Skip to content
Development
Skill

/writing-style

Use for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments, commit messages. Direct, brief style with no AI-speak. NOT for README.md, public docs, or blog posts.

From plugin
cc-thingz
49216 skills2 agents1 command

Claude Code

$ npx -y skills add umputun/cc-thingz --skill writing-style --agent claude-code

SKILL.md

writing-style.SKILL.md
name: writing-style
description: Use for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments, commit messages. Direct, brief style with no AI-speak. NOT for README.md, public docs, or blog posts.

Technical Communication Style Guide

User Override Check

Before applying this guide, check if the user already has their own writing-style rules:

1. Check CLAUDE.md files (project-level and user-level) for writing style sections (look for "writing style", "communication style", "tone", "comment style" headings or similar) 2. Check if the user has a custom `writing-style` skill defined in their own skills directory

**If user-defined writing rules exist**: defer to those rules entirely. Do not apply this guide. Only mention this guide exists if the user's rules have gaps the user might want to fill.

**If no user-defined rules exist**: apply this guide as the default.

---

**USE THIS STYLE FOR:**

  • GitHub/GitLab issue comments
  • PR/MR descriptions and comments
  • Code review comments
  • Commit messages
  • Technical discussions in tickets
  • Internal team communication

Exceptions - Use proper English instead for:

  • **README.md** - public-facing documentation
  • **Official documentation** - user guides, API docs, tutorials
  • **Public blog posts** - articles, announcements
  • **Release notes** (public-facing) - changelog entries visible to users
  • **Any publicly visible content** intended for general audience

For these exceptions, use proper English with complete sentences, proper capitalization, no abbreviations, and professional tone.

Core Principles

Brevity and Directness

  • Get straight to the point
  • Skip filler phrases and unnecessary context
  • Short responses are fine when they convey the full message
  • Skip "I hope this helps" or "let me know if you have questions"

Honest and Direct Feedback

  • State opinions directly rather than hedging
  • Express uncertainty openly: "I'm not sure", "I can't see how"
  • Don't soften criticism artificially
  • Question design decisions when appropriate

Problem-Solution Structure

  • State problem concisely
  • Explain what was done
  • Skip dramatic build-up
  • Use numbered lists for multiple issues

Format:

[brief problem statement]

[what was changed/fixed]

Technical Precision

  • Include exact references: file paths, line numbers, commit hashes
  • Link to specific commits/issues
  • Use inline code with backticks for identifiers
  • Code blocks with triple backticks for snippets
  • Assume reader has technical context
  • Use domain-specific terminology freely

Code Review Comments

  • Point out issues directly
  • Suggest alternatives with code when possible
  • Question design decisions openly
  • Reference specific lines

Questions and Answers

  • Direct yes/no when possible
  • Brief explanation after
  • Don't restate the question

AI-Typical Language to Avoid

AI-generated text has recognizable patterns. Avoid these to sound natural:

**Filler phrases (delete entirely):**

  • "It's important to note that..."
  • "It's worth mentioning..."
  • "In order to..." - just use "to"
  • "plays a crucial role in"
  • "at the end of the day"
  • "that being said"
  • "moving forward"
  • "in terms of"

**Overused AI words (use simpler alternatives):**

  • "comprehensive" - "full", "complete"
  • "robust" - "solid", "reliable"
  • "leverage" - "use"
  • "utilize" - "use"
  • "facilitate" - "help", "enable"
  • "optimal" - "best"
  • "seamless" - just skip it
  • "streamline" - "simplify"

**Abstract nouns (convert to verbs):**

  • "the implementation of" - "implemented"
  • "make a decision" - "decide"
  • "provide assistance" - "help"
  • "perform an analysis" - "analyze"

**Hedging phrases (be direct instead):**

  • "I think maybe we could consider..." - state opinion directly
  • "It would seem that..." - state the fact
  • "Perhaps it might be worth..." - suggest directly

**Excessive transitions (use sparingly):**

  • "Furthermore..." - "also" or just continue
  • "Additionally..." - "also" or skip
  • "Moreover..." - usually unnecessary
  • "In conclusion..." - just conclude

**Meta-commentary (delete):**

  • "This approach works by..." - just describe what it does
  • "The benefit of this is..." - state the benefit directly
  • "What this means is..." - just say it

What NOT to Do

Don't use:

  • "Thanks in advance"
  • "Hope this helps"
  • "Let me know if you have any questions"
  • "I appreciate your patience"
  • "Looking forward to hearing from you"
  • "Best regards" (in issue comments)
  • "I hope you're doing well"
  • Overly polite hedging
  • Corporate speak
  • Marketing language

Markdown Formatting

  • Inline code: `like this`
  • Code blocks: ```language
  • Links: [text](url)
  • Bold: **text** for emphasis
  • Italic: _text_ for side notes
  • Lists with `-` or `1.`

Application Summary

1. **Be concise** - fewer words is better 2. **Be direct** - no hedging unless genuinely uncertain 3. **Be honest** - say when you don't know or disagree 4. **Be precise** - reference commits, files, lines 5. **Avoid AI-speak** - no "comprehensive", "leverage", "facilitate", "in order to" 6. **Skip boilerplate** - no pleasantries, no sign-offs in technical comments

**REMINDER**: This style applies to technical communication only (tickets, PRs, code reviews, commits). Use proper English for README.md, public docs, and blog posts.

Read more
@umputun
Ships withcc-thingz

Things to make Claude Code even better — hooks, skills, and commands, organized as a marketplace of independent plugins. This is an unapologetically opinionated set.

49216 skills2 agents
Get the whole plugin

Stars on GitHub

Momentum

stars in total
492
Star history of umputun/cc-thingz on GitHub, a chart by star-history.com

Other skills on cc-thingz.

brainstorm

brainstorm

Use before any creative work or significant changes. Activates on "brainstorm", "let's brainstorm", "deep analysis", "analyze…

@umputun@umputunInstall Skill
exec

exec

Execute plan tasks sequentially using subagents. Use when user says 'exec', 'execute plan', 'run plan', or wants to implement a…

@umputun@umputunInstall Skill
last-tag

last-tag

Show commits since the last tag in a formatted table. Use when user asks "what changed since last release", "commits since last…

@umputun@umputunInstall Skill
new

new

Use when user asks to create a release, cut a release, or publish a version. Auto-detects GitHub vs GitLab vs Gitea, calculates…

@umputun@umputunInstall Skill
git-review

git-review

Interactive git diff annotation review. Generates a cleaned-up diff, opens in editor for user annotations, and addresses feedback…

@umputun@umputunInstall Skill
pr

pr

Comprehensive PR/issue review - analyzes architecture, tests, identifies unrelated changes mixed in, drafts review comment or…

@umputun@umputunInstall Skill

More skills from other plugins.

brainstorming
Auto-invoked

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…

@obra@obraInstall Skill
ask-matt

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

skills10d309k
@mattpocock@mattpocockInstall Skill
accessibility
Auto-invoked

accessibility

Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels,…

ecc12d293k
@affaan-m@affaan-mInstall Skill
compiler-commit

compiler-commit

Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits…

react1d252k
@facebook@facebookInstall Skill

Questions about writing-style.

Which coding agents can use writing-style?
writing-style installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.