[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71RVAPNM059D6BQCYZNJEER":3,"skill-same:01M71RVAPNM059D6BQCYZNJEER":60},{"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":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":43,"ownerDescription":44,"updatedAt":45,"install":46,"resources":59},"01M71RVAPNM059D6BQCYZNJEER","configure-eve-driver",null,"Use when choosing, editing, or overriding EvE driver settings for Codex, OpenCode, or interactive\u002Fdebug runs.","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\u002Fconfigure-eve-driver\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31],"eve","configure","driver","configure eve driver","codex","debug","editing","interactive","settings","use","opencode","for","when","2026-11-10 13:02:02",false,"---\nname: configure-eve-driver\ndescription: \"Use when choosing, editing, or overriding EvE driver settings for Codex, OpenCode, or interactive\u002Fdebug runs.\"\n---\n\n# Configure the EvE Driver\n\nUse the public presets first:\n\n- `driver: codex_smoke` is for fast runtime validation.\n- `driver: codex_max` is for full non-interactive runs.\n- `driver: opencode_smoke` is the equivalent fast OpenCode path.\n- `driver: opencode_max` is the equivalent full-run OpenCode path.\n\nDo not add a new preset for a one-off variation. Prefer Hydra overrides until the role is stable enough to document as a supported entrypoint.\n\n## Public Surface\n\nDriver presets live in `configs\u002Feve\u002Fdriver\u002F`. Keep that directory small:\n\n- `codex_smoke.yaml`: non-interactive Codex backend, small turn budget, web search disabled.\n- `codex_max.yaml`: non-interactive Codex backend, full-run budget, web search enabled.\n- `opencode_smoke.yaml`: non-interactive OpenCode backend with a small native step cap.\n- `opencode_max.yaml`: non-interactive OpenCode backend with a full-run native step cap.\n\nTask smoke configs live beside task configs, but keep the root config surface compact:\n\n- `circle_packing.smoke` is the single tracked circle packing smoke preset.\n- By default it validates the ordinary loop.\n- Use explicit Hydra overrides from that same entrypoint for judge evaluation or role-specific system prompt smoke paths.\n\nTask smoke configs use `driver: codex_smoke` by default; select `driver=opencode_smoke` to exercise OpenCode. Do not shrink `loop.n_workers_phase2` in the default smoke path; the two-worker default covers Phase 2 multi-worker behavior and optimizer sync. Use `loop.n_parallel_phase2` when you only need to reduce concurrent solver agents.\n\n## Normal Commands\n\nFast smoke:\n\n```bash\nuv run python -m scaling_evolve.algorithms.eve.runner --config-name=circle_packing.smoke\n```\n\nOpenCode smoke (use a native `provider\u002Fmodel` identifier):\n\n```bash\nuv run python -m scaling_evolve.algorithms.eve.runner --config-name=circle_packing.smoke driver=opencode_smoke driver.model=deepseek\u002Fdeepseek-chat\n```\n\nJudge evaluation smoke:\n\n```bash\nuv run python -m scaling_evolve.algorithms.eve.runner \\\n  --config-name=circle_packing.smoke \\\n  evaluation=circle_packing.judge \\\n  label=circle-packing-judge-smoke\n```\n\nRole-specific system prompt smoke:\n\n```bash\nuv run python -m scaling_evolve.algorithms.eve.runner \\\n  --config-name=circle_packing.smoke \\\n  evaluation=circle_packing.judge \\\n  loop.max_iterations=1 \\\n  label=circle-packing-codex-prompt-smoke \\\n  +driver.overrides.solver.system_prompt_file=configs\u002Feve\u002Foptimizer\u002Fcircle_packing\u002Fprompt\u002FCODEX_SYSTEM_PROMPT.md\n```\n\nFull run:\n\n```bash\nuv run python -m scaling_evolve.algorithms.eve.runner --config-name=circle_packing\n```\n\nOpenCode full run:\n\n```bash\nuv run python -m scaling_evolve.algorithms.eve.runner --config-name=circle_packing driver=opencode_max driver.model=deepseek\u002Fdeepseek-chat\n```\n\nOne-off interactive\u002Fdebug run:\n\n```bash\nuv run python -m scaling_evolve.algorithms.eve.runner \\\n  --config-name=circle_packing.smoke \\\n  driver.driver=codex_tmux \\\n  driver.open_iterm2=true\n```\n\nIf overriding from a full config, keep the backend switch explicit:\n\n```bash\nuv run python -m scaling_evolve.algorithms.eve.runner \\\n  --config-name=circle_packing \\\n  driver.driver=codex_tmux \\\n  driver.open_iterm2=true\n```\n\nDo not preserve interactive\u002Fdebug overrides as new YAML presets unless the team decides they are a supported public entry.\n\n## Selection Semantics\n\nThe driver config lives under the top-level `driver:` key.\n\n- `driver.driver` selects the backend and wins over `driver.provider`.\n- `driver.provider` is accepted for older configs. Avoid it for new public presets.\n- If a config inherits from `codex_max`, changing only `driver.provider` will not switch the backend because `driver.driver=codex_exec` is still set.\n- Role overrides are shallow merges: EvE starts from the base `driver` mapping, then overlays `driver.overrides.solver` or `driver.overrides.eval`.\n- Do not configure `driver.overrides.optimizer`; the independent optimizer driver role was removed.\n\nSupported backend names are `codex_exec`, `codex_tmux`, and `opencode`.\n\n## Authentication\n\n- Codex uses its native authentication by default; alternate providers may use `model_providers.*.env_key`.\n- OpenCode uses credentials saved by `opencode auth login` unless an explicit `model_providers.*.env_key` is configured.\n- Explicit environment credentials take precedence. Do not rely on undeclared ambient variables.\n\n## Driver Options\n\nCommon fields:\n\n- `driver.executable`: command name to launch; defaults to `codex` or `opencode` according to the backend.\n- `driver.model`: backend-native model identifier.\n- `driver.rollout_max_turns`: per-rollout agent turn\u002Fstep cap.\n- `driver.timeout_seconds`: per-rollout wall-clock timeout.\n- `driver.system_prompt_file`: repo-relative path to a backend system prompt file.\n- `driver.model_providers`: provider config map; if an entry declares `env_key`, EvE fails fast when that environment variable is missing.\n- `driver.token_pricing`: per-driver pricing metadata override. Prefer shared pricing in `configs\u002Fpricing.yaml` unless a run needs a local override.\n\nCodex-only fields (`codex_exec`, `codex_tmux`):\n\n- `driver.reasoning_effort`: reasoning budget where supported.\n- `driver.effort_level`: accepted as a fallback spelling for Codex-style reasoning effort.\n- `driver.web_search`: `disabled`, `cached`, or `live`.\n- `driver.budget_prompt`: whether EvE injects the budget prompt wrapper.\n- `driver.enable_multi_agent`: optional backend feature override.\n- `driver.personality`: optional backend personality override.\n- `driver.model_provider`: optional alternate provider id for Codex-style backends.\n\nOpenCode-only semantics (`opencode`):\n\n- `driver.model` must use OpenCode's native `provider\u002Fmodel` form when set; omit it to use OpenCode's configured default.\n- `driver.variant` passes the provider-specific native variant unchanged.\n- `driver.rollout_max_turns` is applied through OpenCode's native `agent.build.steps` setting.\n- `driver.budget_prompt` must be `false`; Codex hook injection is not translated.\n- Codex-only options are rejected instead of ignored or mapped.\n- HOME, XDG state, project discovery, and external skills are isolated per EvE workspace.\n- EvE-owned `AGENTS.md`, guidance skills, and helper agents are projected into the isolated\n  OpenCode configuration.\n- Only `model_providers.*.env_key` is reused; other Codex provider settings are rejected\n  instead of translated.\n- Spawn creates a native OpenCode session; resume uses its exact session ID in the same workspace. Native fork, cross-workspace migration, and snapshots are unsupported.\n\nTmux-only fields (`codex_tmux`):\n\n- `driver.approval_policy`: approval policy passed to the interactive backend.\n- `driver.sandbox_mode`: sandbox mode passed to the interactive backend.\n- `driver.allow_network`: when `sandbox_mode` is omitted, `true` maps to `danger-full-access`; otherwise the default is `workspace-write`.\n- `driver.open_iterm2`: whether EvE opens the tmux session in a visible terminal window.\n- `driver.completion_filename`: internal tmux completion marker filename.\n- `driver.instruction_filename`: internal tmux instruction filename.\n\n## Implementation References\n\nThis skill is grounded in the current runtime surfaces:\n\n- `src\u002Fscaling_evolve\u002Falgorithms\u002Feve\u002Fruntime\u002Fdriver.py` for backend selection, role overrides, tmux pool creation, sandbox\u002Fweb-search normalization, provider environment resolution, and pricing config loading.\n- `src\u002Fscaling_evolve\u002Fproviders\u002Fagent\u002Fdrivers\u002Fcodex_exec.py` for non-interactive Codex fields.\n- `src\u002Fscaling_evolve\u002Fproviders\u002Fagent\u002Fdrivers\u002Fopencode.py` for non-interactive OpenCode spawn\u002Fresume, JSONL parsing, and native step limits.\n- `src\u002Fscaling_evolve\u002Fproviders\u002Fagent\u002Fdrivers\u002Fcodex_tmux.py` for interactive Codex\u002Ftmux fields.\n- `src\u002Fscaling_evolve\u002Fproviders\u002Fagent\u002Fconfig.py` for persistent session provider config validation.\n","# Configure the EvE Driver\n\nUse the public presets first:\n\n- `driver: codex_smoke` is for fast runtime validation.\n- `driver: codex_max` is for full non-interactive runs.\n- `driver: opencode_smoke` is the equivalent fast OpenCode path.\n- `driver: opencode_max` is the equivalent full-run OpenCode path.\n\nDo not add a new preset for a one-off variation. Prefer Hydra overrides until the role is stable enough to document as a supported entrypoint.\n\n## Public Surface\n\nDriver presets live in `configs\u002Feve\u002Fdriver\u002F`. Keep that directory small:\n\n- `codex_smoke.yaml`: non-interactive Codex backend, small turn budget, web search disabled.\n- `codex_max.yaml`: non-interactive Codex backend, full-run budget, web search enabled.\n- `opencode_smoke.yaml`: non-interactive OpenCode backend with a small native step cap.\n- `opencode_max.yaml`: non-interactive OpenCode backend with a full-run native step cap.\n\nTask smoke configs live beside task configs, but keep the root config surface compact:\n\n- `circle_packing.smoke` is the single tracked circle packing smoke preset.\n- By default it validates the ordinary loop.\n- Use explicit Hydra overrides from that same entrypoint for judge evaluation or role-specific system prompt smoke paths.\n\nTask smoke configs use `driver: codex_smoke` by default; select `driver=opencode_smoke` to exercise OpenCode. Do not shrink `loop.n_workers_phase2` in the default smoke path; the two-worker default covers Phase 2 multi-worker behavior and optimizer sync. Use `loop.n_parallel_phase2` when you only need to reduce concurrent solver agents.\n\n## Normal Commands\n\nFast smoke:\n\n```bash\nuv run python -m scaling_evolve.algorithms.eve.runner --config-name=circle_packing.smoke\n```\n\nOpenCode smoke (use a native `provider\u002Fmodel` identifier):\n\n```bash\nuv run python -m scaling_evolve.algorithms.eve.runner --config-name=circle_packing.smoke driver=opencode_smoke driver.model=deepseek\u002Fdeepseek-chat\n```\n\nJudge evaluation smoke:\n\n```bash\nuv run python -m scaling_evolve.algorithms.eve.runner \\\n  --config-name=circle_packing.smoke \\\n  evaluation=circle_packing.judge \\\n  label=circle-packing-judge-smoke\n```\n\nRole-specific system prompt smoke:\n\n```bash\nuv run python -m scaling_evolve.algorithms.eve.runner \\\n  --config-name=circle_packing.smoke \\\n  evaluation=circle_packing.judge \\\n  loop.max_iterations=1 \\\n  label=circle-packing-codex-prompt-smoke \\\n  +driver.overrides.solver.system_prompt_file=configs\u002Feve\u002Foptimizer\u002Fcircle_packing\u002Fprompt\u002FCODEX_SYSTEM_PROMPT.md\n```\n\nFull run:\n\n```bash\nuv run python -m scaling_evolve.algorithms.eve.runner --config-name=circle_packing\n```\n\nOpenCode full run:\n\n```bash\nuv run python -m scaling_evolve.algorithms.eve.runner --config-name=circle_packing driver=opencode_max driver.model=deepseek\u002Fdeepseek-chat\n```\n\nOne-off interactive\u002Fdebug run:\n\n```bash\nuv run python -m scaling_evolve.algorithms.eve.runner \\\n  --config-name=circle_packing.smoke \\\n  driver.driver=codex_tmux \\\n  driver.open_iterm2=true\n```\n\nIf overriding from a full config, keep the backend switch explicit:\n\n```bash\nuv run python -m scaling_evolve.algorithms.eve.runner \\\n  --config-name=circle_packing \\\n  driver.driver=codex_tmux \\\n  driver.open_iterm2=true\n```\n\nDo not preserve interactive\u002Fdebug overrides as new YAML presets unless the team decides they are a supported public entry.\n\n## Selection Semantics\n\nThe driver config lives under the top-level `driver:` key.\n\n- `driver.driver` selects the backend and wins over `driver.provider`.\n- `driver.provider` is accepted for older configs. Avoid it for new public presets.\n- If a config inherits from `codex_max`, changing only `driver.provider` will not switch the backend because `driver.driver=codex_exec` is still set.\n- Role overrides are shallow merges: EvE starts from the base `driver` mapping, then overlays `driver.overrides.solver` or `driver.overrides.eval`.\n- Do not configure `driver.overrides.optimizer`; the independent optimizer driver role was removed.\n\nSupported backend names are `codex_exec`, `codex_tmux`, and `opencode`.\n\n## Authentication\n\n- Codex uses its native authentication by default; alternate providers may use `model_providers.*.env_key`.\n- OpenCode uses credentials saved by `opencode auth login` unless an explicit `model_providers.*.env_key` is configured.\n- Explicit environment credentials take precedence. Do not rely on undeclared ambient variables.\n\n## Driver Options\n\nCommon fields:\n\n- `driver.executable`: command name to launch; defaults to `codex` or `opencode` according to the backend.\n- `driver.model`: backend-native model identifier.\n- `driver.rollout_max_turns`: per-rollout agent turn\u002Fstep cap.\n- `driver.timeout_seconds`: per-rollout wall-clock timeout.\n- `driver.system_prompt_file`: repo-relative path to a backend system prompt file.\n- `driver.model_providers`: provider config map; if an entry declares `env_key`, EvE fails fast when that environment variable is missing.\n- `driver.token_pricing`: per-driver pricing metadata override. Prefer shared pricing in `configs\u002Fpricing.yaml` unless a run needs a local override.\n\nCodex-only fields (`codex_exec`, `codex_tmux`):\n\n- `driver.reasoning_effort`: reasoning budget where supported.\n- `driver.effort_level`: accepted as a fallback spelling for Codex-style reasoning effort.\n- `driver.web_search`: `disabled`, `cached`, or `live`.\n- `driver.budget_prompt`: whether EvE injects the budget prompt wrapper.\n- `driver.enable_multi_agent`: optional backend feature override.\n- `driver.personality`: optional backend personality override.\n- `driver.model_provider`: optional alternate provider id for Codex-style backends.\n\nOpenCode-only semantics (`opencode`):\n\n- `driver.model` must use OpenCode's native `provider\u002Fmodel` form when set; omit it to use OpenCode's configured default.\n- `driver.variant` passes the provider-specific native variant unchanged.\n- `driver.rollout_max_turns` is applied through OpenCode's native `agent.build.steps` setting.\n- `driver.budget_prompt` must be `false`; Codex hook injection is not translated.\n- Codex-only options are rejected instead of ignored or mapped.\n- HOME, XDG state, project discovery, and external skills are isolated per EvE workspace.\n- EvE-owned `AGENTS.md`, guidance skills, and helper agents are projected into the isolated\n  OpenCode configuration.\n- Only `model_providers.*.env_key` is reused; other Codex provider settings are rejected\n  instead of translated.\n- Spawn creates a native OpenCode session; resume uses its exact session ID in the same workspace. Native fork, cross-workspace migration, and snapshots are unsupported.\n\nTmux-only fields (`codex_tmux`):\n\n- `driver.approval_policy`: approval policy passed to the interactive backend.\n- `driver.sandbox_mode`: sandbox mode passed to the interactive backend.\n- `driver.allow_network`: when `sandbox_mode` is omitted, `true` maps to `danger-full-access`; otherwise the default is `workspace-write`.\n- `driver.open_iterm2`: whether EvE opens the tmux session in a visible terminal window.\n- `driver.completion_filename`: internal tmux completion marker filename.\n- `driver.instruction_filename`: internal tmux instruction filename.\n\n## Implementation References\n\nThis skill is grounded in the current runtime surfaces:\n\n- `src\u002Fscaling_evolve\u002Falgorithms\u002Feve\u002Fruntime\u002Fdriver.py` for backend selection, role overrides, tmux pool creation, sandbox\u002Fweb-search normalization, provider environment resolution, and pricing config loading.\n- `src\u002Fscaling_evolve\u002Fproviders\u002Fagent\u002Fdrivers\u002Fcodex_exec.py` for non-interactive Codex fields.\n- `src\u002Fscaling_evolve\u002Fproviders\u002Fagent\u002Fdrivers\u002Fopencode.py` for non-interactive OpenCode spawn\u002Fresume, JSONL parsing, and native step limits.\n- `src\u002Fscaling_evolve\u002Fproviders\u002Fagent\u002Fdrivers\u002Fcodex_tmux.py` for interactive Codex\u002Ftmux fields.\n- `src\u002Fscaling_evolve\u002Fproviders\u002Fagent\u002Fconfig.py` for persistent session provider config validation.\n",{"name":5,"description":7},"main","979065fd2cf1b3be9caf70596478fe27df7815ad","docs\u002Fskills\u002Fconfigure-eve-driver",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":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add scaling-group\u002Feve --skill configure-eve-driver",{"tool":52,"command":53},"bunx","bunx skills add scaling-group\u002Feve --skill configure-eve-driver",{"tool":55,"command":56},"pnpm","pnpm dlx skills add scaling-group\u002Feve --skill configure-eve-driver","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fscaling-group\u002Feve\u002Fblob\u002Fmain\u002Fdocs\u002Fskills\u002Fconfigure-eve-driver\u002FSKILL.md",true,[],[61,84,103,117,136,151],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":77,"publishedAt":32},"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",[67,72],{"categoryNo":68,"categoryName":69,"taxonomyType":70,"taxonomyTypeDesc":71},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":73,"categoryName":74,"taxonomyType":75,"taxonomyTypeDesc":76},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[78,79,80,25,81,82,28,83,31],"writing","writing skills","work","deployment","new","Existing",{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":93,"publishedAt":32},"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",[90],{"categoryNo":91,"categoryName":92,"taxonomyType":70,"taxonomyTypeDesc":71},"01JBSEEDCAT000000000000021","资料检索与研究",[94,95,28,96,97,98,99,100,101,102],"theorem search","search","literature","results","verify","find","dependencies","proof","Mathematical",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":32},"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",[],[110,111,112,113,114,115,116,31,28,19],"supervise run","supervise","run","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":32},"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",[],[112,124,125,126,127,101,128,129,116,130,131,19,28,31,132,133,97,111,134,135],"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":32},"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",[],[143,144,112,145,146,31,147,30,148,19,28,149,132,150],"circle","packing","smoke","run circle packing smoke","development","end","loop","fast",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":160,"publishedAt":32},"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",[157],{"categoryNo":158,"categoryName":159,"taxonomyType":75,"taxonomyTypeDesc":76},"01JBSEEDCAT000000000000038","人力资源",[161,112,162,25,19,28,31,163,164,114,115],"resume","resume run","id","same"]