autonomous-dev

autonomous-dev is an Execution & autonomous loops skill for AI agents, published by bkywksj in the knowledge-base repository on GitHub. Skillspace rates autonomous-dev D (59/100) and it passed the safety scan; the rating is based on static analysis only.

自主连续开发方法论（Codex 版）。把一个项目按「每轮一个最小可提交单元」的方式推进到完成： 每轮读真相源 → 选下一个未做项 → 做一个最小单元 → 过验证门 → 记录勾选 → 最小提交 → 报进度。 适用于"按需求/台账建功能、还原原型、修一批 bug、补测试、重构、迁移、清理"等需要反复同构推进的任务。 与 Claude Code 的关系：Claude Code 有内置 `/loop` 自动续期（`/loop /dev-loop`），Codex 没有—— 所以 Codex 端由你（或脚本 / cron）反复触发"继续下一轮"，方法论本身一致。 触发场景： - 想让 Codex 把某个项目/某个意图"一轮轮推进到完成" - 还原原型图、修一批 warning、补单测、重构模块等同构重复任务 - 需要"每步可编译、可回退、可恢复"的稳健推进方式 触发词：自主开发、连续开发、循环开发、一轮一提交、还原原型、批量修复、autonomous dev、continuous dev

Grade
D
Quality
59 / 100
Safety
Passed
GitHub stars
292

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubbkywksj/knowledge-base

Our review

Architecture
84 / 100
Maturity
Basic: a single SKILL.md
Security scan
No issues found
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Execution & autonomous loops

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.