[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7987A3AX2ETKA6J3AXBY3JC":3,"skill-same:01M7987A3AX2ETKA6J3AXBY3JC":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},"01M7987A3AX2ETKA6J3AXBY3JC","reduced_recovery_harness",null,"Build executable soft-mode LDM proxy recovery artifacts from generated skills with mechanism checks and validator evidence.","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\u002Flatent_diffusion_models\u002Freduced_recovery_harness\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: reduced_recovery_harness\ndescription: Build executable soft-mode LDM proxy recovery artifacts from generated skills with mechanism checks and validator evidence.\n---\n\n# Reduced Recovery Harness\n\nUse this skill when full Latent Diffusion Model checkpoints or datasets are unavailable in a bounded run and soft-mode recovery permits a declared proxy. It coordinates generated skill scripts, writes recovery artifacts, and prepares evidence for the Distiller recovery validator. Do not use it in hard mode as accepted success.\n\n## Inputs\n\n- Attempt directory containing `module_plan.json`.\n- Runtime handoff path from environment preparation.\n- Generated skills root containing compression, objective, conditioning, and spatial scripts.\n- Optional resource provenance for a synthetic or resource-derived image item.\n\n## Outputs\n\n- `recovery\u002Frecovery_result.json`.\n- `recovery\u002Flogs\u002Ftraining_trace.json`.\n- `recovery\u002Flogs\u002Fgenerated_data_item.json`.\n- `recovery\u002Flogs\u002Fgenerated_skill_invocations.json`.\n- `recovery\u002Fsource_manifest.json` and command evidence produced by the caller.\n\n## Workflow\n\n1. Read the module-plan target and runtime blockers.\n2. Declare whether the experiment is reduced\u002Fproxy and why full recovery is blocked.\n3. Invoke the generated module scripts instead of duplicating their logic silently.\n4. Combine their outputs into mechanism checks for compression, latent noising, cross-attention, spatial planning, and optimizer execution.\n5. Write validation-compatible artifacts and keep the original source repository out of recovery sources.\n\n## Validation\n\nRun `python scripts\u002Fbuild_proxy_result.py --attempt-dir \u003Cattempt> --skills-root \u003Cgenerated_skills_root> --runtime-handoff \u003Cattempt>\u002Fenvironment\u002Fruntime_handoff.json`. Then run the Distiller recovery validator on the attempt directory.\n\n## Limitations\n\nThe harness produces a reduced mechanism proxy, not a published FID reproduction. It depends on the generated module scripts and must be rerun after skill refinements.\n","# Reduced Recovery Harness\n\nUse this skill when full Latent Diffusion Model checkpoints or datasets are unavailable in a bounded run and soft-mode recovery permits a declared proxy. It coordinates generated skill scripts, writes recovery artifacts, and prepares evidence for the Distiller recovery validator. Do not use it in hard mode as accepted success.\n\n## Inputs\n\n- Attempt directory containing `module_plan.json`.\n- Runtime handoff path from environment preparation.\n- Generated skills root containing compression, objective, conditioning, and spatial scripts.\n- Optional resource provenance for a synthetic or resource-derived image item.\n\n## Outputs\n\n- `recovery\u002Frecovery_result.json`.\n- `recovery\u002Flogs\u002Ftraining_trace.json`.\n- `recovery\u002Flogs\u002Fgenerated_data_item.json`.\n- `recovery\u002Flogs\u002Fgenerated_skill_invocations.json`.\n- `recovery\u002Fsource_manifest.json` and command evidence produced by the caller.\n\n## Workflow\n\n1. Read the module-plan target and runtime blockers.\n2. Declare whether the experiment is reduced\u002Fproxy and why full recovery is blocked.\n3. Invoke the generated module scripts instead of duplicating their logic silently.\n4. Combine their outputs into mechanism checks for compression, latent noising, cross-attention, spatial planning, and optimizer execution.\n5. Write validation-compatible artifacts and keep the original source repository out of recovery sources.\n\n## Validation\n\nRun `python scripts\u002Fbuild_proxy_result.py --attempt-dir \u003Cattempt> --skills-root \u003Cgenerated_skills_root> --runtime-handoff \u003Cattempt>\u002Fenvironment\u002Fruntime_handoff.json`. Then run the Distiller recovery validator on the attempt directory.\n\n## Limitations\n\nThe harness produces a reduced mechanism proxy, not a published FID reproduction. It depends on the generated module scripts and must be rerun after skill refinements.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbridging-data-gaps\u002Fskill\u002Flatent_diffusion_models\u002Freduced_recovery_harness",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 reduced_recovery_harness",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill reduced_recovery_harness",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill reduced_recovery_harness","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\u002Flatent_diffusion_models\u002Freduced_recovery_harness\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fbuild_proxy_result.py","SCRIPT","脚本",3353,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbridging-data-gaps\u002Fskill\u002Flatent_diffusion_models\u002Freduced_recovery_harness\u002Fscripts\u002Fbuild_proxy_result.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"tests\u002Ftest_build_proxy_result.py",1689,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbridging-data-gaps\u002Fskill\u002Flatent_diffusion_models\u002Freduced_recovery_harness\u002Ftests\u002Ftest_build_proxy_result.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",[],[]]