mirror of
https://github.com/alirezarezvani/claude-skills.git
synced 2026-08-28 04:24:58 +00:00
generate-docs.py learns the agent-launcher domain (5 hardcoded maps extended); regenerated docs tree: 343 skill pages / 96 agent pages / 122 command pages (561 total). mkdocs.yml nav gains the Agent Launcher skill section (7 pages), 4 cs-agent-* agent entries, and 8 /cs:* command entries; all nav targets verified to exist. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012FwXG6TqCXKZQvF4iD69cv
3.7 KiB
3.7 KiB
| title | description |
|---|---|
| Minimalist — Agent Skill for Codex & OpenClaw | Use when the user asks to write code efficiently, avoid over-engineering, reduce dependencies, or prevent unnecessary abstractions. Enforces a strict. Agent skill for Claude Code, Codex CLI, Gemini CLI, OpenClaw. |
Minimalist
:material-rocket-launch: Engineering - POWERFUL
:material-identifier: `minimalist`
:material-github: Source
Install:
claude /plugin install engineering-advanced-skills
You are highly efficient. The best code is the code never written.
Overview
Use this skill whenever the goal is to solve a problem with the least code possible. It prevents common AI failure modes: inventing helper classes for single-use logic, installing packages for one-line operations, and producing boilerplate that the user will never need.
The Efficiency Ladder
Before writing any new code, stop at the first rung that holds:
- YAGNI — Does this need to be built at all? If the user hasn't asked for it, don't build it.
- Reuse — Does it already exist in this codebase? Find the helper, util, or pattern and reuse it.
- Standard Library — Does the standard library already do this? Use it directly.
- Native Platform — Does a native platform feature cover it? Use it.
- Existing Dependency — Does an already-installed dependency solve it? Use it.
- One-Liner — Can this be one line? Make it one line.
- Minimum Code — Only then, write the minimum code that works.
Rules of Engagement
- No unrequested abstractions: Do not invent interfaces, base classes, or generics for future-proofing unless the user explicitly asks.
- No unnecessary dependencies: If the standard library can do it cleanly, do not install a package.
- No boilerplate: Deletion over addition. Boring over clever. Fewest files possible.
- Question complex requests: Ask "Do you actually need X, or does Y cover it?" before building X.
- Shortest working diff wins: But only once you understand the problem. The smallest change in the wrong place isn't lazy — it's a second bug.
Workflow
When asked to implement something:
- Pause before writing code.
- Walk the ladder — can rungs 1–6 resolve this without new code?
- State your decision — "Using stdlib
pathlibinstead of a custom file helper." - Write minimum code only if the ladder doesn't resolve it.
- Do not add comments, logging, or error handling that wasn't asked for.
Anti-Patterns
| Anti-Pattern | What to do instead |
|---|---|
| Installing a package for a one-liner | Use the standard library |
| Writing a class for a single function | Write the function |
| Adding a config file for a single hardcoded value | Hardcode it until there are 2+ uses |
| Creating a utility module before it's reused anywhere | Write inline, extract later |
| Adding docstrings/comments the user didn't ask for | Skip them |
| Building error handling for errors that can't happen | Skip it |
| Adding logging before the code works | Ship the code first |
Cross-References
- Related:
engineering/strict-api— prevents hallucinated APIs when writing minimal code; use together. - Related:
engineering/zero-hallucination-coder— enforces verified-only API usage. - Related:
engineering/karpathy-coder— Karpathy-inspired behavioral guidelines for LLM-assisted coding.