[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7984QDFY3JNJNJXFT2SWDBM":3,"skill-same:01M7984QDFY3JNJNJXFT2SWDBM":54},{"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7984QDFY3JNJNJXFT2SWDBM","cdc_similarity_loss",null,"Compute cross-domain distance consistency softmax-KL losses for few-shot generator adaptation experiments.","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\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbridging-data-gaps\u002Fskill\u002Fcdc_few_shot_image_generation\u002Fcdc_similarity_loss\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cdc_similarity_loss\ndescription: Compute cross-domain distance consistency softmax-KL losses for few-shot generator adaptation experiments.\n---\n\n# Cross-Domain Distance Consistency Loss\n\nUse this skill when implementing or auditing a few-shot generator adaptation run that must preserve the relative relationships learned by a pretrained source generator. The skill is appropriate for full image features, intermediate generator activations, or reduced vector proxies. Do not use it as a target-realism loss by itself; it only checks whether source and adapted samples keep comparable pairwise similarity structure.\n\n## Inputs\n- `source_layers`: mapping from layer name to a list of source activation vectors for the same latent batch.\n- `adapted_layers`: mapping with identical layer names and vector counts for the adapted generator.\n- Optional `temperature` and `eps` values for stable probability and KL calculations.\n\n## Outputs\n- Total CDC loss averaged across layers and anchor rows.\n- Per-layer KL divergence values.\n- Source and adapted row-wise similarity distributions for debugging.\n\n## Workflow\n1. For each layer, compute cosine similarities between each anchor vector and every non-self vector in the batch.\n2. Convert each anchor row to a probability distribution using a temperature-scaled softmax.\n3. Compute KL divergence from the source distribution to the adapted distribution for every anchor row.\n4. Average the KL values across layers and rows and save row diagnostics when requested.\n5. Treat identical source\u002Fadapted activations as a near-zero-loss sanity check.\n\n## Validation\nRun `python tests\u002Ftest_cdc_loss.py` or validate this skill tree with `validate_skill_tree.py --run-tests`.\n\n## Limitations\nThis skill does not train a generator, compute LPIPS, or replace discriminator losses. In a reduced recovery it can operate on vectors, but the recovery must explicitly label that execution as proxy evidence.\n","# Cross-Domain Distance Consistency Loss\n\nUse this skill when implementing or auditing a few-shot generator adaptation run that must preserve the relative relationships learned by a pretrained source generator. The skill is appropriate for full image features, intermediate generator activations, or reduced vector proxies. Do not use it as a target-realism loss by itself; it only checks whether source and adapted samples keep comparable pairwise similarity structure.\n\n## Inputs\n- `source_layers`: mapping from layer name to a list of source activation vectors for the same latent batch.\n- `adapted_layers`: mapping with identical layer names and vector counts for the adapted generator.\n- Optional `temperature` and `eps` values for stable probability and KL calculations.\n\n## Outputs\n- Total CDC loss averaged across layers and anchor rows.\n- Per-layer KL divergence values.\n- Source and adapted row-wise similarity distributions for debugging.\n\n## Workflow\n1. For each layer, compute cosine similarities between each anchor vector and every non-self vector in the batch.\n2. Convert each anchor row to a probability distribution using a temperature-scaled softmax.\n3. Compute KL divergence from the source distribution to the adapted distribution for every anchor row.\n4. Average the KL values across layers and rows and save row diagnostics when requested.\n5. Treat identical source\u002Fadapted activations as a near-zero-loss sanity check.\n\n## Validation\nRun `python tests\u002Ftest_cdc_loss.py` or validate this skill tree with `validate_skill_tree.py --run-tests`.\n\n## Limitations\nThis skill does not train a generator, compute LPIPS, or replace discriminator losses. In a reduced recovery it can operate on vectors, but the recovery must explicitly label that execution as proxy evidence.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbridging-data-gaps\u002Fskill\u002Fcdc_few_shot_image_generation\u002Fcdc_similarity_loss",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill cdc_similarity_loss",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill cdc_similarity_loss",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill cdc_similarity_loss","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbridging-data-gaps\u002Fskill\u002Fcdc_few_shot_image_generation\u002Fcdc_similarity_loss\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fcdc_loss.py","SCRIPT","脚本",2205,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbridging-data-gaps\u002Fskill\u002Fcdc_few_shot_image_generation\u002Fcdc_similarity_loss\u002Fscripts\u002Fcdc_loss.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"tests\u002Ftest_cdc_loss.py",415,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbridging-data-gaps\u002Fskill\u002Fcdc_few_shot_image_generation\u002Fcdc_similarity_loss\u002Ftests\u002Ftest_cdc_loss.py",[55,62,69,76,83,90],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"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":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":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},"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":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},"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":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},"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",[],[]]