agentleFS
TsukiNi22TsukiNi22/ai-utils/skills/routers/style/SKILL.md

style

Skill1 starsChanged 3 days agoMITView on GitHub

Router for the user's coding style in every language - picks the style skills matching the files (C++, CMake, Python, shell, Lua, JS/TS, C, YAML, comments, docs) to write, format or review code like the user. Invoke manually with /style.

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When xstyle is installed (command -v xstyle), start with xstyle --rtk <paths> -r (compact, made for the assistant.

    line 32
  2. Distinctive:

    Start the answer with one line listing the loaded skills.

    line 38

“Common” is measured: kept by at least 6 in 10 of the 6 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Coding style router

Request given with /style: $ARGUMENTS

Load the skills with the Skill tool (never the other routers: they are manual-only), then write / reformat / review. The request is the text given with /style (or the latest request; if none, review the uncommitted changes: git diff --stat, git diff).

Skills by file / language

FilesSkills
.cpp, .hpp, .tpp, .inl (and .h of a C++ project)cpp-style + cpp-comments
.pypython-style + python-comments (new files: python-class)
any other language: .sh, .lua, .js/.ts, .rs, .go, .c/.h (C), .yml, .json...coding-style + comments
comments of any file (C, CMake, Makefile, shell, Python, Lua, YAML...)comments
new C++ files / classescpp-class (layout, header, sections) + the two above
CMakeLists.txt, *.cmake, *.cmake.incmake-style
Markdown docsreadme-style
HTML docshtml-doc
protocol docs (frames, codes, commands: Markdown / PDF / HTML)protocol-doc
commit messagesgit-conventions
whole project review with a reportaudit-quality (PDF)

Review mode

When xstyle is installed (command -v xstyle), start with xstyle --rtk <paths> -r (compact, made for the assistant; -o /tmp/xstyle.md when a Markdown report is wanted, -S for the counters): its findings (rule code + severity + fix) are the base of the review, checked and completed by hand; xstyle --rtk --fix [CODES] applies the fixable ones when the user asks for the fixes. The review is delivered through report (format asked once, English, audit/ at the repository root) (audit-quality for a whole project). List the deviations per file with the rule they break (skill + rule), most important first, then propose the fixes; only apply them if asked. Never change the logic while restyling. Start the answer with one line listing the loaded skills.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.