Skills for Real Engineers. Straight from my .agents directory.
chisle-audit
Agent skill fromJayPokale/Chisle
One-shot efficiency audit of a file, diff, or whole repo across BOTH axes at once: over-engineered code (reinvented stdlib, needless abstractions, speculative config) AND bloated prose (verbose comments, padded docstrings, redundant doc sections). Neither a pure code-minimizer nor a pure prose compressor does both in one pass. That's the point. Ranked report, biggest saving first; changes nothing. Use when the user says "chisle audit", "/chisle-audit", "audit this for bloat", "what can I cut", "review this PR for over-engineering and verbosity".
How to install chisle-audit
npx skills add JayPokale/Chisle# or add only this skill to Claude Code: copy the folder
skills/chisle-audit/
# into
~/.claude/skills/chisle-audit/ (all projects)
.claude/skills/chisle-audit/ (one project)
1# Chisle Audit23Scan the target (a diff, a file, or the repo tree) and report what to cut, on4both axes. One-shot. Read-only: never edit, never write a flag, never apply fixes.56## Scope78- No argument → audit the current `git diff` (staged + unstaged). Empty diff → audit `HEAD~1..HEAD`.9- A path → audit that file or directory.10- "repo" / "whole repo" → walk the tree (skip vendored/generated/`node_modules`/`dist`/lockfiles).1112## What to flag1314**Code (the YAGNI axis):**15- Reinvented stdlib (hand-rolled debounce, deep-clone, groupBy, retry loop, date math)16- Abstraction with one implementation (interface/factory/wrapper for a single case)17- New dependency for what a few lines or an installed dep already covers18- Config/option/flag that never varies19- Speculative "for later" scaffolding with no current caller20- Verbose code where a native platform feature (CSS, DB constraint, `<input type>`) does it2122**Prose (the compression axis), the half a code-only auditor misses:**23- Comments that restate the code (`i += 1 // increment i`)24- Docstrings/READMEs padded with filler, hedging, ceremony, or duplicated content25- Multi-paragraph explanations where one tight sentence carries the meaning26- Decorative tables/emoji/headings that add tokens, not information27- Dead prose: TODO graveyards, stale "see also" links, obsolete sections2829## What NOT to flag3031Input validation at trust boundaries, error handling that prevents data loss,32…
Excerpt shown under the repository's MIT license.
More skills in Chisle
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
