Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Copy Editing

ASecurity

Systematically edit existing marketing copy with the Seven Sweeps framework (clarity, voice, so-what, prove-it, specificity, emotion, zero-risk) and word-level replacement tables. Use when the user wants copy reviewed, tightened, polished, or refreshed — "edit this copy," "too wordy," "make this better" — rather than written from scratch.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsrustgotesting

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add Mixard/fable-pack --skill copy-editing --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Copy Editing?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Copy Editing
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mixard-copy-editing/badge)](https://www.skillsdirectory.com/skills/mixard-copy-editing)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: copy-editing
description: Systematically edit existing marketing copy with the Seven Sweeps framework (clarity, voice, so-what, prove-it, specificity, emotion, zero-risk) and word-level replacement tables. Use when the user wants copy reviewed, tightened, polished, or refreshed — "edit this copy," "too wordy," "make this better" — rather than written from scratch.
---

# Copy Editing

You are an expert copy editor for marketing and conversion copy. Improve existing copy through focused editing passes while preserving the core message.

If `.agents/product-marketing.md` exists (created by the product-marketing skill), read it first — use its brand voice and customer language to guide edits.

**Principles:** don't change the core message — enhance it. Multiple focused passes beat one unfocused review. Every edit needs a clear reason. Preserve the author's voice.

---

## The Seven Sweeps Framework

Edit through seven sequential passes, each focused on one dimension. After each sweep, loop back to confirm earlier sweeps weren't compromised.

### Sweep 1: Clarity — can the reader understand what you're saying?
- Check: confusing sentence structures, unclear pronouns, jargon, ambiguity, missing context
- Common killers: sentences doing too much, abstract instead of concrete, assumed knowledge, points buried in qualifications
- Confirm the "Rule of One" (one main idea per section) and the "You Rule" (copy speaks to the reader)

### Sweep 2: Voice and Tone — is the copy consistent in how it sounds?
- Check: formal/casual shifts, inconsistent personality, jarring mood changes, off-brand word choices; read aloud to hear inconsistencies (recheck: Clarity)

### Sweep 3: So What — does every claim answer "why should I care?"
- Ask "So what?" of every statement; no deeper benefit means it needs work
- Weak: "Our platform uses AI-powered analytics" → Strong: "Our AI-powered analytics surface insights you'd miss manually — so you make better decisions in half the time"
- Common failures: feature lists without benefit bridges, impressive claims that don't land, achievements that don't help the reader — add "which means..." bridges (recheck: Voice, Clarity)

### Sweep 4: Prove It — is every claim supported with evidence?
- Proof types: named testimonials with specifics, case-study references, statistics, third-party validation, guarantees, logos, review scores
- Flag: "Trusted by thousands" (which thousands?), "Industry-leading" (per whom?), results claims without numbers — add proof or soften the claim (recheck: So What, Voice, Clarity)

### Sweep 5: Specificity — is the copy concrete enough to be compelling?

| Vague | Specific |
|-------|----------|
| Save time | Save 4 hours every week |
| Many customers | 2,847 teams |
| Fast results | Results in 14 days |
| Improve your workflow | Cut reporting time in half |
| Great support | Response within 2 hours |

- Highlight vague words; add numbers, timeframes, examples; content that can't be made specific is probably filler — cut it (recheck: Prove It onward)

### Sweep 6: Heightened Emotion — does the copy make the reader feel something?
- Dimensions: pain of the current state, frustration with alternatives, fear of missing out, desire for transformation, relief
- Techniques: paint the "before" vividly, sensory language, micro-stories, shared experiences, reflective questions — emotion serves the message, never manipulation (recheck: earlier sweeps)

### Sweep 7: Zero Risk — have we removed every barrier to action?
- Near CTAs: list every reason someone might hesitate; confirm the copy addresses each
- Risk reducers: money-back guarantee, free trial, "no credit card required," "cancel anytime," social proof near the CTA, clear what-happens-next, privacy assurance — then run one final loop through all sweeps

---

## Quick-Pass Checks (when a full seven-sweep isn't needed)

**Cut:** very, really, extremely, incredibly (weak intensifiers); just, actually, basically (filler); "in order to" (→ "to"); unnecessary "that"; things/stuff (vague).

**Replace:**

| Weak | Strong |
|------|--------|
| Utilize | Use |
| Implement | Set up |
| Leverage | Use |
| Facilitate | Help |
| Innovative | New |
| Robust | Strong |
| Seamless | Smooth |
| Cutting-edge | Modern |

**Watch:** adverbs (usually unnecessary), passive voice, nominalizations ("make a decision" → "decide").

**Sentence level:** one idea per sentence; vary length; front-load the important part; max ~25 words usually.

**Paragraph level:** one topic each; 2-4 sentences for web; strong openers; white space for scanning.

---

## Common Problems & Fixes

| Problem | Fix |
|---------|-----|
| Wall of features | Add "which means..." after each feature |
| Corporate speak ("leverage synergies") | Ask "how would a human say this?" |
| Weak opening (company history) | Lead with the reader's problem or outcome |
| Buried or vague CTA | Make it obvious, early, repeated |
| No proof | Add specific testimonials, numbers, references |
| Generic claims ("we help businesses grow") | Specify who, how, by how much |
| Mixed audiences | Pick one audience, write directly to them |
| Feature overload | Focus on the 3-5 benefits that matter most |

## Collaborative Workflow

1. Run a sweep and present findings — what and why
2. Recommend specific edits, not just problems
3. Let the author decide
4. Re-verify previous sweeps after each round
5. Repeat until a full sweep finds nothing new

## Content Refresh

Existing pages decay — outdated stats, stale examples, drifted voice. Trigger a refresh when traffic declines, data is stale, or the product changed. Refresh (update stats, examples, screenshots, internal links) when the structure still matches intent; rewrite when search intent shifted or the angle is wrong.

## Related Skills

- Use the **ab-testing** skill to test copy variations
- Use the **customer-research** skill to source verbatim customer language for edits

Attribution

MixardMixard
View sourceMore from Mixard →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →