[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M798A59BNTVHT74YY9KTDHCR":3,"skill-same:01M798A59BNTVHT74YY9KTDHCR":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},"01M798A59BNTVHT74YY9KTDHCR","sf_transfer_recovery",null,"Run a bounded successor-features plus GPI transfer recovery experiment for changing linear-reward RL tasks.","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\u002Ffre\u002Fskill\u002Fsuccessor_features_transfer\u002Fsf_transfer_recovery\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sf_transfer_recovery\ndescription: Run a bounded successor-features plus GPI transfer recovery experiment for changing linear-reward RL tasks.\n---\n\n# Successor-Feature Transfer Recovery Harness\n\nUse this skill to validate a reduced, mechanism-faithful recovery of Successor Features for Transfer in Reinforcement Learning. It should be used after successor-feature and GPI utilities exist and before claiming the paper mechanism has been recovered.\n\n## Inputs\n\n- Attempt directory containing `module_plan.json` and `environment\u002Fruntime_handoff.json`.\n- Generated skill root containing `successor_feature_model` and `generalized_policy_improvement`.\n- Soft-mode permission for a reduced\u002Fproxy experiment when full four-room or MuJoCo recovery is not feasible.\n\n## Outputs\n\n- `recovery\u002Frecovery_result.json` with `mean_transfer_advantage`.\n- `recovery\u002Flogs\u002Fgenerated_data_item.json` describing the gridworld and reward weights.\n- `recovery\u002Flogs\u002Fgenerated_skill_invocations.json` proving generated modules were imported\u002Fcalled.\n- `recovery\u002Flogs\u002Ftraining_trace.json` recording exact dynamic-programming\u002Fsource-policy construction traces.\n\n## Workflow\n\n1. Construct a small deterministic shared-dynamics gridworld with feature-bearing terminal goals.\n2. Define source reward weights and held-out transfer weights.\n3. Derive source policies using exact value iteration for each source reward.\n4. Compute successor features for each source policy using the generated successor-feature module.\n5. Reweight source successor features for each held-out reward and apply generated GPI selection.\n6. Evaluate GPI and a restricted single-source baseline on each held-out reward.\n7. Save numeric returns, mechanism checks, and validation-ready artifacts.\n\n## Validation\n\nRun:\n\n```bash\npython scripts\u002Frun_sf_transfer_recovery.py --attempt-dir \u003Cattempt_dir> --skills-root \u003Cgenerated_skills_root>\npython tests\u002Ftest_recovery_harness.py\n```\n\n## Limitations\n\nThis is a reduced\u002Fproxy recovery. It does not reproduce the paper's four-room continuous-navigation or MuJoCo experiments, but it preserves the core mechanism of shared dynamics, changing linear rewards, successor-feature reweighting, and GPI transfer.\n","# Successor-Feature Transfer Recovery Harness\n\nUse this skill to validate a reduced, mechanism-faithful recovery of Successor Features for Transfer in Reinforcement Learning. It should be used after successor-feature and GPI utilities exist and before claiming the paper mechanism has been recovered.\n\n## Inputs\n\n- Attempt directory containing `module_plan.json` and `environment\u002Fruntime_handoff.json`.\n- Generated skill root containing `successor_feature_model` and `generalized_policy_improvement`.\n- Soft-mode permission for a reduced\u002Fproxy experiment when full four-room or MuJoCo recovery is not feasible.\n\n## Outputs\n\n- `recovery\u002Frecovery_result.json` with `mean_transfer_advantage`.\n- `recovery\u002Flogs\u002Fgenerated_data_item.json` describing the gridworld and reward weights.\n- `recovery\u002Flogs\u002Fgenerated_skill_invocations.json` proving generated modules were imported\u002Fcalled.\n- `recovery\u002Flogs\u002Ftraining_trace.json` recording exact dynamic-programming\u002Fsource-policy construction traces.\n\n## Workflow\n\n1. Construct a small deterministic shared-dynamics gridworld with feature-bearing terminal goals.\n2. Define source reward weights and held-out transfer weights.\n3. Derive source policies using exact value iteration for each source reward.\n4. Compute successor features for each source policy using the generated successor-feature module.\n5. Reweight source successor features for each held-out reward and apply generated GPI selection.\n6. Evaluate GPI and a restricted single-source baseline on each held-out reward.\n7. Save numeric returns, mechanism checks, and validation-ready artifacts.\n\n## Validation\n\nRun:\n\n```bash\npython scripts\u002Frun_sf_transfer_recovery.py --attempt-dir \u003Cattempt_dir> --skills-root \u003Cgenerated_skills_root>\npython tests\u002Ftest_recovery_harness.py\n```\n\n## Limitations\n\nThis is a reduced\u002Fproxy recovery. It does not reproduce the paper's four-room continuous-navigation or MuJoCo experiments, but it preserves the core mechanism of shared dynamics, changing linear rewards, successor-feature reweighting, and GPI transfer.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Ffre\u002Fskill\u002Fsuccessor_features_transfer\u002Fsf_transfer_recovery",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 sf_transfer_recovery",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill sf_transfer_recovery",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill sf_transfer_recovery","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Ffre\u002Fskill\u002Fsuccessor_features_transfer\u002Fsf_transfer_recovery\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Frun_sf_transfer_recovery.py","SCRIPT","脚本",8858,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Ffre\u002Fskill\u002Fsuccessor_features_transfer\u002Fsf_transfer_recovery\u002Fscripts\u002Frun_sf_transfer_recovery.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"tests\u002Ftest_recovery_harness.py",1256,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Ffre\u002Fskill\u002Fsuccessor_features_transfer\u002Fsf_transfer_recovery\u002Ftests\u002Ftest_recovery_harness.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",[],[]]