copy-editing

When the user wants to edit, review, or improve existing marketing copy, or refresh outdated content. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' 'copy sweep,' 'tighten this up,' 'this reads awkwardly,' 'clean up this text,' 'too wordy,' 'sharpen the messaging,' 'refresh this content,' 'update this page,' 'this content is outdated,' or 'content audit.' Use this when the user already has copy and wants it improved or refreshed rather than rewritten from scratch. For writing new copy, see copywriting.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/copy-editing/SKILL.md

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable instruction skill with an exemplary sequenced workflow and built-in validation/feedback loops, backed by three real reference files that keep heavy detail offloaded. The main drag on token efficiency is length: several 'Common X issues' sections and the full replacement tables restate checks already covered and could move to the reference files.

Suggestions

Move the Vague→Specific, Weak→Strong, and Word-Level replacement tables into references/plain-english-alternatives.md (or checklist.md) and reference them, trimming 60-80 lines from SKILL.md.

Collapse the per-sweep 'Common X issues/kills/failures' subsections into the existing 'What to check' bullets to remove duplication while preserving coverage.

Move the Recommended Expert Panels persona lists and the Scoring Rubric table into a reference file (e.g., references/expert-panel.md), keeping only the 'When to Use' guidance and panel-building steps inline.

Dimension	Reasoning	Score
Conciseness	The body is well-organized but noticeably long (~450 lines) with some padded restatement—e.g., 'Common clarity killers,' 'Common voice issues,' 'Common So What failures,' and 'Common specificity issues' repeat checks already implied by the 'What to check' lists, and the 'After this sweep' loopback instructions are spelled out seven times.	3 / 5
Actionability	Each sweep gives concrete 'What to check,' example do/don't pairs (the So What ❌/✅ and the Vague→Specific tables), and a step-by-step process, so the guidance is mostly executable. It falls short of 5 only because much guidance is instructional checks rather than copy-paste-ready mechanics, which is appropriate for an instruction-only skill.	4 / 5
Workflow Clarity	The Seven Sweeps are explicitly sequenced (1–7), each ends with a named validation checkpoint ('After this sweep: return to ...'), the final sweep mandates a full re-pass through all prior sweeps, and the Expert Panel section adds an explicit validate→fix→re-score feedback loop with pass criteria (7+ per persona, 8+ average).	5 / 5
Progressive Disclosure	Three real one-level-deep reference files exist (checklist.md, content-refresh.md, plain-english-alternatives.md) and are clearly signaled from the body, keeping bulk detail out of SKILL.md. It is not a 5 because sizable reference-grade material—e.g., the full Specificity and Word Replacement tables, the Expert Panel persona lists, and the Quick-Pass checks—could reasonably live in those reference files rather than inline.	4 / 5
	Total	16 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that excels at trigger-term coverage and clearly answers both 'what' and 'when,' including helpful boundary guidance against copywriting. Its main weakness is specificity of capabilities: it states the high-level actions but does not surface the concrete editing techniques the skill actually performs.

Suggestions

Add 2-3 concrete editing actions to the 'what' clause (e.g., 'runs seven focused editing passes—clarity, voice, proof, specificity, emotion, and risk—and scores copy against an expert panel') so capabilities are visible without reading the body.

Trim the longest quoted trigger lists slightly; the most distinctive phrases already carry the signal and a tighter list reads as more deliberate.

Dimension	Reasoning	Score
Specificity	The description names the domain (editing/reviewing/refreshing marketing copy) and 1-2 concrete actions ('edit,' 'review,' 'refresh') but does not enumerate the specific sweep-level techniques (e.g., clarity, specificity, emotion, risk reversal) that constitute the skill's actual capabilities.	3 / 5
Completeness	It explicitly answers both 'what' (edit, review, improve, or refresh existing marketing copy) and 'when' (a long 'Use when the user mentions...' clause plus a boundary statement for writing new copy), with concrete trigger phrases.	5 / 5
Trigger Term Quality	It lists a comprehensive set of natural phrases users would actually say ('edit this copy,' 'proofread,' 'polish this,' 'copy sweep,' 'tighten this up,' 'this reads awkwardly,' 'too wordy,' 'sharpen the messaging,' 'refresh this content,' 'content audit'), including synonyms and variations.	5 / 5
Distinctiveness Conflict Risk	It carves a clear niche (improving existing copy vs. writing new copy, which it explicitly routes to 'copywriting') with distinct triggers; minor overlap risk remains with adjacent marketing skills (cro, marketing-psychology), so it is not a clean 5.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: coreyhaines31/marketingskills
Path: skills/copy-editing/SKILL.md
Commit: f557c54

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.