[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7980BPC26MWAYD1RBK7Z80S":3,"skill-same:01M7980BPC26MWAYD1RBK7Z80S":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},"01M7980BPC26MWAYD1RBK7Z80S","particle_mirror_descent_mixture_protocol",null,"Use this skill to construct the synthetic tied Gaussian mixture posterior target from the Particle Mirror Descent paper, including data generation, log prior\u002Flikelihood functions, and grid posterior evaluation.","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\u002Fbam\u002Fskill\u002Fparticle_mirror_descent\u002Fparticle_mirror_descent_mixture_protocol\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: particle_mirror_descent_mixture_protocol\ndescription: Use this skill to construct the synthetic tied Gaussian mixture posterior target from the Particle Mirror Descent paper, including data generation, log prior\u002Flikelihood functions, and grid posterior evaluation.\n---\n\n# Synthetic Mixture Model Protocol\n\n## When To Use\n\nUse this skill when a recovery or experiment needs the paper's synthetic multimodal Bayesian target. Do not use it to run PMD updates or score a completed density estimate.\n\n## Inputs\n\n- Random seed and observation count.\n- Optional model constants: `theta_true=(1,-2)`, `sigma1=1`, `sigma2=1`, `sigma_x=2.5`, `mix_prob=0.5`.\n- Optional grid bounds for posterior evaluation.\n\n## Outputs\n\n- Generated observations and provenance metadata.\n- Stable `log_prior`, `log_likelihood`, and dataset log posterior functions.\n- Normalized target posterior density on a two-dimensional grid.\n- Expected symmetric mode locations.\n\n## Workflow\n\n1. Generate observations from the tied two-component Gaussian mixture described in Section 6.\n2. Evaluate likelihoods with log-sum-exp to avoid underflow.\n3. Combine independent Gaussian priors and the full-data likelihood into an unnormalized posterior.\n4. Normalize grid posterior arrays before downstream metric computation.\n5. Save generated data provenance when used in recovery.\n\n## Validation\n\nRun:\n\n```bash\npython tests\u002Ftest_mixture_protocol.py\n```\n\n## Limitations\n\nThis skill provides a reduced synthetic protocol, not the paper's full repeated 1000-sample comparison against all baselines.\n","# Synthetic Mixture Model Protocol\n\n## When To Use\n\nUse this skill when a recovery or experiment needs the paper's synthetic multimodal Bayesian target. Do not use it to run PMD updates or score a completed density estimate.\n\n## Inputs\n\n- Random seed and observation count.\n- Optional model constants: `theta_true=(1,-2)`, `sigma1=1`, `sigma2=1`, `sigma_x=2.5`, `mix_prob=0.5`.\n- Optional grid bounds for posterior evaluation.\n\n## Outputs\n\n- Generated observations and provenance metadata.\n- Stable `log_prior`, `log_likelihood`, and dataset log posterior functions.\n- Normalized target posterior density on a two-dimensional grid.\n- Expected symmetric mode locations.\n\n## Workflow\n\n1. Generate observations from the tied two-component Gaussian mixture described in Section 6.\n2. Evaluate likelihoods with log-sum-exp to avoid underflow.\n3. Combine independent Gaussian priors and the full-data likelihood into an unnormalized posterior.\n4. Normalize grid posterior arrays before downstream metric computation.\n5. Save generated data provenance when used in recovery.\n\n## Validation\n\nRun:\n\n```bash\npython tests\u002Ftest_mixture_protocol.py\n```\n\n## Limitations\n\nThis skill provides a reduced synthetic protocol, not the paper's full repeated 1000-sample comparison against all baselines.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbam\u002Fskill\u002Fparticle_mirror_descent\u002Fparticle_mirror_descent_mixture_protocol",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 particle_mirror_descent_mixture_protocol",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill particle_mirror_descent_mixture_protocol",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill particle_mirror_descent_mixture_protocol","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbam\u002Fskill\u002Fparticle_mirror_descent\u002Fparticle_mirror_descent_mixture_protocol\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fmixture_protocol.py","SCRIPT","脚本",3688,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbam\u002Fskill\u002Fparticle_mirror_descent\u002Fparticle_mirror_descent_mixture_protocol\u002Fscripts\u002Fmixture_protocol.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"tests\u002Ftest_mixture_protocol.py",816,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbam\u002Fskill\u002Fparticle_mirror_descent\u002Fparticle_mirror_descent_mixture_protocol\u002Ftests\u002Ftest_mixture_protocol.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",[],[]]