[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796TCDHTKYC8873MV3B063F":3,"skill-same:01M796TCDHTKYC8873MV3B063F":75},{"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},"01M796TCDHTKYC8873MV3B063F","portrait-workflows",null,"Run U-2-Net portrait drawing, own-image face-crop portrait inference, and portrait\u002Foriginal compositing workflows.","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\u002Fu-2-net\u002Fsub-skills\u002Fportrait-workflows\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: portrait-workflows\ndescription: \"Run U-2-Net portrait drawing, own-image face-crop portrait\n  inference, and portrait\u002Foriginal compositing workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Portrait Workflows\n\nUse this sub-skill when the task is portrait drawing\u002Fgeneration with the U-2-Net portrait checkpoint, own-photo face-crop portrait inference, Haar-cascade handling, or portrait\u002Foriginal composite images with explicit blur and blend controls.\n\n## Start here\n\n1. Choose the portrait workflow in [workflows](references\u002Fworkflows.md): APDrawingGAN-style portrait-set inference, own-image face-crop inference, or portrait\u002Foriginal compositing.\n2. Run the bundled helpers instead of original demo scripts:\n   - [`scripts\u002Fportrait_infer.py`](scripts\u002Fportrait_infer.py) for portrait-set and own-image portrait maps.\n   - [`scripts\u002Fportrait_composite.py`](scripts\u002Fportrait_composite.py) for Gaussian-blurred original plus portrait-map composites.\n3. Supply explicit `u2net_portrait.pth`-compatible weights with `--weights`; pretrained portrait weights are not bundled.\n4. Use [troubleshooting](references\u002Ftroubleshooting.md) when weights, OpenCV, cascade parsing, CUDA selection, no-face fallback, alpha\u002Fsigma validation, or image quality is the problem.\n\n## Common routes\n\n- **APDrawingGAN-style portrait inputs:** use `portrait_infer.py --mode portrait-set`. Inputs should already be split\u002Fcropped portrait images, commonly 512x512.\n- **Own photos:** use `portrait_infer.py --mode own-images`. It uses the bundled Haar cascade by default, selects the largest face, crops\u002Fpads\u002Fresizes to 512, and falls back to the whole image if no face is found.\n- **Composite style:** use `portrait_composite.py --sigma 20 --alpha 0.5` or other explicit values. It writes `*_sigma_\u003Csigma>_alpha_\u003Calpha>_composite.png` with numeric punctuation sanitized for portability.\n- **Plumbing-only smoke checks:** add `--allow-random-weights-for-smoke --max-images 1 --device cpu` only to verify imports, preprocessing, forward pass, and output writing. Do not treat random-weight outputs as portrait quality evidence.\n\n## Quality constraints\n\nFor own photos, high-quality portrait drawing requires the head region to be close to or larger than 512x512 and the head background to be relatively clear. Small, blurry, occluded, profile, crowded, or cluttered photos may run but usually produce weak portraits.\n\n## Boundaries\n\n- Generic salient-object masks, background removal, and human\u002Fperson masks route to `salient-object-inference`.\n- Architecture internals, side-output semantics, model variant choice, and checkpoint-shape diagnosis route to `model-architecture`.\n- Dataset construction, augmentation, retraining, loss wiring, and long training runs route to `data-and-training`.\n\n## Minimal commands\n\nPortrait-set inference:\n\n```bash\npython scripts\u002Fportrait_infer.py \\\n  --weights PATH_TO_WEIGHTS\u002Fu2net_portrait.pth \\\n  --input-dir INPUT_PORTRAITS \\\n  --output-dir PORTRAIT_RESULTS \\\n  --mode portrait-set \\\n  --device auto\n```\n\nOwn-image inference with the bundled cascade:\n\n```bash\npython scripts\u002Fportrait_infer.py \\\n  --weights PATH_TO_WEIGHTS\u002Fu2net_portrait.pth \\\n  --input-dir OWN_IMAGES \\\n  --output-dir YOUR_PORTRAIT_RESULTS \\\n  --mode own-images \\\n  --device auto\n```\n\nComposite with README-style parameters:\n\n```bash\npython scripts\u002Fportrait_composite.py \\\n  --weights PATH_TO_WEIGHTS\u002Fu2net_portrait.pth \\\n  --input-dir OWN_IMAGES \\\n  --output-dir COMPOSITE_RESULTS \\\n  --sigma 20 \\\n  --alpha 0.5 \\\n  --device auto\n```\n","# Portrait Workflows\n\nUse this sub-skill when the task is portrait drawing\u002Fgeneration with the U-2-Net portrait checkpoint, own-photo face-crop portrait inference, Haar-cascade handling, or portrait\u002Foriginal composite images with explicit blur and blend controls.\n\n## Start here\n\n1. Choose the portrait workflow in [workflows](references\u002Fworkflows.md): APDrawingGAN-style portrait-set inference, own-image face-crop inference, or portrait\u002Foriginal compositing.\n2. Run the bundled helpers instead of original demo scripts:\n   - [`scripts\u002Fportrait_infer.py`](scripts\u002Fportrait_infer.py) for portrait-set and own-image portrait maps.\n   - [`scripts\u002Fportrait_composite.py`](scripts\u002Fportrait_composite.py) for Gaussian-blurred original plus portrait-map composites.\n3. Supply explicit `u2net_portrait.pth`-compatible weights with `--weights`; pretrained portrait weights are not bundled.\n4. Use [troubleshooting](references\u002Ftroubleshooting.md) when weights, OpenCV, cascade parsing, CUDA selection, no-face fallback, alpha\u002Fsigma validation, or image quality is the problem.\n\n## Common routes\n\n- **APDrawingGAN-style portrait inputs:** use `portrait_infer.py --mode portrait-set`. Inputs should already be split\u002Fcropped portrait images, commonly 512x512.\n- **Own photos:** use `portrait_infer.py --mode own-images`. It uses the bundled Haar cascade by default, selects the largest face, crops\u002Fpads\u002Fresizes to 512, and falls back to the whole image if no face is found.\n- **Composite style:** use `portrait_composite.py --sigma 20 --alpha 0.5` or other explicit values. It writes `*_sigma_\u003Csigma>_alpha_\u003Calpha>_composite.png` with numeric punctuation sanitized for portability.\n- **Plumbing-only smoke checks:** add `--allow-random-weights-for-smoke --max-images 1 --device cpu` only to verify imports, preprocessing, forward pass, and output writing. Do not treat random-weight outputs as portrait quality evidence.\n\n## Quality constraints\n\nFor own photos, high-quality portrait drawing requires the head region to be close to or larger than 512x512 and the head background to be relatively clear. Small, blurry, occluded, profile, crowded, or cluttered photos may run but usually produce weak portraits.\n\n## Boundaries\n\n- Generic salient-object masks, background removal, and human\u002Fperson masks route to `salient-object-inference`.\n- Architecture internals, side-output semantics, model variant choice, and checkpoint-shape diagnosis route to `model-architecture`.\n- Dataset construction, augmentation, retraining, loss wiring, and long training runs route to `data-and-training`.\n\n## Minimal commands\n\nPortrait-set inference:\n\n```bash\npython scripts\u002Fportrait_infer.py \\\n  --weights PATH_TO_WEIGHTS\u002Fu2net_portrait.pth \\\n  --input-dir INPUT_PORTRAITS \\\n  --output-dir PORTRAIT_RESULTS \\\n  --mode portrait-set \\\n  --device auto\n```\n\nOwn-image inference with the bundled cascade:\n\n```bash\npython scripts\u002Fportrait_infer.py \\\n  --weights PATH_TO_WEIGHTS\u002Fu2net_portrait.pth \\\n  --input-dir OWN_IMAGES \\\n  --output-dir YOUR_PORTRAIT_RESULTS \\\n  --mode own-images \\\n  --device auto\n```\n\nComposite with README-style parameters:\n\n```bash\npython scripts\u002Fportrait_composite.py \\\n  --weights PATH_TO_WEIGHTS\u002Fu2net_portrait.pth \\\n  --input-dir OWN_IMAGES \\\n  --output-dir COMPOSITE_RESULTS \\\n  --sigma 20 \\\n  --alpha 0.5 \\\n  --device auto\n```\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\u002Fu-2-net\u002Fsub-skills\u002Fportrait-workflows",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 portrait-workflows",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill portrait-workflows",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill portrait-workflows","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fu-2-net\u002Fsub-skills\u002Fportrait-workflows\u002FSKILL.md",[47,53,57,61,67,71],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",2709,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fu-2-net\u002Fsub-skills\u002Fportrait-workflows\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",2350,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fu-2-net\u002Fsub-skills\u002Fportrait-workflows\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",3361,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fu-2-net\u002Fsub-skills\u002Fportrait-workflows\u002Freferences\u002Fworkflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fhaarcascade_frontalface_default.xml","SCRIPT","脚本",930127,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fu-2-net\u002Fsub-skills\u002Fportrait-workflows\u002Fscripts\u002Fhaarcascade_frontalface_default.xml",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fportrait_composite.py",6999,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fu-2-net\u002Fsub-skills\u002Fportrait-workflows\u002Fscripts\u002Fportrait_composite.py",{"path":72,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fportrait_infer.py",9242,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fu-2-net\u002Fsub-skills\u002Fportrait-workflows\u002Fscripts\u002Fportrait_infer.py",[76,83,90,97,104,111],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]