copy-editing

When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' or 'copy sweep.' This skill provides a systematic approach to editing marketing copy through multiple focused passes.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

81%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 highly actionable, well-sequenced editing framework with concrete tooling and examples. The main weakness is conciseness — significant redundancy across the sweeps, checklist, and problems-and-fixes sections — plus one orphaned reference file.

Suggestions

Consolidate the overlapping coverage of the seven dimensions: keep the detailed sweeps, and either drop or sharply shorten the 'Copy Editing Checklist' and 'Common Copy Problems & Fixes' sections that repeat the same material.

Link references/ai-detection-patterns.md from the AI-Pattern Check section so the existing bundle file is discoverable rather than orphaned.

Consider moving the word-, sentence-, and paragraph-level Quick-Pass tables into references/plain-english-alternatives.md (or a dedicated reference) to slim the SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	Mostly useful but structurally redundant: the seven sweeps are detailed, then re-stated as a checklist, then partly re-stated in 'Common Copy Problems & Fixes,' plus overlapping Quick-Pass checks. Could be tightened without losing value.	3 / 5
Actionability	Provides executable commands (readability_scorer.py, ai_content_detector.py with --json), concrete before/after tables, a worked So-What example, and specific per-sweep steps that cover the common cases.	5 / 5
Workflow Clarity	The seven sweeps are a clearly sequenced multi-step process with explicit feedback loops ('After this sweep: Return to…'), validation (re-run the scorer; Flesch must improve), and an accompanying checklist.	5 / 5
Progressive Disclosure	Clear section structure with a References entry and inline script invocations, but references/ai-detection-patterns.md is not surfaced from the body and some inlined material (quick-pass checks) could live in reference files.	4 / 5
	Total	17 / 20 Passed

Description

91%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, well-constructed description that clearly states purpose and provides rich, natural trigger phrases. Minor room to sharpen distinctiveness from sibling marketing skills and to surface more concrete capabilities inline.

Dimension	Reasoning	Score
Specificity	Names the domain ('marketing copy') and several concrete actions ('edit, review, or improve') plus a systematic multi-pass approach, but does not comprehensively enumerate the skill's concrete capabilities in the description itself.	4 / 5
Completeness	Explicitly answers both 'what' (systematic editing of marketing copy through multiple focused passes) and 'when' with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural user phrases including synonyms ('edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' 'copy sweep') that users would actually say.	5 / 5
Distinctiveness Conflict Risk	Targets a clear niche (marketing copy editing) with distinct triggers, but has minor overlap risk with related skills (copywriting, content-humanizer) and the generic 'make this better' phrasing.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (503 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: marketing-skill/skills/copy-editing/SKILL.md
Commit: 19392f7

Reviewed: ~1 hour 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.