[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78TY59E7Z5PQ2KBQ364BX40":3,"skill-same:01M78TY59E7Z5PQ2KBQ364BX40":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},"01M78TY59E7Z5PQ2KBQ364BX40","prompt-engineering",null,"Build CLIP zero-shot class prompts, tokenizer-safe templates, and normalized text classifier weights.","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\u002Fclip\u002Fsub-skills\u002Fprompt-engineering\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: prompt-engineering\ndescription: \"Build CLIP zero-shot class prompts, tokenizer-safe templates, and\n  normalized text classifier weights.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Prompt Engineering\n\nUse this sub-skill when an agent needs to turn class labels into CLIP text prompts, tokenize them safely, build zero-shot classifier weights, or diagnose prompt\u002Ftemplate failures.\n\n## Route\n\n- Start with `references\u002Fprompting-workflows.md` for class taxonomies, template design, prompt ensembling, normalized text features, and top-k zero-shot scoring.\n- Use `references\u002Ftokenization.md` before generating large prompt sets or when `clip.tokenize` raises context-length errors.\n- Use `references\u002Ftroubleshooting.md` for unsafe category design, malformed templates, device mismatches, unnormalized features, and multilingual\u002FEnglish limitations.\n- Use `scripts\u002Fbuild_zeroshot_classifier.py` when you need a reusable helper for expanding templates, dry-run tokenization, or building normalized classifier weights from a loaded CLIP model.\n\n## Boundaries\n\n- Model selection, `clip.load`, image preprocessing, and image-text inference setup belong in `..\u002Fmodel-loading-inference\u002F`.\n- Linear probes, cached image feature evaluation, and dataset-scale benchmark loops belong in `..\u002Ffeature-evaluation\u002F`.\n- Dataset downloads mentioned in source docs are reference-only; do not make prompt workflows depend on downloading raw datasets by default.\n\n## Minimal Safe Flow\n\n1. Define a fixed English class taxonomy with non-overlapping labels and avoid sensitive or deployment-risk categories unless the user explicitly asks for a research-only audit.\n2. Choose templates containing exactly one `{}` placeholder, such as `a photo of a {}.` or domain-specific variants like `a photo of a {}, a type of bird.`\n3. Dry-run tokenize the expanded prompts with `clip.tokenize(..., context_length=77, truncate=False)` before running model inference.\n4. Encode prompt batches with a loaded CLIP model, normalize every prompt embedding, average templates per class, normalize the averaged class vector, then stack weights as `[text_feature_dim, num_classes]`.\n5. For image classification, normalize image features and compute `100.0 * image_features @ zeroshot_weights`; treat softmax\u002Ftop-k scores as relative to the candidate class list, not calibrated real-world confidence.\n\n## Helper Script\n\nDry-run prompt tokenization without loading or downloading model checkpoints:\n\n```bash\npython sub-skills\u002Fprompt-engineering\u002Fscripts\u002Fbuild_zeroshot_classifier.py \\\n  --class-name cat --class-name \"electric ray\" \\\n  --template \"a photo of a {}.\" \\\n  --dry-run-tokenize\n```\n\nBuild classifier weights only when a model load is explicitly requested or a caller imports `build_zeroshot_classifier(model, class_names, templates)` with an already loaded model. See `references\u002Fprompting-workflows.md` for the importable contract.\n","# Prompt Engineering\n\nUse this sub-skill when an agent needs to turn class labels into CLIP text prompts, tokenize them safely, build zero-shot classifier weights, or diagnose prompt\u002Ftemplate failures.\n\n## Route\n\n- Start with `references\u002Fprompting-workflows.md` for class taxonomies, template design, prompt ensembling, normalized text features, and top-k zero-shot scoring.\n- Use `references\u002Ftokenization.md` before generating large prompt sets or when `clip.tokenize` raises context-length errors.\n- Use `references\u002Ftroubleshooting.md` for unsafe category design, malformed templates, device mismatches, unnormalized features, and multilingual\u002FEnglish limitations.\n- Use `scripts\u002Fbuild_zeroshot_classifier.py` when you need a reusable helper for expanding templates, dry-run tokenization, or building normalized classifier weights from a loaded CLIP model.\n\n## Boundaries\n\n- Model selection, `clip.load`, image preprocessing, and image-text inference setup belong in `..\u002Fmodel-loading-inference\u002F`.\n- Linear probes, cached image feature evaluation, and dataset-scale benchmark loops belong in `..\u002Ffeature-evaluation\u002F`.\n- Dataset downloads mentioned in source docs are reference-only; do not make prompt workflows depend on downloading raw datasets by default.\n\n## Minimal Safe Flow\n\n1. Define a fixed English class taxonomy with non-overlapping labels and avoid sensitive or deployment-risk categories unless the user explicitly asks for a research-only audit.\n2. Choose templates containing exactly one `{}` placeholder, such as `a photo of a {}.` or domain-specific variants like `a photo of a {}, a type of bird.`\n3. Dry-run tokenize the expanded prompts with `clip.tokenize(..., context_length=77, truncate=False)` before running model inference.\n4. Encode prompt batches with a loaded CLIP model, normalize every prompt embedding, average templates per class, normalize the averaged class vector, then stack weights as `[text_feature_dim, num_classes]`.\n5. For image classification, normalize image features and compute `100.0 * image_features @ zeroshot_weights`; treat softmax\u002Ftop-k scores as relative to the candidate class list, not calibrated real-world confidence.\n\n## Helper Script\n\nDry-run prompt tokenization without loading or downloading model checkpoints:\n\n```bash\npython sub-skills\u002Fprompt-engineering\u002Fscripts\u002Fbuild_zeroshot_classifier.py \\\n  --class-name cat --class-name \"electric ray\" \\\n  --template \"a photo of a {}.\" \\\n  --dry-run-tokenize\n```\n\nBuild classifier weights only when a model load is explicitly requested or a caller imports `build_zeroshot_classifier(model, class_names, templates)` with an already loaded model. See `references\u002Fprompting-workflows.md` for the importable contract.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fclip\u002Fsub-skills\u002Fprompt-engineering",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 prompt-engineering",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill prompt-engineering",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill prompt-engineering","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fclip\u002Fsub-skills\u002Fprompt-engineering\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fprompting-workflows.md","REFERENCE","参考文档",6157,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fclip\u002Fsub-skills\u002Fprompt-engineering\u002Freferences\u002Fprompting-workflows.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftokenization.md",4425,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fclip\u002Fsub-skills\u002Fprompt-engineering\u002Freferences\u002Ftokenization.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",4537,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fclip\u002Fsub-skills\u002Fprompt-engineering\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fbuild_zeroshot_classifier.py","SCRIPT","脚本",12575,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fclip\u002Fsub-skills\u002Fprompt-engineering\u002Fscripts\u002Fbuild_zeroshot_classifier.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",[],[]]