[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71RVQK0X8XYENJS6TZHDHCF":3,"skill-same:01M71RVQK0X8XYENJS6TZHDHCF":56},{"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":28,"linkOnly":29,"markdownContent":30,"markdownBody":31,"frontMatter":32,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M71RVQK0X8XYENJS6TZHDHCF","inspect-population",null,"Use when reading what an Eve run evolved — its best solvers\u002Foptimizers, their code, and how the population improved","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\u002Finspect-population\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27],"inspect","inspect population","eve","use","when","code","how","run","reading","2026-11-10 13:02:02",false,"---\nname: inspect-population\ndescription: \"Use when reading what an Eve run evolved — its best solvers\u002Foptimizers, their code, and how the population improved\"\n---\n\n# Inspect a run's population\n\nRead what a run actually evolved: the best candidates, their code, and how scores progressed. Source of truth is the run's lineage DBs + artifacts (local; no wandb needed). run_root layout is in `docs\u002Fusing-eve.md`.\n\n## The candidates\n\nEach run has `\u003Crun_root>\u002Fsolver_lineage.db` and `\u003Crun_root>\u002Foptimizer_lineage.db`. The eve populations live in the `eve_population_entries` table, one row per candidate:\n\n```bash\nsqlite3 \u003Crun_root>\u002Fsolver_lineage.db \\\n  \"SELECT entry_id, created_at FROM eve_population_entries ORDER BY created_at;\"\n```\n\nSwap in `optimizer_lineage.db` for optimizers. (Note: the DB also has generic `nodes` \u002F `edges` tables, but the eve loop does not populate them, do not query those.)\n\n## Scores (rank best-first)\n\nScores are not stored inline in the DB; each entry references a flat score artifact (`{status, score, summary}`) at `artifacts\u002F\u003Crun-id>_solver\u002Fstate\u002F\u003C...>__\u003Centry_id>_score.yaml`. Rank candidates best-first:\n\n```bash\nfor f in \u003Crun_root>\u002Fartifacts\u002F*_solver\u002Fstate\u002F*_score.yaml; do\n  s=$(awk -F': ' '\u002F^score:\u002F{print $2; exit}' \"$f\")\n  printf '%s\\t%s\\n' \"$s\" \"$(basename \"$f\")\"\ndone | sort -rn | head\n```\n\nThe filename carries the `\u003Centry_id>`; top line = best so far. (The same flat score is also at each candidate's `\u003Cworkspace>\u002Flogs\u002Fevaluate\u002Fscore.yaml`. Do **not** parse the workspace-*root* `score.yaml`, that one is a different, nested phase-2 record, not the flat score.)\n\nSmoke runs typically show `score: 0.0` with a `status: error` summary; that is the known circle_packing smoke payload error, not a skill problem.\n\n## Read a candidate's evolved code\n\nThe agent's written solution is under that candidate's workspace: `\u003Crun_root>\u002Fsolver_workspaces\u002F\u003C...>\u002Fsolver\u002F`. The archived copy is also stored inline as JSON in the entry's `files_ref_json` artifact under `\u003Crun_root>\u002Fartifacts\u002F\u003Crun-id>_solver\u002Fstate\u002F`.\n\n## Improvement over the run\n\nWorkspace directories are named `..._step_\u003Cn>_...`; compare the best `score.yaml` per step to see the trajectory. The optimizer log trees under `\u003Crun_root>\u002Fartifacts\u002F\u003Crun-id>_optimizer\u002F` show how the guidance evolved.\n\n## Notes\n\n- Completed-iteration count: `grep -c \"Phase 3: updated Elo\" \u003Crun_root>\u002Frunner.log`.\n- To understand *why* a candidate behaved a certain way (not just its score\u002Fcode), read its agent session: `..\u002Fdebug-agent-session\u002FSKILL.md`.\n","# Inspect a run's population\n\nRead what a run actually evolved: the best candidates, their code, and how scores progressed. Source of truth is the run's lineage DBs + artifacts (local; no wandb needed). run_root layout is in `docs\u002Fusing-eve.md`.\n\n## The candidates\n\nEach run has `\u003Crun_root>\u002Fsolver_lineage.db` and `\u003Crun_root>\u002Foptimizer_lineage.db`. The eve populations live in the `eve_population_entries` table, one row per candidate:\n\n```bash\nsqlite3 \u003Crun_root>\u002Fsolver_lineage.db \\\n  \"SELECT entry_id, created_at FROM eve_population_entries ORDER BY created_at;\"\n```\n\nSwap in `optimizer_lineage.db` for optimizers. (Note: the DB also has generic `nodes` \u002F `edges` tables, but the eve loop does not populate them, do not query those.)\n\n## Scores (rank best-first)\n\nScores are not stored inline in the DB; each entry references a flat score artifact (`{status, score, summary}`) at `artifacts\u002F\u003Crun-id>_solver\u002Fstate\u002F\u003C...>__\u003Centry_id>_score.yaml`. Rank candidates best-first:\n\n```bash\nfor f in \u003Crun_root>\u002Fartifacts\u002F*_solver\u002Fstate\u002F*_score.yaml; do\n  s=$(awk -F': ' '\u002F^score:\u002F{print $2; exit}' \"$f\")\n  printf '%s\\t%s\\n' \"$s\" \"$(basename \"$f\")\"\ndone | sort -rn | head\n```\n\nThe filename carries the `\u003Centry_id>`; top line = best so far. (The same flat score is also at each candidate's `\u003Cworkspace>\u002Flogs\u002Fevaluate\u002Fscore.yaml`. Do **not** parse the workspace-*root* `score.yaml`, that one is a different, nested phase-2 record, not the flat score.)\n\nSmoke runs typically show `score: 0.0` with a `status: error` summary; that is the known circle_packing smoke payload error, not a skill problem.\n\n## Read a candidate's evolved code\n\nThe agent's written solution is under that candidate's workspace: `\u003Crun_root>\u002Fsolver_workspaces\u002F\u003C...>\u002Fsolver\u002F`. The archived copy is also stored inline as JSON in the entry's `files_ref_json` artifact under `\u003Crun_root>\u002Fartifacts\u002F\u003Crun-id>_solver\u002Fstate\u002F`.\n\n## Improvement over the run\n\nWorkspace directories are named `..._step_\u003Cn>_...`; compare the best `score.yaml` per step to see the trajectory. The optimizer log trees under `\u003Crun_root>\u002Fartifacts\u002F\u003Crun-id>_optimizer\u002F` show how the guidance evolved.\n\n## Notes\n\n- Completed-iteration count: `grep -c \"Phase 3: updated Elo\" \u003Crun_root>\u002Frunner.log`.\n- To understand *why* a candidate behaved a certain way (not just its score\u002Fcode), read its agent session: `..\u002Fdebug-agent-session\u002FSKILL.md`.\n",{"name":5,"description":7},"main","979065fd2cf1b3be9caf70596478fe27df7815ad","docs\u002Fskills\u002Finspect-population",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":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add scaling-group\u002Feve --skill inspect-population",{"tool":48,"command":49},"bunx","bunx skills add scaling-group\u002Feve --skill inspect-population",{"tool":51,"command":52},"pnpm","pnpm dlx skills add scaling-group\u002Feve --skill inspect-population","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fscaling-group\u002Feve\u002Fblob\u002Fmain\u002Fdocs\u002Fskills\u002Finspect-population\u002FSKILL.md",true,[],[57,81,100,113,132,148],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":73,"publishedAt":28},"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",[63,68],{"categoryNo":64,"categoryName":65,"taxonomyType":66,"taxonomyTypeDesc":67},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":69,"categoryName":70,"taxonomyType":71,"taxonomyTypeDesc":72},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[74,75,76,77,78,79,22,80,23],"writing","writing skills","work","editing","deployment","new","Existing",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":90,"publishedAt":28},"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",[87],{"categoryNo":88,"categoryName":89,"taxonomyType":66,"taxonomyTypeDesc":67},"01JBSEEDCAT000000000000021","资料检索与研究",[91,92,22,93,94,95,96,97,98,99],"theorem search","search","literature","results","verify","find","dependencies","proof","Mathematical",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":28},"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",[],[107,108,26,109,110,111,112,23,22,21],"supervise run","supervise","monitoring","experiment","it","running",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":28},"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",[],[26,120,121,122,123,98,124,125,112,126,127,21,22,23,128,129,94,108,130,131],"math","run math proof quickstart","quickstart","math proof","copy","launch","problem","local","task","create","report","Evaluation",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":28},"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",[],[139,140,26,141,142,23,143,144,145,21,22,146,128,147],"circle","packing","smoke","run circle packing smoke","development","for","end","loop","fast",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":157,"publishedAt":28},"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",[154],{"categoryNo":155,"categoryName":156,"taxonomyType":71,"taxonomyTypeDesc":72},"01JBSEEDCAT000000000000038","人力资源",[158,26,159,77,21,22,23,160,161,110,111],"resume","resume run","id","same"]