User-Facing Text Cleanup
guillaumemeyer/watermarks-remover
Audits prose for invisible Unicode characters and rewrites it while keeping facts, citations, code and required disclosures unchanged and the writer's voice intact.
Systematic copy editing through focused passes (the Seven Sweeps Framework) covering clarity, voice, proof, specificity, and friction removal.
$ npx skills add borghei/Claude-Skills --skill copy-editing -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install borghei/Claude-Skills copy-editing --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/marketing/copy-editing .claude/skills/copy-editing && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "copy-editing" agent skill from https://github.com/borghei/Claude-Skills/tree/main/marketing/copy-editing into .claude/skills/copy-editing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "copy-editing", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/borghei/Claude-Skills/tree/main/marketing/copy-editingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add borghei/Claude-Skills --skill copy-editing -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install borghei/Claude-Skills copy-editing --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/marketing/copy-editing .agents/skills/copy-editing && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "copy-editing" agent skill from https://github.com/borghei/Claude-Skills/tree/main/marketing/copy-editing into .agents/skills/copy-editing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "copy-editing", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add borghei/Claude-Skills --skill copy-editing -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install borghei/Claude-Skills copy-editing --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/marketing/copy-editing .cursor/skills/copy-editing && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "copy-editing" agent skill from https://github.com/borghei/Claude-Skills/tree/main/marketing/copy-editing into .cursor/skills/copy-editing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "copy-editing", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/borghei/Claude-Skills.git --path marketing/copy-editing--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add borghei/Claude-Skills --skill copy-editing -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install borghei/Claude-Skills copy-editing --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/marketing/copy-editing .gemini/skills/copy-editing && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "copy-editing" agent skill from https://github.com/borghei/Claude-Skills/tree/main/marketing/copy-editing into .gemini/skills/copy-editing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "copy-editing", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install borghei/Claude-Skills copy-editingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add borghei/Claude-Skills --skill copy-editing -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/marketing/copy-editing .github/skills/copy-editing && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "copy-editing" agent skill from https://github.com/borghei/Claude-Skills/tree/main/marketing/copy-editing into .github/skills/copy-editing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "copy-editing", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add borghei/Claude-Skills --skill copy-editing -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install borghei/Claude-Skills copy-editing --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/marketing/copy-editing .opencode/skills/copy-editing && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "copy-editing" agent skill from https://github.com/borghei/Claude-Skills/tree/main/marketing/copy-editing into .opencode/skills/copy-editing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "copy-editing", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
copy-editingSystematic copy editing through focused passes (the Seven Sweeps Framework) covering clarity, voice, proof, specificity, and friction removal.
Copy Editing is an agent skill from borghei/Claude-Skills. Systematic copy editing through focused passes (the Seven Sweeps Framework) covering clarity, voice, proof, specificity, and friction removal. Use when editing marketing copy, reviewing drafts, polishing content, or proofreading.
Its SKILL.md is about 5.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/ai_pattern_detector.py`, `scripts/readability_scorer.py` and `scripts/style_checker.py`).
It sits in Writing & Content, covering Copy editing and proofreading. The repository describes itself as: 385 AI skills, 77 expert agents, and 900 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, research, and a LinkedIn toolkit… The licence is MIT.
8 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit c9a1487. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 3 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Copy Editing loads about 5.1k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 2,576 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from borghei/Claude-Skills at commit c9a1487, republished under its MIT licence (© borghei). 2,576 words, ~5,062 tokens.
.claude/skills/copy-editing/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Systematic copy improvement through focused editorial passes that enhance clarity, voice, proof, and conversion impact.
copy editing, editorial review, copy feedback, proofreading, content polishing, copy sweep, editorial standards, style consistency, grammar check, fact-checking, clarity editing, voice consistency, benefit framing, proof validation, specificity, conversion copy editing, marketing copy review, copy quality
Before editing, confirm these inputs. If any is unknown or vague, ASK — do not assume:
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
Edit through seven sequential passes. Each focuses on one dimension. After each sweep, verify previous sweeps are not compromised.
Focus: Can the reader understand what you are saying on the first read?
What to check:
Clarity killers to fix:
| Problem | Fix |
|---|---|
| Sentence over 30 words | Split into two sentences |
| Abstract language | Replace with concrete example |
| Buried main point | Move to beginning of paragraph |
| Three-clause sentence | Simplify to one or two clauses |
| Undefined acronym | Spell out on first use |
After this sweep: Confirm the "Rule of One" (one idea per section) and "You Rule" (copy speaks to the reader as "you") are intact.
Focus: Does the copy sound consistent throughout?
What to check:
Voice consistency indicators:
| Consistent | Inconsistent |
|---|---|
| Same level of contractions throughout | Contractions in some sections, full forms in others |
| Humor style maintained | Random joke in otherwise serious copy |
| Same sentence structure patterns | Short punchy intro, corporate middle, casual close |
| Consistent use of "you" | Switching between "you," "users," "customers," "one" |
After this sweep: Return to Sweep 1 to ensure voice edits did not introduce confusion.
Focus: Does every claim answer "why should I care?"
The So What test: For every statement, ask "So what?" If the copy does not answer with a deeper benefit, it needs work.
| Before (features only) | After (feature + benefit) |
|---|---|
| "Our platform uses AI-powered analytics" | "Our AI analytics surface insights you would miss manually — so you make better decisions in half the time" |
| "SOC 2 Type II certified" | "SOC 2 certified — your security team approves us in days, not months" |
| "Real-time dashboard" | "See exactly what is happening right now, not what happened last week" |
After this sweep: Return to Sweeps 2 and 1.
Focus: Is every claim backed with evidence?
Types of proof to verify:
| Proof Type | Strength | Example |
|---|---|---|
| Named testimonial | Strong | "Sarah Chen, VP Marketing at Stripe: 'Reduced our setup time by 60%'" |
| Specific statistic | Strong | "2,847 teams use [Product] daily" |
| Case study reference | Strong | "See how Linear reduced churn by 23% in 90 days" |
| Third-party validation | Strong | "Named a Leader in Gartner's Magic Quadrant 2025" |
| Customer logos | Medium | Recognizable brand logos with permission |
| Generic claim | Weak — flag it | "Customers love us," "Industry-leading" |
Common proof gaps to flag:
After this sweep: Return to Sweeps 3, 2, and 1.
Focus: Is the copy concrete enough to be compelling?
Specificity upgrades:
| 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 from 4 hours to 15 minutes" |
| "Great support" | "Average response time: 2 hours" |
| "Easy to use" | "Set up in 10 minutes, no code required" |
| "Affordable" | "Starting at $29/month" |
| "Scalable" | "Handles 10,000 to 10 million records without slowdown" |
Rule: If a claim cannot be made specific, it is probably filler. Cut it or replace it with something verifiable.
After this sweep: Return to Sweeps 4, 3, 2, and 1.
Focus: Does the copy make the reader feel something?
Emotional dimensions to check:
| Emotion | Where to Use | Technique |
|---|---|---|
| Pain/frustration | Problem section | Paint the "before" state vividly |
| Relief | Solution section | Show the contrast with current pain |
| Fear of missing out | Social proof | "Teams like yours already use..." |
| Pride | Aspiration section | "Be the team that..." |
| Confidence | CTA area | "Join 2,847 teams who already..." |
| Urgency | Near CTA | Only if genuine (real deadline, limited spots) |
Emotion techniques:
After this sweep: Return to Sweeps 5, 4, 3, 2, and 1.
Focus: Have we removed every barrier to action?
Friction checklist near CTAs:
After this sweep: Return through all previous sweeps one final time.
Always cut: very, really, extremely, incredibly, quite, rather, somewhat, just, actually, basically, essentially, literally (unless literal), in order to (use "to"), the fact that, it should be noted that, it is important to
Always replace:
| Weak | Strong |
|---|---|
| Utilize | Use |
| Implement | Set up, build, create |
| Leverage | Use, apply |
| Facilitate | Help, enable |
| Innovative | New, original, first-of-its-kind |
| Robust | Strong, thorough, [be specific] |
| Seamless | Smooth, easy, [be specific] |
| Cutting-edge | Modern, latest, [be specific] |
| Synergy | [Delete or be specific about the collaboration] |
| Paradigm | [Delete or say what actually changed] |
| Problem | Symptom | Fix |
|---|---|---|
| Wall of features | List of what it does, no why | Add "which means..." after each feature |
| Corporate speak | "Leverage synergies to optimize outcomes" | Ask "How would a human say this?" |
| Weak opening | Starts with company history or vague statement | Lead with reader's problem or desired outcome |
| Buried CTA | Ask comes after too much buildup | Make CTA obvious, early, and repeated |
| No proof | "Customers love us" with no evidence | Add specific testimonials, numbers, case references |
| Generic claims | "We help businesses grow" | Specify who, how, and by how much |
| Mixed audiences | Tries to speak to everyone | Pick one audience per page/section |
| Feature overload | Every capability listed | Focus on 3-5 benefits that matter most |
| Passive voice | "Reports are generated by the system" | "The system generates reports" |
| Weasel words | "Up to 50% improvement" | State the median or typical result with context |
| Decision | Option A | Option B | How to Decide |
|---|---|---|---|
| Oxford comma | Yes | No | Pick one, document it, enforce it |
| Heading capitalization | Sentence case | Title Case | Sentence case is modern standard |
| "Login" vs "Log in" | One word (noun) | Two words (verb) | "Log in" as verb, "Login" as noun/adjective |
| "Setup" vs "Set up" | One word (noun) | Two words (verb) | Same pattern as login |
| Ampersand vs "and" | & | and | "and" in prose, "&" only in headings if brand standard |
Edit in passes, not all at once — Trying to fix everything in one read misses issues. Each sweep catches what the others miss.
Preserve the author's voice — Good copy editing enhances; it does not replace. Maintain the original voice while improving clarity and impact.
Every edit needs a reason — Never change a word without explaining the principle. "Changed because it is clearer" or "Replaced because the original was vague."
Prioritize by conversion impact — Fix the CTA before fixing a comma. Fix the headline before fixing paragraph 12.
Read aloud — Voice and rhythm problems become obvious when read aloud. If it sounds wrong spoken, it reads wrong too.
Flag what you cannot fix — If a claim needs proof the author must provide, flag it clearly. You can improve phrasing but you cannot invent evidence.
Re-check previous sweeps — Each sweep can introduce issues caught by earlier sweeps. Always go back.
Cut first, add second — Most marketing copy is 20-30% too long. Cut the fat before adding new content.
Get context before editing — A copy edit without knowing the audience, goal, and voice standard produces misaligned feedback.
Track recurring issues — If the same problems appear across multiple pieces, the issue is systemic. Flag it as a process improvement, not just an edit.
| Problem | Likely Cause | Fix |
|---|---|---|
| Same issues appear across multiple pieces from the same writer | Systemic writing habit, not a one-off error | Create a writer-specific checklist of recurring issues; address in style guide or training, not just per-piece edits |
| Copy loses its original voice after editing | Editor over-corrected; replaced author voice with editor's style | Preserve author voice — enhance clarity and impact without rewriting personality. Read original aloud before editing |
| Edits introduce new inconsistencies | Previous sweeps not re-checked after later sweeps modified content | Always re-run earlier sweeps after making changes — Sweep 7 edits can break Sweep 1 clarity |
| CTA buried or ineffective despite multiple edit passes | CTA was not the focus of any sweep — copy editing focused on prose quality | Prioritize CTA area first (Sweep 7: Zero Risk) before polishing earlier sections |
| Fact-checking reveals unverifiable claims | Writer invented statistics or used outdated data | Flag and return to writer — editor cannot invent evidence. Document all unverifiable claims explicitly |
| Style inconsistencies between sections | Multiple writers contributed or copy was assembled from different drafts | Run style consistency checklist end-to-end; standardize contractions, heading case, number format, and punctuation |
In scope:
Out of scope:
Known limitations:
# Score content readability with detailed metrics
python scripts/readability_scorer.py article.md --json
# Detect AI patterns that need humanization before editing
python scripts/ai_pattern_detector.py article.md --verbose
# Check style consistency across multiple documents
python scripts/style_checker.py --files doc1.md doc2.md doc3.md --json© borghei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files (scripts) in marketing/copy-editing of borghei/Claude-Skills.
Open the folder on GitHubat commit c9a1487
Copy Editing next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Copy Editing this skillborghei/Claude-Skills | 874 | — | ~5.1k | Automated safety check: Pass | MIT | |
| User-Facing Text Cleanupguillaumemeyer/watermarks-remover | 23k | — | ~3.5k | Automated safety check: Pass | MIT | |
| Story Multi-Perspective Reviewzenstory-ai/oh-story-claudecode | 7.3k | 3 repos | ~3k | Automated safety check: Pass | MIT | |
| Chinese Text Humanizerop7418/Humanizer-zh | 19k | — | ~2k | Automated safety check: Pass | MIT | |
| Baoyu TranslateJimLiu/baoyu-skills | 26k | 1 repos | ~3.9k | Automated safety check: Pass | MIT | |
| Natural Japanese Business Writingcoji/natural-japanese | 1.9k | — | ~2.1k | Automated safety check: Pass | MIT |
guillaumemeyer/watermarks-remover
Audits prose for invisible Unicode characters and rewrites it while keeping facts, citations, code and required disclosures unchanged and the writer's voice intact.
zenstory-ai/oh-story-claudecode
Reviews Chinese web-novel text with several reviewer agents in parallel, falling back to a single-agent pass, and reports structure, character, prose and setting problems with fixes.
op7418/Humanizer-zh
Edits Chinese articles, comments and documents to remove filler, repetition and template phrasing while keeping the facts, the level of certainty and the author's voice.
JimLiu/baoyu-skills
Translates articles and files in quick, normal or refined mode, with a custom glossary, saved preferences and a review-and-polish workflow for publication quality.
coji/natural-japanese
Writes and edits Japanese business documents so they read clearly and naturally, removes AI-sounding phrasing and can score how AI-like a text reads.
lennney/stop-that-shit
Cuts defensive disclaimers, stacked hedging and self-protective narration from proposals and summaries, keeping only limits that affect the reader's decision.
borghei/Claude-Skills
Run delivery when AI coding and ops agents take tickets. An agent skill from borghei/Claude-Skills.
borghei/Claude-Skills
Check AI-generated marketing content and reviews for required disclosures under the EU AI Act, FTC rules and platform AI-label policies.
borghei/Claude-Skills
Idea to AI-generated prototype to customer validation to engineering handoff.
borghei/Claude-Skills
Analytics engineering across data modeling, dbt, transformation, and semantic layers.
borghei/Claude-Skills
Ansoff Matrix — 4-quadrant framework for growth options: market penetration, market/product development, and diversification.
borghei/Claude-Skills
OKR brainstorming and validation using the Radical Focus framework — outcome objectives, measurable key results, counter-metrics.
Categories
Systematic copy editing through focused passes (the Seven Sweeps Framework) covering clarity, voice, proof, specificity, and friction removal. Copy Editing is an agent skill from borghei/Claude-Skills. Systematic copy editing through focused passes (the Seven Sweeps Framework) covering clarity, voice, proof, specificity, and friction removal.
Copy Editing fits situations like: editing marketing copy; reviewing drafts; polishing content.
Run `npx skills add borghei/Claude-Skills --skill copy-editing -a claude-code`. Or copy the skill folder (marketing/copy-editing in borghei/Claude-Skills) into .claude/skills/copy-editing in your project. Claude Code loads it when a task matches its description.
Run `npx skills add borghei/Claude-Skills --skill copy-editing -a codex`. Or copy the skill folder (marketing/copy-editing in borghei/Claude-Skills) into .agents/skills/copy-editing in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add borghei/Claude-Skills --skill copy-editing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/copy-editing, .gemini/skills/copy-editing, .github/skills/copy-editing and .opencode/skills/copy-editing in your project.
Going by SKILL.md and its folder, Copy Editing needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Copy Editing is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.1k tokens (SKILL.md is roughly 20k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Copy Editing: User-Facing Text Cleanup (guillaumemeyer/watermarks-remover, 23k stars), Story Multi-Perspective Review (zenstory-ai/oh-story-claudecode, 7.3k stars), Chinese Text Humanizer (op7418/Humanizer-zh, 19k stars) and Baoyu Translate (JimLiu/baoyu-skills, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
borghei (a GitHub user) maintains it in borghei/Claude-Skills, which has 874 GitHub stars. The repository holds 364 skills in this directory. The repository was last updated on October 7, 2026.
Source: borghei/Claude-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.