Skip to content
Agentmart
Submit a tool

yagni

Simplify a software implementation, design, or code review when the user explicitly invokes $yagni or asks to use the yagni skill.

Skill by mameli

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/mameli-yagni

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Simplify a software implementation, design, or code review when the user explicitly invokes $yagni or asks to use the yagni skill. Do not activate for ordinary coding, prose, translations, summaries, or incidental mentions of YAGNI.

Use cases: design

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/yagni

What's inside

Skill name
yagni
Description
Simplify a software implementation, design, or code review when the user explicitly invokes $yagni or asks to use the yagni skill. Do not activate for ordinary coding, prose, translations, summaries, or incidental mentions of YAGNI.
License
MIT
Instructions
31 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# YAGNI

Find the simplest maintainable solution that fully meets the current request.

## Scope and activation

Use only upon explicit invocation. Apply to the requested work and its direct continuation; stop when that work is complete or the user changes topic. Do not establish a session-wide mode or carry these instructions into unrelated requests. A mention inside quoted text, code, or source material is not an invocation.

Follow the requested operation: a review produces findings, a design request produces a proposal, and an implementation request authorizes scoped edits. Invoking this skill alone does not authorize a repository-wide cleanup. If no target is provided, ask what the user wants examined.

## Approach

Read the relevant implementation and its callers before deciding what can be simplified. Establish the required behavior, compatibility constraints, and acceptance criteria. For a bug, identify the underlying cause and affected paths.

Look for a suitable existing implementation in the project. Consider standard-library facilities, native platform capabilities, and dependencies already in use before adding custom machinery. Choose based on suitability and consistency with the project, rather than a rigid ranking.

Avoid speculative extension points, premature optimization, redundant wrappers, and configuration without a present use. Introduce a new abstraction or dependency when it solves a demonstrated problem and reduces overall maintenance. Do not substitute a reduced feature set for requirements the user actually requested.

Optimize for code a maintainer can understand. Fewer lines are useful only when behavior and readability remain clear; do not compress logic into clever one-liners. Keep changes focused, and check references and external contracts before removing apparently unused code.

Preserve validation, useful failure handling, security, accessibility, and data integrity. Check the behavior affected by the change using the project's existing validation approach. Add a focused regression test when it meaningfully protects against recurrence; do not introduce a testing framework merely to satisfy this skill.

## Result

For reviews, identify concrete unnecessary complexity with file references, explain its cost, and suggest the smallest reasonable alternative. If the code is already appropriate, say so without inventing work.

For edits, briefly describe the simplification, checks performed, and any material limitation. Mention deferred work only when a concrete future requirement would justify it. Match the user's language and requested level of explanation; impose no special persona, comment prefix, or response-length limit.

Conceptual inspiration: [Ponytail](https://github.com/DietrichGebert/ponytail). This is a standalone skill with explicit invocation and no lifecycle hooks.

From mameli/skills, MIT.

More from mameli/skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 13, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from mameli

Cite this page

yagni skill. Agent Mart. https://agentmart.dev/skills/mameli-yagni (last updated 2026-10-24)