跳到正文
TakoAPI
返回技能列表

iterative-code-evolution

由 aaronjmars 提供

Coding Agents & IDEs
550下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Systematically improve code through structured analysis-mutation-evaluation loops.

描述

该技能的功能

A structured methodology for improving code through repeated analyze-plan-mutate-verify-score-archive cycles, adapted from the ALMA research framework. Each cycle is logged in `.evolution/log.json`, so lessons from past iterations inform the next change. Designed for situations where ad-hoc fixes keep failing.

Unlike ad-hoc iteration, it enforces a maximum of 3 changes per cycle and requires every change to link to a specific observation, making it possible to attribute improvements or regressions accurately.

何时使用

  • Debugging a web scraper that fails on 40% of target pages
  • Optimizing a slow database query through multiple profiling rounds
  • Improving an LLM prompt pipeline with structured variant tracking
  • Breaking out of a debugging loop after two or more failed fix attempts
  • Evolving an agent's memory design through principled experimentation

示例工作流

输入

User asks: improve a web scraper that fails on 40% of target pages

智能体
  1. 1

    Assess each component: marks parse_html() as Broken (crashes on pages without <article>), fetch_page() as Working, extract_links() as Fragile

  2. 2

    Plan one targeted change: add fallback selectors in parse_html() for pages missing <article>

  3. 3

    Mutate the code: add cascading selector logic trying <article>, then <main>, then <body>

  4. 4

    Verify: run the scraper against the same test pages, confirm no crashes

  5. 5

    Score and archive: pass rate rises from 40% to 72%, log the change and record the learned principle

输出

Pass rate reaches 88% after a second cycle fixing relative URL resolution in extract_links(), with both cycles logged in .evolution/log.json

安装

clawhub install aaronjmars/iterative-code-evolution

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接