[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794N9QTQ1DMK81TP866JPC6":3,"skill-same:01M794N9QTQ1DMK81TP866JPC6":64},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M794N9QTQ1DMK81TP866JPC6","scientific-agent-skills",null,"Maintains the Scientific Agent Skills repository: adding or updating Agent Skills, validating SKILL.md frontmatter and repo tests, planning isolated skill suites, running or triaging security scans, and keeping catalog\u002Frelease evidence aligned. Use for K-Dense-AI\u002Fscientific-agent-skills checkout tasks, skills-ref validate, tests\u002F_meta, tests\u002Frun_all.py, scan_pr_skills.py, scan_skills.py, metadata.version, allowed-tools, openclaw\u002Fhermes metadata, docs\u002Fskills.md, and scanner findings.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fscientific-agent-skills\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: scientific-agent-skills\ndescription: \"Maintains the Scientific Agent Skills repository: adding or\n  updating Agent Skills, validating SKILL.md frontmatter and repo tests,\n  planning isolated skill suites, running or triaging security scans, and\n  keeping catalog\u002Frelease evidence aligned. Use for\n  K-Dense-AI\u002Fscientific-agent-skills checkout tasks, skills-ref validate,\n  tests\u002F_meta, tests\u002Frun_all.py, scan_pr_skills.py, scan_skills.py,\n  metadata.version, allowed-tools, openclaw\u002Fhermes metadata, docs\u002Fskills.md, and\n  scanner findings.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Scientific Agent Skills Repository Maintenance\n\nUse this repo skill when the user is editing, reviewing, validating, testing, or preparing a pull request for the `K-Dense-AI\u002Fscientific-agent-skills` repository. It is a maintainer skill for the skill collection itself; it is not the route for using RDKit, Scanpy, Paperclip, or any other scientific workflow skill.\n\n## First decision\n\n| User intent | Read |\n|---|---|\n| Add a new skill, update an existing skill, fix frontmatter\u002Fmetadata, decide whether content belongs in `references\u002F`, `scripts\u002F`, or `assets\u002F`, or update catalog\u002Fdiagram artifacts | `sub-skills\u002Fskill-authoring\u002FSKILL.md` |\n| Choose validation commands, run `skills-ref`, diagnose `tests\u002F_meta`, add `tests\u002F\u003Cskill>\u002F`, edit `tests\u002Fskill-requirements.toml`, or use `tests\u002Frun_all.py --isolated` | `sub-skills\u002Fvalidation-testing\u002FSKILL.md` |\n| Run changed-skill or weekly security scans, handle missing `SKILL_SCANNER_LLM_API_KEY`, interpret scanner findings, or update `docs\u002Fsecurity-triage.md` | `sub-skills\u002Fsecurity-scanning\u002FSKILL.md` |\n| Check repository layout, source snapshot, selected evidence, or staleness before refreshing this generated repo skill | `references\u002Frepo-overview.md`, `references\u002Frepo-provenance.md` |\n| Diagnose cross-cutting repo failures or confusing policies before touching files | `references\u002Ftroubleshooting.md` |\n\n## Repository setup defaults\n\n1. Work from the repository root of a target checkout.\n2. Prefer the repository's `uv` workflow for Python 3.13 tooling:\n\n   ```bash\n   uv sync --python 3.13\n   ```\n\n3. Do not install every scientific dependency into the project environment. Individual skills have mutually incompatible package pins; use `tests\u002Frun_all.py --isolated \u003Cskill>` for skill-specific suites.\n4. Treat generated scan reports, diagrams, caches, and local environments as outputs, not source evidence.\n5. Before a PR, run the smallest checks that cover the changed skill and then escalate to repo-wide checks when shared contracts, runner logic, or many skills changed.\n\n## Common route patterns\n\n- **New skill with scripts**: start in `skill-authoring`, then use `validation-testing` to add a suite and isolated requirements entry, then use `security-scanning` to plan the PR scan.\n- **Existing skill update**: read the current skill first, bump `metadata.version`, test only changed examples\u002Fscripts, and run focused validation before broad checks.\n- **CI failure**: identify whether it came from skill spec validation, repo-specific metadata rules, `tests\u002F_meta`, a per-skill suite, or the security scanner; then enter the matching sub-skill.\n- **Scanner finding**: never fix from the finding text alone. Inspect the cited files, verify whether they exist, compare behavior to the skill's documented service, and check the triage reference for known false-positive classes.\n\n## Safety and scope boundaries\n\n- Do not make medical, scientific, or regulatory claims by editing a skill without evidence from the package\u002Fservice docs and tests that skill targets.\n- Do not put tests, fixtures, scratch data, or generated reports inside a runtime `skills\u002F\u003Cname>\u002F` package.\n- Do not add secrets, private URLs, unpublished data, local paths, or environment names to skill files.\n- Do not run networked security scans, upload reports, create releases, or mutate tags unless the user explicitly authorizes that side effect.\n- Avoid using this skill when the task is ordinary scientific analysis with an installed package; route to the package-specific scientific skill instead.\n\n## Provenance and refresh\n\nRead `references\u002Frepo-provenance.md` before relying on this generated repo skill for a checkout at a different commit, branch, version, or dirty state. If the repository policy files, CI workflows, test contract, scanner scripts, or catalog layout have changed, refresh this repo skill before using it for high-stakes maintenance.\n","# Scientific Agent Skills Repository Maintenance\n\nUse this repo skill when the user is editing, reviewing, validating, testing, or preparing a pull request for the `K-Dense-AI\u002Fscientific-agent-skills` repository. It is a maintainer skill for the skill collection itself; it is not the route for using RDKit, Scanpy, Paperclip, or any other scientific workflow skill.\n\n## First decision\n\n| User intent | Read |\n|---|---|\n| Add a new skill, update an existing skill, fix frontmatter\u002Fmetadata, decide whether content belongs in `references\u002F`, `scripts\u002F`, or `assets\u002F`, or update catalog\u002Fdiagram artifacts | `sub-skills\u002Fskill-authoring\u002FSKILL.md` |\n| Choose validation commands, run `skills-ref`, diagnose `tests\u002F_meta`, add `tests\u002F\u003Cskill>\u002F`, edit `tests\u002Fskill-requirements.toml`, or use `tests\u002Frun_all.py --isolated` | `sub-skills\u002Fvalidation-testing\u002FSKILL.md` |\n| Run changed-skill or weekly security scans, handle missing `SKILL_SCANNER_LLM_API_KEY`, interpret scanner findings, or update `docs\u002Fsecurity-triage.md` | `sub-skills\u002Fsecurity-scanning\u002FSKILL.md` |\n| Check repository layout, source snapshot, selected evidence, or staleness before refreshing this generated repo skill | `references\u002Frepo-overview.md`, `references\u002Frepo-provenance.md` |\n| Diagnose cross-cutting repo failures or confusing policies before touching files | `references\u002Ftroubleshooting.md` |\n\n## Repository setup defaults\n\n1. Work from the repository root of a target checkout.\n2. Prefer the repository's `uv` workflow for Python 3.13 tooling:\n\n   ```bash\n   uv sync --python 3.13\n   ```\n\n3. Do not install every scientific dependency into the project environment. Individual skills have mutually incompatible package pins; use `tests\u002Frun_all.py --isolated \u003Cskill>` for skill-specific suites.\n4. Treat generated scan reports, diagrams, caches, and local environments as outputs, not source evidence.\n5. Before a PR, run the smallest checks that cover the changed skill and then escalate to repo-wide checks when shared contracts, runner logic, or many skills changed.\n\n## Common route patterns\n\n- **New skill with scripts**: start in `skill-authoring`, then use `validation-testing` to add a suite and isolated requirements entry, then use `security-scanning` to plan the PR scan.\n- **Existing skill update**: read the current skill first, bump `metadata.version`, test only changed examples\u002Fscripts, and run focused validation before broad checks.\n- **CI failure**: identify whether it came from skill spec validation, repo-specific metadata rules, `tests\u002F_meta`, a per-skill suite, or the security scanner; then enter the matching sub-skill.\n- **Scanner finding**: never fix from the finding text alone. Inspect the cited files, verify whether they exist, compare behavior to the skill's documented service, and check the triage reference for known false-positive classes.\n\n## Safety and scope boundaries\n\n- Do not make medical, scientific, or regulatory claims by editing a skill without evidence from the package\u002Fservice docs and tests that skill targets.\n- Do not put tests, fixtures, scratch data, or generated reports inside a runtime `skills\u002F\u003Cname>\u002F` package.\n- Do not add secrets, private URLs, unpublished data, local paths, or environment names to skill files.\n- Do not run networked security scans, upload reports, create releases, or mutate tags unless the user explicitly authorizes that side effect.\n- Avoid using this skill when the task is ordinary scientific analysis with an installed package; route to the package-specific scientific skill instead.\n\n## Provenance and refresh\n\nRead `references\u002Frepo-provenance.md` before relying on this generated repo skill for a checkout at a different commit, branch, version, or dirty state. If the repository policy files, CI workflows, test contract, scanner scripts, or catalog layout have changed, refresh this repo skill before using it for high-stakes maintenance.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fscientific-agent-skills",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill scientific-agent-skills",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill scientific-agent-skills",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill scientific-agent-skills","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fscientific-agent-skills\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Frepo-overview.md","REFERENCE","参考文档",3630,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fscientific-agent-skills\u002Freferences\u002Frepo-overview.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",2521,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fscientific-agent-skills\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",542,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fscientific-agent-skills\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",3243,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fscientific-agent-skills\u002Freferences\u002Ftroubleshooting.md",[65,73,80,87,94,101],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":69,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"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.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":69,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":69,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":69,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":69,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":69,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"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",[],[]]