agentleFS
kopp0510kopp0510/claude-dd/skills/code-simplifier/SKILL.md

code-simplifier

Skill12 starsChanged 13 days agoMITView on GitHub

調用官方 code-simplifier agent 簡化程式碼。當使用者要求簡化、降低複雜度、清理冗餘,或執行 8 步開發迴圈步驟 3 時啟用。不適用於 PR 審查(用 code-reviewer)。

59 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use tdd-rust, type-design-analyzer and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • FlorianBruniauxSkill

    tdd-rust

    Also in 3 projects that use this

  • PaulKinlanSkill

    type-design-analyzer

    Analyzes type design quality focusing on encapsulation, invariant expression, usefulness, and enforcement. Provides quantitative ratings (1-10) for each dimension.

    Also in 3 projects that use this

  • PaulKinlanSkill

    comment-analyzer

    Analyzes code comments for accuracy, completeness, and long-term maintainability. Identifies misleading comments, comment rot, and documentation gaps.

    Also in 4 projects that use this

  • ufodev-ioSkill

    security-guardian

    Comprehensive security layer for all interactions with Claude: audits code, dependencies, commands, configs, and AI-generated output for vulnerabilities. Protects against prompt injection, data leaks, unsafe advice, and social engineering. Works in Cursor, Claude Code, claude.ai, and API contexts. Use always as a background security protocol in any Claude-powered environment.

    Also in 3 projects that use this

  • SentrySkill

    find-bugs

    Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.

    Also in 3 projects that use this

  • tossSkill

    pr-triage

    Classify and summarize a PR for efficient review

    Also in 3 projects that use this

  • +1 more from PaulKinlan

The file

Files
SKILL.md

Code Simplifier — 官方 agent 包裝器

本 skill 只負責介面層:定範圍 → 調用官方 code-simplifier agent → 呈現結果。 簡化邏輯全在 agent 內,不在此重複。

範圍決定

  • 8 步開發迴圈步驟 3(最常見):範圍 = 該功能段落從起點到現在的變更(git diff <起點>, 起點 = ~/.claude/scripts/check-claude-md.sh --segment-base 的輸出),不詢問,直接執行。 一段常有好幾個 commit,HEAD~1 只看得到最後一個;取不到起點(指令 exit 非 0 或輸出是空的)時當成「範圍不明」問一題,不要退回 HEAD~1。 專案有 task-planner 進度表時例外:起點改用表上這段 commits 欄的起點。 表在哪不用問 —— 根目錄 CLAUDE.md 第一個 ## 之前的指路句會寫明檔名(通常在 docs/designs/); 沒有那句指路就是沒有進度表,照 --segment-base 走。回頭做 BLOCKED 過的段落時, 中間插做別段會把 --segment-base 往後推,用它會漏掉這段先前已寫好的部分
  • 使用者指明檔案/目錄/片段:照指示,不追問
  • 範圍不明:問一題 —「要簡化哪個範圍?(預設:最近修改的檔案)」,其餘參數用預設

預設不含測試檔;使用者要求才包含。

Agent 調用

依序嘗試 subagent_type:

  1. code-simplifier:code-simplifier(plugin 命名空間)
  2. code-simplifier(本地 ~/.claude/agents/code-simplifier.md)

兩者皆回 Agent type not found → 停下,請使用者跑 ./install-dd-pipeline.sh 補齊。

Prompt 模板:

請簡化以下程式碼,提高可讀性與可維護性,保留所有功能:

範圍:{檔案清單或片段}

重點:降低圈複雜度、改善命名、移除冗餘、簡化條件(early return、減少巢狀)。
約束:不改公開 API 簽名;有測試必須全過。
輸出:簡化摘要 + 關鍵變更的 Before/After 對比。

結果呈現

轉述 agent 的簡化摘要與 Before/After 對比。統計數字只引用 agent 實際回報的, 沒有就不列 — 禁止自行估算複雜度指標。

簡化後提醒(在 8 步迴圈中則直接續行步驟 4):用 git diff 審查變更,重跑測試確認行為不變。

範圍外

  • 架構層重構(模組拆分、設計模式)、效能調校 — 超出簡化範疇,明說不做
  • 第三方 / 生成的程式碼 — 不修改
  • 效能關鍵段落 — 「看似複雜但高效」的寫法保留,標註說明即可

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.