\n- The default face detector is CPU-friendly HOG. The CNN detector and\n  `batch_face_locations` are useful for accuracy\u002Fbatch workflows, but CUDA is\n  only an optional acceleration path, not a requirement for the core API.\n- Use `face_distance` or CLI `--show-distance` to tune tolerance; lower\n  tolerance is stricter and can reduce false positives at the cost of more\n  false negatives.\n- For known-person folders, the CLI uses the image file basename as the label\n  and expects one usable face per known image.\n- Optional examples that need OpenCV, Flask, scikit-learn, scipy, Raspberry Pi\n  camera hardware, GUI display, network streams, or Docker should stay optional\n  unless the user explicitly asks for that workflow.\n- Face recognition has fairness, age, privacy, consent, and legal constraints.\n  The repository documents poorer performance on children and variation across\n  demographic groups; surface these caveats in user-facing applications.\n\n## Evidence-backed helper scripts\n\n- [scripts\u002Fcheck_install.py](scripts\u002Fcheck_install.py) checks importability,\n  installed versions, core API smoke behavior, and CLI help availability.\n- [scripts\u002Fshowcase_api.py](scripts\u002Fshowcase_api.py) is a headless adaptation of\n  the image detection, landmark, distance, comparison, and batch example\n  patterns. It accepts image paths supplied by the user and never reads the\n  original repository examples.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fface-recognition",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 face-recognition",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill face-recognition",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill face-recognition","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fface-recognition\u002FSKILL.md",[46,52,56,60,64,68,72,76,82],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",6237,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fface-recognition\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fcli-reference.md",4112,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fface-recognition\u002Freferences\u002Fcli-reference.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fdeployment.md",3670,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fface-recognition\u002Freferences\u002Fdeployment.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Frepo-provenance.md",2189,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fface-recognition\u002Freferences\u002Frepo-provenance.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Frepo-routing-metadata.json",421,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fface-recognition\u002Freferences\u002Frepo-routing-metadata.json",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Ftroubleshooting.md",6633,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fface-recognition\u002Freferences\u002Ftroubleshooting.md",{"path":73,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fworkflows.md",6963,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fface-recognition\u002Freferences\u002Fworkflows.md",{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"scripts\u002Fcheck_install.py","SCRIPT","脚本",9305,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fface-recognition\u002Fscripts\u002Fcheck_install.py",{"path":83,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":84,"sourceHtmlUrl":85},"scripts\u002Fshowcase_api.py",9508,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fface-recognition\u002Fscripts\u002Fshowcase_api.py",[87,95,102,109,116,123],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"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":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"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":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"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":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"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",[],[]]