Simplify
Skill8 starsChanged 7 months agoApache-2.0View on GitHub
Bounded simplification pass for a file or hunk that preserves behavior while reducing complexity.
119 other projects use a version of this.
Adopted by
Most recently taken up by
- thistleknot/skillstheir own version, first seen Nov 8, 2026
- PeanutGT/NutsSkillstheir own version, first seen Nov 8, 2026
- Ovich/charrettetheir own version, first seen Nov 8, 2026
- caidanw/skillstheir own version, first seen Nov 8, 2026
- Ovich/swarmstormtheir own version, first seen Nov 8, 2026
- alexandrosandre/agentic-engineeringtheir own version, first seen Nov 8, 2026
Used with
Projects with it also use codex-system, design-tracker 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.
gaebalaiSkillcodex-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
gaebalaiSkilldesign-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
mike22890Skillclonedeps
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
mdrubelamin2Skillverification-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
devbrother2024Skillartifact-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
codebycoreySkillbatch
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
Other versions119 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 119
- Z3Prover/z3★ 13ksame name
- aaddrick/claude-desktop-debian★ 5.5ksame name
- CherryHQ/cherry-studio-app★ 4.1ksame name
- elliothux/open-compute★ 3.3ksame name
- meta-pytorch/OpenEnv★ 2.8ksame name
- huggingface/OpenEnv★ 2.8ksame name
- bholmesdev/hubble.md★ 1.5ksame name
- kdlbs/kandev★ 1.1ksame name
- truffle-ai/dexto★ 659same name
- deadlock-mod-manager/deadlock-mod-manager★ 584same name
109 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository38 other files it gives its agents.
- Brave SearchSkill
- BrowserSkill
- CloudflareSkill
- DNS ToolsSkill
- Docker APISkill
- Endpoint CheckSkill
- Fetch URLSkill
- GitHubSkill
- Google OAuthSkill
- GoogleSkill
- GoPlacesSkill
- LoopSkill
- Microsoft Edge TTSSkill
- 1PasswordSkill
- OpenAI WhisperSkill
- OpenStreetMapSkill
- PDF ExtractSkill
- ProxmoxSkill
- RememberSkill
- RSS / AtomSkill
- RTSP SnapshotSkill
- Session LogsSkill
- SkillifySkill
- SpotifySkill
- SSH ExecSkill
- StuckSkill
- SummarizeSkill
- TaskFlowSkill
- Tesseract OCRSkill
- tmuxSkill
- TranslateSkill
- Update ConfigSkill
- VerifySkill
- Video FramesSkill
- WeatherSkill
- WikipediaSkill
- Wolfram AlphaSkill
- yt-dlpSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 9 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 111 edited versions we read keep these.
9
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 37
If structured args are provided, use them directly.
- Very specific: line 46
If target is still missing, ask for one concrete file or hunk.
- Distinctive: line 51
Read the target and identify purpose, invariants, and public interfaces.
- Distinctive: line 54
remove dead code / unreachable branches
- Very specific: line 60
If preserve_behavior=true, avoid interface/semantic changes.
- Distinctive: line 61
If a behavior change seems necessary, stop and ask for confirmation.
- Very specific: line 63
Run targeted checks (lint/test/build scope relevant to changed files).
- Very specific: line 65
no further meaningful simplification remains (status=already_simple), or
- Distinctive: line 72
Never run unbounded refactor loops.
- Distinctive: line 73
Do not introduce speculative abstractions with no local payoff.
- Distinctive: line 74
Do not touch unrelated files "while here".
- Distinctive: line 75
Prefer small, reviewable edits over sweeping rewrites.
- Distinctive: line 76
Keep comments only for non-obvious WHY.
“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.
Files
Simplify
Simplify code in a bounded, evidence-driven way: smaller, clearer, and easier to maintain while preserving behavior unless the user explicitly asks otherwise.
Use when
- User asks for refactor/cleanup without adding new features.
- A file or hunk looks noisy (duplication, dead code, redundant guards).
- You need clearer names and tighter structure with minimal risk.
Do not use when
- User is requesting new behavior or a product-level redesign.
- You do not have a concrete target file/hunk.
- The change would require broad API/contract breakage without approval.
Input contract
target(required): file path or hunk identifier to simplify.scope(optional):fileorhunk(defaultfile).max_passes(optional): default2, clamp to[1, 4].preserve_behavior(optional): defaulttrue.focus(optional): subset ofreuse,dead_code,redundant_guards,naming,duplication,efficiency.
Parsing rules (priority order)
- If structured args are provided, use them directly.
- Else infer from user language:
- "this file", explicit path, or pasted diff ->
target - "just this block/hunk" ->
scope=hunk - "two passes/max 3 rounds" ->
max_passes - "don't change behavior" ->
preserve_behavior=true - keywords like "remove dead code", "rename", "dedupe" ->
focus
- "this file", explicit path, or pasted diff ->
- Defaults:
scope=file,max_passes=2,preserve_behavior=true
- If
targetis still missing, ask for one concrete file or hunk.
Canonical workflow
- Understand baseline
- Read the target and identify purpose, invariants, and public interfaces.
- Run bounded simplify passes (
1..max_passes)- Apply only high-signal improvements:
- remove dead code / unreachable branches
- collapse redundant guards and repeated conditionals
- deduplicate copy-paste logic into local helpers where appropriate
- improve naming for intent clarity
- replace ad-hoc logic with existing utilities when available
- Apply only high-signal improvements:
- Behavior safety check
- If
preserve_behavior=true, avoid interface/semantic changes. - If a behavior change seems necessary, stop and ask for confirmation.
- If
- Verification
- Run targeted checks (lint/test/build scope relevant to changed files).
- Stop when:
- no further meaningful simplification remains (
status=already_simple), or - simplification applied safely (
status=simplified), or - blocked by missing context/approval (
status=needs_user_input), or - pass budget reached (
status=max_passes_reached).
- no further meaningful simplification remains (
Guardrails
- Never run unbounded refactor loops.
- Do not introduce speculative abstractions with no local payoff.
- Do not touch unrelated files "while here".
- Prefer small, reviewable edits over sweeping rewrites.
- Keep comments only for non-obvious WHY; remove narrative noise.
Output format
Always return:
status:simplified|already_simple|needs_user_input|max_passes_reachedpasses_run: number of simplify passes executedtarget: normalized file/hunk targetfocus_used: normalized focus dimensionschanges: concise bullet list of concrete simplificationsbehavior_safety: why behavior is preserved (or what approval is needed)verification: checks run + outcomesnext_action: required unlessstatus=simplifiedoralready_simple
Examples
target="crates/core/src/agent/mod.rs" max_passes=2 focus="dead_code,redundant_guards"target="src/main.rs#L120" scope="hunk" preserve_behavior=truetarget="diff:latest" focus="reuse,duplication,naming" max_passes=3
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
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.

