every-style-editor
This skill should be used when reviewing or editing copy to ensure adherence to Every's style guide. It provides a systematic line-by-line review process for grammar, punctuation, mechanics, and style guide compliance.
Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security
Installation for Agentic Skill
View all platforms →skilz install EveryInc/compound-engineering-plugin/every-style-editor skilz install EveryInc/compound-engineering-plugin/every-style-editor --agent opencode skilz install EveryInc/compound-engineering-plugin/every-style-editor --agent codex skilz install EveryInc/compound-engineering-plugin/every-style-editor --agent gemini
First time? Install Skilz: pip install skilz
Works with 22+ AI coding agents
Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...
Extract and copy to ~/.claude/skills/ then restart Claude Desktop
git clone https://github.com/EveryInc/compound-engineering-plugin cp -r compound-engineering-plugin/plugins/compound-engineering/skills/every-style-editor ~/.claude/skills/ Need detailed installation help? Check our platform-specific guides:
Related Agentic Skills
mastering-github-cli
by SpillwaveSolutionsGitHub CLI (gh) command reference for repository search, code discovery, CI/CD monitoring, workflow authoring, and automation. Triggers on "gh" comman...
mastering-github-cli
by SpillwaveSolutionsGitHub CLI (gh) command reference for repository search, code discovery, CI/CD monitoring, workflow authoring, and automation. Triggers on "gh" comman...
signal-intel
by gtmagentsUse when consolidating intent, product usage, and third-party signals to prioritize ABM actions.
meal-prep-efficiency-guru
by sandraschiExpert in batch cooking, meal planning, food storage, and efficient kitchen workflows
Agentic Skill Details
- Repository
- compound-engineering-plugin
- Type
- Non-Technical
- Meta-Domain
- development
- Primary Domain
- github
- Market Score
- 83.0
Agent Skill Grade
B
Score: 83/100
Click to see breakdown
Score Breakdown
Areas to Improve
- No trigger phrases
- 530-line reference file lacks table of contents for navigation
- Inconsistent between 'This skill enables' (third person) and 'Begin by reading' (imperative)
Recommendations
- Add trigger phrases to description for discoverability
- Add table of contents for files over 100 lines
Graded: 1/5/2026
Developer Feedback
I took a look at your every-style-editor skill and wanted to share some thoughts.
Links:
The TL;DR
You're at 83/100, which puts you solidly in B territory - good fundamentals with some polish work to do. Your Progressive Disclosure Architecture is your strongest area (26/30), meaning you've nailed the token-efficient layering between your main SKILL.md and the comprehensive EVERY_WRITE_STYLE.md reference. The gaps are mostly around metadata and consistency rather than core design.
What's Working Well
- Excellent layering strategy - Your 135-line SKILL.md efficiently summarizes workflow while delegating the full 530-line style guide to a reference file. That's exactly how PDA should work.
- Solid structured output - The template with line-by-line checklist gives users clear direction on what to deliver. The examples in your reference file make it actionable.
- Practical problem-solving - You're addressing a real need (consistent editorial review), and your style guide rules are thorough enough to actually guide someone through edits.
The Big One: Description Needs Trigger Phrases
This is the main opportunity holding you back. Your frontmatter description says "This skill should be used when reviewing or editing copy..." but it's missing the explicit trigger phrases that help discoverability.
Why it matters: When someone asks Claude "review this for style", the system needs to know this skill exists. Right now, it's relying on fuzzy matching instead of direct keywords.
The fix: Update your SKILL.md frontmatter description to include triggers like:
"Use when asked to review style, perform line editing, check grammar compliance, proofread for tone, or ensure adherence to Every's style guide."
This bump alone gets you +2 points (83→85).
Other Things Worth Fixing
Mixed voice throughout SKILL.md - You jump between "This skill enables performing..." (third person) and "Begin by reading..." (imperative). Pick one and be consistent. Lean imperative since that's more scannable.
The 530-line reference needs a TOC - Without a table of contents, someone looking for "Capitalization rules" has to scroll forever. Add links to major sections (Abbreviations, Capitalization, Commas, etc.) at the top. That's +1 point of easy wins.
Key Principles section duplicates Step 2 - Both cover punctuation, capitalization, passive voice. Merge or cut one to tighten the overall flow. Redundancy eats token budget.
Quick Wins
Most impactful first:
- Add trigger phrases to description → +2 points
- Add TOC to EVERY_WRITE_STYLE.md → +1 point
- Standardize voice (imperative throughout) → +2 points
- Remove redundancy between Key Principles and Step 2 → +1 point
That's 6 points of relatively quick improvements getting you to 89/100 (solid A territory).
Checkout your skill here: SkillzWave.ai | SpillWave We have an agentic skill installer that install skills in 14+ coding agent platforms. Check out this guide on how to improve your agentic skills.
Browse Category
More development Agentic SkillsReport Security Issue
Found a security vulnerability in this agent skill?