agentleFS
Sign inStart free
StormixStormix/transcripts-mcp/.agents/skills/simplify/SKILL.md

simplify

Skill8 starsChanged 2 months agoMITView on GitHub

Simplify scoped code with parallel read-only review subagents, then apply targeted cleanup fixes without a large refactor.

119 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use codex-system, design-tracker and 9 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.
  • gaebalaiSkill

    codex-system

    PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. Codex is a trusted expert you should ALWAYS consult BEFORE making decisions on: design choices, implementation approaches, debugging strategies, refactoring plans, or any non-trivial problem. When uncertain, consult Codex. Don't hesitate - Codex provides better analysis. Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".

    Also in 3 projects that use this

  • gaebalaiSkill

    design-tracker

    PROACTIVELY track and document project design decisions without being asked. Activate automatically when detecting architecture discussions, implementation decisions, pattern choices, library selections, or any technical decisions. Also use when user explicitly says "記録して", "設計どうなってる", "record this". Do NOT wait for user to ask - record important decisions immediately.

    Also in 3 projects that use this

  • mike22890Skill

    clonedeps

    将项目依赖的第三方库源码克隆到本地，便于深入阅读和调试。当需要查看库的实现细节、阅读源码、调试第三方依赖、理解 SDK/framework 内部机制、查看 node_modules 之外的原始代码、分析开源库架构、学习他人代码、查看依赖的 TypeScript 类型定义时使用。

    Also in 3 projects that use this

  • mdrubelamin2Skill

    verification-planning

    Plans how to prove a change works or broke nothing: frames the claim, designs an evidence path from the system itself, and requires every check to be able to fail.

    Also in 3 projects that use this

  • devbrother2024Skill

    artifact-design

    단독 self-contained HTML 산출물(랜딩 페이지, 정적 문서·리포트, 독립 대시보드, 데모·게임, 개발 전 UX/UI 대안 비교 목업)을 만들 때 팔레트·타이포그래피·레이아웃을 의도적으로 설계하고 템플릿·AI스러운 디자인을 피하도록 돕는 디자인 가이드. HTML/CSS를 쓰기 전에 로드한다. "랜딩 만들어줘", "이 내용 단일 HTML로 예쁘게", "UX 대안 HTML로 비교해줘", "디자인 잡아줘"처럼 단독 HTML 아티팩트를 만들거나 비교하는 요청에 활성화하고, 기존 앱(React·Vue 등)의 인앱 컴포넌트 수정이나 순수 백엔드·로직 작업에는 쓰지 않는다.

    Also in 3 projects that use this

  • codebycoreySkill

    batch

    Create multiple proposals from free-form feature descriptions. Use when planning several features at once, batch creating proposals, or setting up related changes.

    Also in 4 projects that use this

  • +3 more from gaebalai

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 111 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run three parallel read-only reviewers on a scoped diff, aggregate their findings, then make targeted cleanup edits yourself.

    line 8
  2. Very specific:

    After /simplify or when asked to simplify code, reduce complexity, or clean up a diff.

    line 14
  3. Distinctive:

    Before review when a change works but feels heavier than it needs to be.

    line 15
  4. Distinctive:

    When you want parallel review passes (quality, performance, reuse) without handing edits to subagents.

    line 16
  5. Distinctive:

    If no local diff: files or symbols mentioned in the conversation.

    line 22
  6. Distinctive:

    Do not broaden scope beyond the selected work unless needed to understand local patterns.

    line 24
  7. Distinctive:

    Run lightweight checks on touched files when practical.

    line 40

“Common” is measured: kept by at least 6 in 10 of the 111 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Simplify

Run three parallel read-only reviewers on a scoped diff, aggregate their findings, then make targeted cleanup edits yourself. The goal is less complexity and better reuse — not a rewrite.

Project skill: .agents/skills/simplify/SKILL.md

When to use

  • After /simplify or when asked to simplify code, reduce complexity, or clean up a diff.
  • Before review when a change works but feels heavier than it needs to be.
  • When you want parallel review passes (quality, performance, reuse) without handing edits to subagents.

Scope selection

  1. Explicit paths, symbols, diff, or area the user named.
  2. Otherwise: combined git diff + git diff --cached.
  3. If no local diff: files or symbols mentioned in the conversation.
  4. Last resort: git show HEAD.
  5. Do not broaden scope beyond the selected work unless needed to understand local patterns.

Subagents (read-only, parallel)

Launch all three with the same model as the parent. They report only — no edits, formatters, worktrees, or commits.

Code quality — low-information comments, one-off helpers, nullable proliferation, catch-all try/catch, premature abstraction, weak type escapes, duplicated or derived state, dead compatibility code.

Performance — blocking hot-path work, uncached expensive ops, busy waits, string concat in loops, N+1 I/O, chatty logging in tight loops.

Reuse — existing helpers or patterns elsewhere in the codebase or already in the diff.

Fixing

  • Aggregate findings and fix what clearly reduces complexity or improves reuse.
  • Skip issues that need more user context or a refactor much larger than the original diff; note those in the summary.
  • Run lightweight checks on touched files when practical.

Output should feel like

  • A short summary: what was fixed, what was skipped but recommended.
  • Behavior preserved unless a clear bug was fixed.
  • Edits stay inside the selected scope.

Related

  • [[deslop]] — strip AI-generated slop from a branch diff.
  • [[thermo-nuclear-code-quality-review]] — deeper structural review when simplification isn't enough.
  • [[improve-codebase-architecture]] — longer-horizon architecture opportunities.
  • [[skills-index]] — vault catalog.

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.

Check your setup, free