Agent skill

Chisle Audit

by JayPokale in JayPokale/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…

MITAuto-check passedDevelopment

Install Chisle Audit

skills CLI
$ npx skills add JayPokale/Chisle --skill chisle-audit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install JayPokale/Chisle chisle-audit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/JayPokale/Chisle.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/chisle-audit .claude/skills/chisle-audit && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
chisle-audit
GitHub stars
636
Token cost
~687 tokens
SKILL.md length
261 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

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…

  • The user says chisle audit
  • SKILL.md covers Scope, What to flag, What NOT to flag and Output
  • Calls git
  • Audit this for bloat

What it does

Chisle Audit is an agent skill from JayPokale/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…

Its SKILL.md is about 690 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Accessibility, Technical documentation and Code simplification. The repository describes itself as: Cut your AI coding agent's token bill on three axes: terse prose, YAGNI-first code, and tool-output compression. Claude Code, Pi, Cursor, Codex, Gemini + 4 more. Zero deps… The licence is MIT.

When your agent uses it

  • The user says chisle audit
  • Audit this for bloat
  • Review this PR for over-engineering and verbosity

Example prompts

  • “chisle audit”
  • “/chisle-audit”
  • “audit this for bloat”
  • “/chisle-audit”

What it can do on your machine

Read from SKILL.md and the folder at commit 52c954b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Chisle Audit loads about 687 tokens when it runs. Until then it costs about 141 tokens; SKILL.md has 261 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~141
When it runs · the whole SKILL.md, loaded when a task matches
~687

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from JayPokale/Chisle at commit 52c954b, republished under its MIT licence (© JayPokale). 261 words, ~687 tokens.

Download SKILL.mdSave it as .claude/skills/chisle-audit/SKILL.md (or your agent's skills folder).
name
chisle-audit
description
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".

Chisle Audit

Scan the target (a diff, a file, or the repo tree) and report what to cut, on both axes. One-shot. Read-only: never edit, never write a flag, never apply fixes.

Scope

  • No argument → audit the current git diff (staged + unstaged). Empty diff → audit HEAD~1..HEAD.
  • A path → audit that file or directory.
  • "repo" / "whole repo" → walk the tree (skip vendored/generated/node_modules/dist/lockfiles).

What to flag

Code (the YAGNI axis):

  • Reinvented stdlib (hand-rolled debounce, deep-clone, groupBy, retry loop, date math)
  • Abstraction with one implementation (interface/factory/wrapper for a single case)
  • New dependency for what a few lines or an installed dep already covers
  • Config/option/flag that never varies
  • Speculative "for later" scaffolding with no current caller
  • Verbose code where a native platform feature (CSS, DB constraint, <input type>) does it

Prose (the compression axis), the half a code-only auditor misses:

  • Comments that restate the code (i += 1 // increment i)
  • Docstrings/READMEs padded with filler, hedging, ceremony, or duplicated content
  • Multi-paragraph explanations where one tight sentence carries the meaning
  • Decorative tables/emoji/headings that add tokens, not information
  • Dead prose: TODO graveyards, stale "see also" links, obsolete sections

What NOT to flag

Input validation at trust boundaries, error handling that prevents data loss, security, accessibility, deliberate // chisle: / // ponytail: shortcuts already documented, or domain comments that explain why (not what).

Output

One ranked list, biggest cut first. One finding per line. No preamble, no praise.

path:line  [code|prose]  <what's bloated> → <the lean replacement>. (~N lines/tokens)

End with a two-line summary:

N findings: X code, Y prose. Est. removable: ~A lines code, ~B lines prose.
Biggest win: <the single highest-impact cut>.

Be honest about uncertainty: mark a finding (check) if cutting it might lose behavior you can't verify from the snippet. Lean toward fewer, high-confidence findings over a long speculative list.

© JayPokale, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/chisle-audit of JayPokale/Chisle.

Open the folder on GitHubat commit 52c954b

Compare with similar skills

Chisle Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Chisle Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Chisle Audit this skillJayPokale/Chisle636—~687Automated safety check: PassMIT
Scientific DocumentationYikai-Liao/symusic189—~5.5kAutomated safety check: PassMIT
Find Slopletehaha/moneymatter160—~3kAutomated safety check: PassAGPL-3.0
Frontend Code Reviewlanggenius/dify158k—~938Automated safety check: PassCustom licence
Moonbit Docs Maintainermoonbitlang/moonbit-docs2.5k—~1.1kAutomated safety check: PassCustom licence
Orchardcore Docs WriterOrchardCMS/OrchardCore8.2k—~1.1kAutomated safety check: PassBSD-3-Clause

Similar skills

  • Scientific Documentation

    Yikai-Liao/symusic

    Set up and maintain documentation for scientific Python packages.

    189 GitHub stars~5.5k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Find Slop

    letehaha/moneymatter

    Hunt "AI slop" in this codebase — duplication, reinvented wheels, over-engineering, defensive cruft, dead code, comment slop, performance antipatterns.

    160 GitHub stars~3k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Frontend Code Review

    langgenius/dify

    Reviews frontend changes under `web/` or `packages/dify-ui/` for concrete defects and broken project contracts, using routed rule packs and a severity scale for findings.

    158k GitHub stars~938 tokensUpdated today
    DevelopmentAuto-check passed
  • Moonbit Docs Maintainer

    moonbitlang/moonbit-docs

    A skill your agent uses when maintaining the moonbitlang/moonbit-docs repository, including Sphinx docs under next/, MoonBit examples under next/sources/, error-code documentation, gettext…

    2.5k GitHub stars~1.1k tokensUpdated 18 days ago
    DevelopmentAuto-check passed
  • Orchardcore Docs Writer

    OrchardCMS/OrchardCore

    Authors OrchardCore documentation — MkDocs Material pages, module README docs, nav entries, admonitions, tabbed content, and redirects.

    8.2k GitHub stars~1.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Domodomo New Tool Workflow

    darknecrocities/DomoDomo---All-in-one-Tool

    Mandatory end-to-end procedure for adding or materially changing a DomoDomo tool or category.

    239 GitHub stars~1.3k tokensUpdated 3 days ago
    DevelopmentAuto-check passed

More from JayPokale/Chisle

  • Chisle Review

    JayPokale/Chisle

    Review a diff or file through the Chisle lens: flag over-engineering, speculative abstractions, reinvented stdlib, and verbose code that a lazier approach would shrink.

    636 GitHub stars~362 tokensUpdated 3 days ago
    Auto-check passed
  • Chisle

    JayPokale/Chisle

    Maximum-efficiency dev mode: terse zero-fluff prose + YAGNI/ladder-first code.

    636 GitHub stars~906 tokensUpdated 3 days ago
    Auto-check passed
  • Chisle Help

    JayPokale/Chisle

    Quick-reference card for Chisle commands. An agent skill from JayPokale/Chisle.

    636 GitHub stars~273 tokensUpdated 3 days ago
    Auto-check passed

Questions about Chisle Audit

What does Chisle Audit do?

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…. Chisle Audit is an agent skill from JayPokale/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).

When should I use Chisle Audit?

Chisle Audit fits situations like: the user says chisle audit; audit this for bloat; review this PR for over-engineering and verbosity.

How do I install Chisle Audit in Claude Code?

Run `npx skills add JayPokale/Chisle --skill chisle-audit -a claude-code`. Or copy the skill folder (skills/chisle-audit in JayPokale/Chisle) into .claude/skills/chisle-audit in your project. Claude Code loads it when a task matches its description.

How do I install Chisle Audit in Codex?

Run `npx skills add JayPokale/Chisle --skill chisle-audit -a codex`. Or copy the skill folder (skills/chisle-audit in JayPokale/Chisle) into .agents/skills/chisle-audit in your project. Codex loads it when a task matches its description.

Can I use Chisle Audit in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JayPokale/Chisle --skill chisle-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/chisle-audit, .gemini/skills/chisle-audit, .github/skills/chisle-audit and .opencode/skills/chisle-audit in your project.

What does Chisle Audit need to run?

Going by SKILL.md and its folder, Chisle Audit needs the command-line tools its instructions call (git).

Does Chisle Audit access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Chisle Audit safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Chisle Audit use?

Chisle Audit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Chisle Audit use?

About 687 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Chisle Audit?

Skills that share tags, products or a category with Chisle Audit: Scientific Documentation (Yikai-Liao/symusic, 189 stars), Find Slop (letehaha/moneymatter, 160 stars), Frontend Code Review (langgenius/dify, 158k stars) and Moonbit Docs Maintainer (moonbitlang/moonbit-docs, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Chisle Audit?

JayPokale (a GitHub user) maintains it in JayPokale/Chisle, which has 636 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 6, 2026.

Source: JayPokale/Chisle on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.