一键导入
evolution-loop
Run a bounded repository improvement loop using explicit fitness criteria, small reversible mutations, validation evidence, and human approval gates.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Run a bounded repository improvement loop using explicit fitness criteria, small reversible mutations, validation evidence, and human approval gates.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Create or improve AGENTS.md files so agents know the active product surface, architecture boundaries, validation commands, debug workflows, observability surfaces, isolation rules, and maintenance rules.
Discover and document a repository's run, health, logs, traces, screenshots, network capture, state reset, and artifact bundle surfaces for agent debugging.
Audit a repository for FullSelfDriving readiness: AGENTS.md quality, debug entry points, progressive discovery, observability, isolation, determinism, validation, safety, and evolutionary improvement readiness.
| name | evolution-loop |
| description | Run a bounded repository improvement loop using explicit fitness criteria, small reversible mutations, validation evidence, and human approval gates. |
Use this skill when the user wants FullSelfDriving to improve a repository, not just audit it.
Common criteria: