[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71RVNJ6KP9P79CNJWVMZY28":3,"skill-same:01M71RVNJ6KP9P79CNJWVMZY28":61},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":44,"ownerDescription":45,"updatedAt":46,"install":47,"resources":60},"01M71RVNJ6KP9P79CNJWVMZY28","import-run",null,"Use when starting a new Eve run seeded from one or more prior runs, e.g. keep the good solvers but try a fresh optimizer","scaling-group\u002Feve","scaling-group","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F181708022?v=4","01M71RTM8RQW6CX3M1934895JA","Scientific Computing and Intelligence Group","01M71RTM99S28ZTFK9BK17R4GC",66,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fscaling-group\u002Feve\u002Fblob\u002Fmain\u002Fdocs\u002Fskills\u002Fimport-run\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32],"import","import run","run","good","eve","more","new","use","when","keep","one","optimizer","fresh","but","2026-11-10 13:02:02",false,"---\nname: import-run\ndescription: \"Use when starting a new Eve run seeded from one or more prior runs, e.g. keep the good solvers but try a fresh optimizer\"\n---\n\n# Import into a new run\n\n`import` starts a **new** run (new run id) whose initial population is seeded from one or more prior runs. Use it to keep what worked and change what didn't. To continue the same run instead, see `..\u002Fresume-run\u002FSKILL.md`.\n\nThe classic case: the optimizer evolved poorly but some solvers are good. Keep the solvers, start a fresh optimizer.\n\n## Command\n\n```bash\nuv run python -m scaling_evolve.algorithms.eve.runner --config-name=\u003Cconfig> \\\n  'import_from={path: \u003Cold_run_root>, import_solvers: true, import_optimizers: false}' \\\n  +optimizer.seed_initial_on_import=true\n```\n\n- `import_solvers` \u002F `import_optimizers` select, per side, which populations carry over (both default `true`); they live inside the per-source mapping.\n- **Gotcha (do not skip):** with `import_optimizers: false`, the optimizer population starts **empty** unless you also pass `+optimizer.seed_initial_on_import=true`, which seeds the new run's `initial_guidance\u002F`. Omit it and the run has no optimizer. The `+` is required (this key is not pre-declared in the config).\n- To change the optimizer for the new run, edit `initial_guidance\u002F` before launching. Unlike resume, import **does** seed it.\n\n## Multiple sources\n\n`import_from` accepts a list; sources import in order, additively:\n\n```bash\n'import_from=[{path: \u003Crun_a>, import_solvers: true, import_optimizers: false}, {path: \u003Crun_b>, import_solvers: true, import_optimizers: false}]'\n```\n\n- Each source DB must contain exactly one run id (a guard; a normal single run satisfies it).\n- Gotcha: if two sources contain entries with the same id, the later one silently overwrites the earlier. Only compose sources you know are disjoint.\n\n## After launch\n\nIt is a normal new run: supervise with `..\u002Fsupervise-run\u002FSKILL.md`, inspect with `..\u002Finspect-population\u002FSKILL.md`.\n\n## Note\n\n- `import_from` and `resume_from` are mutually exclusive.\n","# Import into a new run\n\n`import` starts a **new** run (new run id) whose initial population is seeded from one or more prior runs. Use it to keep what worked and change what didn't. To continue the same run instead, see `..\u002Fresume-run\u002FSKILL.md`.\n\nThe classic case: the optimizer evolved poorly but some solvers are good. Keep the solvers, start a fresh optimizer.\n\n## Command\n\n```bash\nuv run python -m scaling_evolve.algorithms.eve.runner --config-name=\u003Cconfig> \\\n  'import_from={path: \u003Cold_run_root>, import_solvers: true, import_optimizers: false}' \\\n  +optimizer.seed_initial_on_import=true\n```\n\n- `import_solvers` \u002F `import_optimizers` select, per side, which populations carry over (both default `true`); they live inside the per-source mapping.\n- **Gotcha (do not skip):** with `import_optimizers: false`, the optimizer population starts **empty** unless you also pass `+optimizer.seed_initial_on_import=true`, which seeds the new run's `initial_guidance\u002F`. Omit it and the run has no optimizer. The `+` is required (this key is not pre-declared in the config).\n- To change the optimizer for the new run, edit `initial_guidance\u002F` before launching. Unlike resume, import **does** seed it.\n\n## Multiple sources\n\n`import_from` accepts a list; sources import in order, additively:\n\n```bash\n'import_from=[{path: \u003Crun_a>, import_solvers: true, import_optimizers: false}, {path: \u003Crun_b>, import_solvers: true, import_optimizers: false}]'\n```\n\n- Each source DB must contain exactly one run id (a guard; a normal single run satisfies it).\n- Gotcha: if two sources contain entries with the same id, the later one silently overwrites the earlier. Only compose sources you know are disjoint.\n\n## After launch\n\nIt is a normal new run: supervise with `..\u002Fsupervise-run\u002FSKILL.md`, inspect with `..\u002Finspect-population\u002FSKILL.md`.\n\n## Note\n\n- `import_from` and `resume_from` are mutually exclusive.\n",{"name":5,"description":7},"main","979065fd2cf1b3be9caf70596478fe27df7815ad","docs\u002Fskills\u002Fimport-run",9,"https:\u002F\u002Fgithub.com\u002Fscaling-group\u002Feve","https:\u002F\u002Fgithub.com\u002Fscaling-group","https:\u002F\u002Fscaling-group.github.io\u002F","Department of Mathematics, National University of Singapore","2026-08-20 15:35:50",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add scaling-group\u002Feve --skill import-run",{"tool":53,"command":54},"bunx","bunx skills add scaling-group\u002Feve --skill import-run",{"tool":56,"command":57},"pnpm","pnpm dlx skills add scaling-group\u002Feve --skill import-run","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fscaling-group\u002Feve\u002Fblob\u002Fmain\u002Fdocs\u002Fskills\u002Fimport-run\u002FSKILL.md",true,[],[62,85,104,117,136,152],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":78,"publishedAt":33},"01M71RW4VG8A6FFRGT7H41J16J","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fscaling-group\u002Feve\u002Fblob\u002Fmain\u002Fdocs\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[68,73],{"categoryNo":69,"categoryName":70,"taxonomyType":71,"taxonomyTypeDesc":72},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[79,80,81,82,83,25,26,84,27],"writing","writing skills","work","editing","deployment","Existing",{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":94,"publishedAt":33},"01M71RW2PFRVWH24AP25T6AV4E","theorem-search","Use TheoremSearch to find, verify, and cite mathematical theorem statements, named results, proof routes, and literature dependencies.","https:\u002F\u002Fgithub.com\u002Fscaling-group\u002Feve\u002Fblob\u002Fmain\u002Fdocs\u002Fskills\u002Ftheorem-search\u002FSKILL.md",[91],{"categoryNo":92,"categoryName":93,"taxonomyType":71,"taxonomyTypeDesc":72},"01JBSEEDCAT000000000000021","资料检索与研究",[95,96,26,97,98,99,100,101,102,103],"theorem search","search","literature","results","verify","find","dependencies","proof","Mathematical",{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":33},"01M71RW0N0GQR9GW1B3HKBB800","supervise-run","Use when monitoring a running Eve experiment and recovering from problems while it runs","https:\u002F\u002Fgithub.com\u002Fscaling-group\u002Feve\u002Fblob\u002Fmain\u002Fdocs\u002Fskills\u002Fsupervise-run\u002FSKILL.md",[],[111,112,21,113,114,115,116,27,26,23],"supervise run","supervise","monitoring","experiment","it","running",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":33},"01M71RVYA101VVX3CKR2HZHBT3","run-math-proof-quickstart","Use when running a Math Proof quickstart from a user-provided problem: create a local task copy, launch a real EvE attempt, supervise it, and report proof\u002Fevaluation results.","https:\u002F\u002Fgithub.com\u002Fscaling-group\u002Feve\u002Fblob\u002Fmain\u002Fdocs\u002Fskills\u002Frun-math-proof-quickstart\u002FSKILL.md",[],[21,124,125,126,127,102,128,129,116,130,131,23,26,27,132,133,98,112,134,135],"math","run math proof quickstart","quickstart","math proof","copy","launch","problem","local","task","create","report","Evaluation",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":33},"01M71RVWYKH6TF0WB6X57GMWJ2","run-circle-packing-smoke","Use when a fast end-to-end smoke run is needed for the Eve loop development, will run on circle packing task.","https:\u002F\u002Fgithub.com\u002Fscaling-group\u002Feve\u002Fblob\u002Fmain\u002Fdocs\u002Fskills\u002Frun-circle-packing-smoke\u002FSKILL.md",[],[143,144,21,145,146,27,147,148,149,23,26,150,132,151],"circle","packing","smoke","run circle packing smoke","development","for","end","loop","fast",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":161,"publishedAt":33},"01M71RVVCE1NEF4ZM405WX815Z","resume-run","Use when continuing an interrupted or paused Eve run from where it stopped (same run, same id), optionally after editing the experiment","https:\u002F\u002Fgithub.com\u002Fscaling-group\u002Feve\u002Fblob\u002Fmain\u002Fdocs\u002Fskills\u002Fresume-run\u002FSKILL.md",[158],{"categoryNo":159,"categoryName":160,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000038","人力资源",[162,21,163,82,23,26,27,164,165,114,115],"resume","resume run","id","same"]