Install any skill in seconds. Free to start, no credit card required.
Get Started Free →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.
.claude/skills/microck-every-style-editor/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 128% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 265% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 109% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 102% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 38% | 0% |
This skill provides a systematic approach to reviewing copy against Every's comprehensive style guide. It transforms Claude into a meticulous line editor and proofreader specializing in grammar, mechanics, and style guide compliance.
Use this skill when:
This skill enables performing a comprehensive review of written content in four phases:
Begin by reading the entire piece to understand:
Review each paragraph systematically, checking for:
Reference the complete EVERY_WRITE_STYLE.md for specific rules when in doubt.
Verify:
Present findings using this structure:
DOCUMENT REVIEW SUMMARY
=====================
Document Type: [type]
Word Count: [approximate]
Overall Assessment: [brief overview]
ERRORS FOUND: [total number]
DETAILED CORRECTIONS
===================
[For each error found:]
**Location**: [Paragraph #, Sentence #]
**Issue Type**: [Grammar/Punctuation/Mechanics/Style Guide]
**Original**: "[exact text with error]"
**Correction**: "[corrected text]"
**Rule Reference**: [Specific style guide rule violated]
**Explanation**: [Brief explanation of why this is an error]
---
RECURRING ISSUES
===============
[List patterns of errors that appear multiple times]
STYLE GUIDE COMPLIANCE CHECKLIST
==============================
✓ [Rule followed correctly]
✗ [Rule violated - with count of violations]
FINAL RECOMMENDATIONS
===================
[2-3 actionable suggestions for improving the draft]The complete Every style guide is included in references/EVERY_WRITE_STYLE.md. Key areas to focus on:
Based on Every's style guide, pay special attention to:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-08 | pass→pass | 9,626 | 7,447 | -23% | 1 | 1 | 0% | 1,624 | 2,322 | +43% | 0 | 0 | — |
case-01 | fail→fail | 10,201 | 2,051 | -80% | 1 | 1 | 0% | 1,697 | 1,375 | -19% | 0 | 0 | — |
case-02 | fail→fail | 6,335 | 4,696 | -26% | 1 | 1 | 0% | 1,020 | 1,662 | +63% | 0 | 0 | — |
case-03 | pass→pass | 10,850 | 17,388 | +60% | 1 | 1 | 0% | 1,780 | 3,926 | +121% | 0 | 0 | — |
case-04 | fail→fail | 7,219 | 4,688 | -35% | 1 | 1 | 0% | 1,227 | 1,719 | +40% | 0 | 0 | — |
case-05 | fail→fail | 8,359 | 8,804 | +5% | 1 | 1 | 0% | 1,423 | 2,643 | +86% | 0 | 0 | — |
case-06 | pass→pass | 3,682 | 3,008 | -18% | 1 | 1 | 0% | 615 | 1,601 | +160% | 0 | 0 | — |
case-07 | pass→pass | 6,890 | 3,659 | -47% | 1 | 1 | 0% | 1,156 | 1,698 | +47% | 0 | 0 | — |
case-09 | fail→pass | 6,033 | 5,892 | -2% | 1 | 1 | 0% | 867 | 1,973 | +128% | 0 | 0 | — |
case-10 | pass→pass | 7,685 | 4,508 | -41% | 1 | 1 | 0% | 1,356 | 1,772 | +31% | 0 | 0 | — |
case-11 | pass→pass | 7,581 | 6,162 | -19% | 1 | 1 | 0% | 1,237 | 2,035 | +65% | 0 | 0 | — |
case-12 | pass→pass | 4,547 | 4,694 | +3% | 1 | 1 | 0% | 714 | 1,778 | +149% | 0 | 0 | — |
case-13 | fail→pass | 3,134 | 3,696 | +18% | 1 | 1 | 0% | 471 | 1,717 | +265% | 0 | 0 | — |
case-14 | pass→pass | 5,202 | 3,583 | -31% | 1 | 1 | 0% | 893 | 1,615 | +81% | 0 | 0 | — |
case-15 | pass→pass | 4,478 | 4,174 | -7% | 1 | 1 | 0% | 772 | 1,708 | +121% | 0 | 0 | — |
case-16 | fail→pass | 4,436 | 3,115 | -30% | 1 | 1 | 0% | 744 | 1,558 | +109% | 0 | 0 | — |
case-17 | fail→pass | 5,108 | 4,725 | -7% | 1 | 1 | 0% | 888 | 1,791 | +102% | 0 | 0 | — |
case-18 | fail→fail | 6,576 | 5,437 | -17% | 1 | 1 | 0% | 947 | 1,837 | +94% | 0 | 0 | — |
case-19 | fail→pass | 9,019 | 6,039 | -33% | 1 | 1 | 0% | 1,444 | 1,987 | +38% | 0 | 0 | — |
case-20 | fail→pass | 8,863 | 11,437 | +29% | 1 | 1 | 0% | 1,391 | 2,954 | +112% | 0 | 0 | — |
case-21 | fail→pass | 9,678 | 8,396 | -13% | 1 | 1 | 0% | 1,466 | 2,294 | +56% | 0 | 0 | — |
case-22 | fail→pass | 7,007 | 5,068 | -28% | 1 | 1 | 0% | 1,060 | 1,831 | +73% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +36 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.