SkillsAdd

liustack/vibemaster

style-audit

Audit product texts (skills, references, READMEs, rules) against the expression-style disciplines — unexplained coined terms, transliterated loan-words, semicolons, source-citation leaks.

First seen Jul 26, 2026

Installation

$ npx skills add liustack/vibemaster --skill style-audit
View on skills.sh ↗ GitHub repository ↗

Summary

  • Audit product texts (skills, references, READMEs, rules) against the expression-style disciplines — unexplained coined terms, transliterated loan-words, semicolons, source-citation leaks.
  • Use when asked to 黑话审计 / style audit / 审查表达风格 / check the writing style, or before shipping a batch of skill copy.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

terraform-style-guide Similar name
hashicorp/agent-skills

Generate Terraform HCL code following HashiCorp's official style conventions and best practices…

10.5K installs
mapbox-style-patterns Similar name
mapbox/mapbox-agent-skills

Common style patterns, layer configurations, and recipes for typical mapping scenarios includin…

1.9K installs
mapbox-style-quality Similar name
mapbox/mapbox-agent-skills

Expert guidance on validating, optimizing, and ensuring quality of Mapbox styles through valida…

1.6K installs
content-style-guide Similar name
bitwarden/ai-plugins

Bitwarden's product content style guide for end-user-facing GUI copy — voice, tone, AP-style-wi…

37 installs
golang-code-style Similar name
samber/cc-skills-golang

Golang code style conventions — line length and breaking, variable declarations, control flow c…

40.3K installs
python-code-style Similar name
wshobson/agents

Python code style, linting, formatting, naming conventions, and documentation standards. Use wh…

14.3K installs

Also in this package

Other skills from liustack/vibemaster · top by installs.

npx skills add liustack/vibemaster
snapshot 44 coding 43 shaping 42 dig 42 ls-first-principles 2 ls-systems-thinking 2 ls-best-practices 2 inversion 2 test-first 2 ls-inversion 2

Browse all from liustack/vibemaster

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 11
License LICENSE
Default branch main
Open issues 0
Status Active

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 2,503 B
  • docs SUMMARY.md 343 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 41 installs

SKILL.md

style-audit: expression-style audit for product texts

Project-local authoring tool. The shipped product lives in skills/ — this skill never ships with it.

Two layers, one ratchet

  • This skill is the judgment layer: it finds what a script cannot — coined labels without an in-sentence explanation, loan-word nouns minted from foreign material, process traces in product copy.
  • scripts/check-style.sh is the mechanical layer: a banned-term list plus a semicolon check, wired into CI. It only knows what audits have already found.
  • The ratchet: every term an audit purges gets appended to BANNED in scripts/check-style.sh, so it can never come back.

Disciplines to audit against

  1. Plain language (rules/plain-language.md): everyday words over terminology — the test is whether a reader outside the project understands without looking anything up. Coined labels and metaphors must be explained in the same sentence on first use. Foreign material is described in your own words, not transliterated into a pet noun.
  2. Punctuation (rules/punctuation.md): no semicolons in prose. The script catches this — spot-check only.
  3. Content discipline: no source citations in product copy (no "per X's book", no repo credits), no process traces ("changed because review said"), no invented metaphors.

Procedure

  1. Scope: changed files by default (git diff --name-only), or all of skills/, rules/, README* on request. .zh-CN translations are held to the same bar.
  2. Report each finding as: the term or sentence, a quoted line, why it fails (one clause), and a concrete fix — a plain rewrite or an in-sentence explanation, with exact wording.
  3. Err on the side of silence: report only what an outside reader would actually stumble on. Terms explained in place, industry-standard vocabulary (API, spec, TDD, AARRR), and skill or product names are not findings.
  4. After fixes land and a term is fully purged, append it to BANNED in scripts/check-style.sh — in both stacks if it appeared in both.
  5. Run bash scripts/check-style.sh and confirm green before committing.