[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M797WPB43MYC52MSVVPKJAGD":3,"skill-same:01M797WPB43MYC52MSVVPKJAGD":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},"01M797WPB43MYC52MSVVPKJAGD","apt_recovery_evaluation_harness",null,"Build bounded APT recovery experiments with executable evidence, generated-skill invocation logs, source manifests, and mechanism checks.","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\u002Fall-in-one\u002Fskill\u002Fautomatic_posterior_transformation\u002Fapt_recovery_evaluation_harness\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: apt_recovery_evaluation_harness\ndescription: Build bounded APT recovery experiments with executable evidence, generated-skill invocation logs, source manifests, and mechanism checks.\n---\n\n# APT Recovery Evaluation Harness\n\nUse this skill when a Distiller recovery run needs to test whether generated APT skills can recover the paper's mechanism without reading the original implementation repository. The harness is especially useful in soft mode, where a declared reduced\u002Fproxy experiment may be accepted only after executable evidence and validation pass.\n\n## Inputs\n\n- Attempt directory with `module_plan.json`, `paper_profile.md`, and `environment\u002Fruntime_handoff.json`.\n- Generated skills root containing the APT protocol, transformation, and atomic-loss skills.\n- Recovery mode from the normalized run config.\n- Bounded command budget and source-boundary constraints.\n\n## Outputs\n\n- `recovery\u002Fexperiment_plan.md`.\n- `recovery\u002Fsource_manifest.json`.\n- `recovery\u002Flogs\u002Fexperiment_command_log.json`.\n- `recovery\u002Flogs\u002Fgenerated_skill_invocations.json`.\n- `recovery\u002Flogs\u002Fgenerated_data_item.json`.\n- `recovery\u002Flogs\u002Ftraining_trace.json`.\n- `recovery\u002Frecovery_result.json`.\n\n## Workflow\n\n1. Read the fast recovery target from the module plan.\n2. Read the runtime handoff and decide whether full neural recovery is available.\n3. If full recovery is blocked and soft mode allows proxy recovery, declare the reduced target.\n4. Invoke generated helper scripts for sequential proposal records, posterior transformation, and atomic loss.\n5. Run an executable experiment command that computes numeric metrics and mechanism checks.\n6. Write a source manifest that lists allowed sources and excludes original repositories.\n7. Run the Distiller recovery gate after the command completes.\n\n## Validation\n\nThe script `scripts\u002Fcheck_recovery_artifacts.py` performs a lightweight local check for key files and mechanism fields. The Distiller gate remains authoritative:\n\n```bash\npython scripts\u002Fcheck_recovery_artifacts.py --attempt-dir \u003Cattempt_dir>\n```\n\nThe same script also checks that `source_manifest.json` does not list forbidden sources and that it mentions `runtime_handoff.json`, which catches common source-boundary mistakes before full analysis.\n\n## Limitations\n\n- This skill does not choose ambiguous paper sources.\n- It cannot turn a proxy experiment into hard-mode success.\n- It should not silently create data from a previous attempt; every recovery run must produce its own command-generated artifacts.\n","# APT Recovery Evaluation Harness\n\nUse this skill when a Distiller recovery run needs to test whether generated APT skills can recover the paper's mechanism without reading the original implementation repository. The harness is especially useful in soft mode, where a declared reduced\u002Fproxy experiment may be accepted only after executable evidence and validation pass.\n\n## Inputs\n\n- Attempt directory with `module_plan.json`, `paper_profile.md`, and `environment\u002Fruntime_handoff.json`.\n- Generated skills root containing the APT protocol, transformation, and atomic-loss skills.\n- Recovery mode from the normalized run config.\n- Bounded command budget and source-boundary constraints.\n\n## Outputs\n\n- `recovery\u002Fexperiment_plan.md`.\n- `recovery\u002Fsource_manifest.json`.\n- `recovery\u002Flogs\u002Fexperiment_command_log.json`.\n- `recovery\u002Flogs\u002Fgenerated_skill_invocations.json`.\n- `recovery\u002Flogs\u002Fgenerated_data_item.json`.\n- `recovery\u002Flogs\u002Ftraining_trace.json`.\n- `recovery\u002Frecovery_result.json`.\n\n## Workflow\n\n1. Read the fast recovery target from the module plan.\n2. Read the runtime handoff and decide whether full neural recovery is available.\n3. If full recovery is blocked and soft mode allows proxy recovery, declare the reduced target.\n4. Invoke generated helper scripts for sequential proposal records, posterior transformation, and atomic loss.\n5. Run an executable experiment command that computes numeric metrics and mechanism checks.\n6. Write a source manifest that lists allowed sources and excludes original repositories.\n7. Run the Distiller recovery gate after the command completes.\n\n## Validation\n\nThe script `scripts\u002Fcheck_recovery_artifacts.py` performs a lightweight local check for key files and mechanism fields. The Distiller gate remains authoritative:\n\n```bash\npython scripts\u002Fcheck_recovery_artifacts.py --attempt-dir \u003Cattempt_dir>\n```\n\nThe same script also checks that `source_manifest.json` does not list forbidden sources and that it mentions `runtime_handoff.json`, which catches common source-boundary mistakes before full analysis.\n\n## Limitations\n\n- This skill does not choose ambiguous paper sources.\n- It cannot turn a proxy experiment into hard-mode success.\n- It should not silently create data from a previous attempt; every recovery run must produce its own command-generated artifacts.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fall-in-one\u002Fskill\u002Fautomatic_posterior_transformation\u002Fapt_recovery_evaluation_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 apt_recovery_evaluation_harness",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill apt_recovery_evaluation_harness",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill apt_recovery_evaluation_harness","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fall-in-one\u002Fskill\u002Fautomatic_posterior_transformation\u002Fapt_recovery_evaluation_harness\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fcheck_recovery_artifacts.py","SCRIPT","脚本",2495,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fall-in-one\u002Fskill\u002Fautomatic_posterior_transformation\u002Fapt_recovery_evaluation_harness\u002Fscripts\u002Fcheck_recovery_artifacts.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"tests\u002Ftest_check_recovery_artifacts.py",2993,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fall-in-one\u002Fskill\u002Fautomatic_posterior_transformation\u002Fapt_recovery_evaluation_harness\u002Ftests\u002Ftest_check_recovery_artifacts.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",[],[]]