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.
Proofread and lightly edit sorg Markdown content before publication.
Install Proofread Content
$ npx skills add brandur/sorg --skill proofread-content -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install brandur/sorg proofread-content --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/brandur/sorg.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/proofread-content .claude/skills/proofread-content && 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 "proofread-content" agent skill from https://github.com/brandur/sorg/tree/master/.codex/skills/proofread-content into .claude/skills/proofread-content/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proofread-content", 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/brandur/sorg/tree/master/.codex/skills/proofread-contentType 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 brandur/sorg --skill proofread-content -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install brandur/sorg proofread-content --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brandur/sorg.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.codex/skills/proofread-content .agents/skills/proofread-content && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "proofread-content" agent skill from https://github.com/brandur/sorg/tree/master/.codex/skills/proofread-content into .agents/skills/proofread-content/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proofread-content", 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 brandur/sorg --skill proofread-content -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install brandur/sorg proofread-content --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brandur/sorg.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.codex/skills/proofread-content .cursor/skills/proofread-content && 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 "proofread-content" agent skill from https://github.com/brandur/sorg/tree/master/.codex/skills/proofread-content into .cursor/skills/proofread-content/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proofread-content", 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/brandur/sorg.git --path .codex/skills/proofread-content--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 brandur/sorg --skill proofread-content -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install brandur/sorg proofread-content --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brandur/sorg.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.codex/skills/proofread-content .gemini/skills/proofread-content && 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 "proofread-content" agent skill from https://github.com/brandur/sorg/tree/master/.codex/skills/proofread-content into .gemini/skills/proofread-content/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proofread-content", 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 brandur/sorg proofread-contentInstalls 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 brandur/sorg --skill proofread-content -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/brandur/sorg.git skills-src && mkdir -p .github/skills && cp -r skills-src/.codex/skills/proofread-content .github/skills/proofread-content && 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 "proofread-content" agent skill from https://github.com/brandur/sorg/tree/master/.codex/skills/proofread-content into .github/skills/proofread-content/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proofread-content", 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 brandur/sorg --skill proofread-content -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install brandur/sorg proofread-content --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brandur/sorg.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.codex/skills/proofread-content .opencode/skills/proofread-content && 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 "proofread-content" agent skill from https://github.com/brandur/sorg/tree/master/.codex/skills/proofread-content into .opencode/skills/proofread-content/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proofread-content", 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.
Facts
- Skill name
proofread-content- GitHub stars
- 525
- Token cost
- ~571 tokens
- SKILL.md length
- 252 words
- Files
- 3 (incl. scripts)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Proofread and lightly edit sorg Markdown content before publication.
- Works in 6 steps: Read the requested file before editing. → Preserve frontmatter, Markdown links,… → Make direct edits only for clear… → …
- The user passes a content file path such as content/nanoglyphs/052-adrift.md
- SKILL.md covers Workflow, Repeated Words, Proofreading Pass and Output
- Runs Python scripts from its folder; calls python3
What it does
Proofread Content is an agent skill from brandur/sorg. Proofread and lightly edit sorg Markdown content before publication. Use when the user passes a content file path such as content/nanoglyphs/052-adrift.md, content/articles/.md, content/fragments/.md, or another prose-heavy Markdown file and asks for a proofread, spelling/grammar check, minor editorial pass, repeated-word scan, or publication readiness review.
Its SKILL.md is about 570 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `agents/openai.yaml` and `scripts/repetition_scan.py`).
It sits in Writing & Content, covering Copy editing and proofreading. The repository describes itself as: A Go-based static site generator that compiles brandur.org. The licence is MIT.
When your agent uses it
- The user passes a content file path such as content/nanoglyphs/052-adrift.md
- Content/articles/.md
- Content/fragments/.md
- Another prose-heavy Markdown file and asks for a proofread
Example prompts
- “/proofread-content”
Requirements
- Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Read the requested file before editing.
- Preserve frontmatter, Markdown links, image tags, headings, anchors, block quotes, and HTML unless they contain a clear typo.
- Make direct edits only for clear spelling, grammar, punctuation, duplicated-word, or typo fixes.
- Keep the author's voice, cadence, humor, contractions, and first-person perspective intact.
- Do not rewrite paragraphs, change claims, normalize style, or fact-check unless the user explicitly asks.
- For subjective wording improvements, report suggestions instead of applying them.
What it can do on your machine
Read from SKILL.md and the folder at commit 3f7daa8. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Proofread Content loads about 571 tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 252 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.
Safety
Auto-check passed
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.
SKILL.md
The full file from brandur/sorg at commit 3f7daa8, republished under its MIT licence (© brandur). 252 words, ~571 tokens.
Download SKILL.mdSave it as
.claude/skills/proofread-content/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- proofread-content
- description
- Proofread and lightly edit sorg Markdown content before publication. Use when the user passes a content file path such as content/nanoglyphs/052-adrift.md, content/articles/*.md, content/fragments/*.md, or another prose-heavy Markdown file and asks for a proofread, spelling/grammar check, minor editorial pass, repeated-word scan, or publication readiness review.
Proofread Content
Workflow
- Read the requested file before editing.
- Preserve frontmatter, Markdown links, image tags, headings, anchors, block quotes, and HTML unless they contain a clear typo.
- Make direct edits only for clear spelling, grammar, punctuation, duplicated-word, or typo fixes.
- Keep the author's voice, cadence, humor, contractions, and first-person perspective intact.
- Do not rewrite paragraphs, change claims, normalize style, or fact-check unless the user explicitly asks.
- For subjective wording improvements, report suggestions instead of applying them.
Repeated Words
Run the bundled scanner against the file:
python3 .codex/skills/proofread-content/scripts/repetition_scan.py <path>Use the scanner output as leads, not as automatic edits. Ignore repeated terms when repetition is intentional, structural, technical, quoted, part of a name/title, or separated by enough context that it reads naturally.
For awkward clusters, suggest specific alternatives that fit the local sentence. Prefer small substitutions over sentence rewrites.
Proofreading Pass
Check the body prose for:
- misspellings and homophones
- subject/verb agreement
- missing or doubled words
- punctuation mistakes
- malformed Markdown links
- obvious typographic inconsistencies
- awkward repeated words in nearby sentences
Treat TOML frontmatter as metadata. Fix obvious typos in human-facing values like title, hook, and image_alt, but do not reformat metadata or change dates, paths, slugs, or image URLs.
Output
When edits are made, summarize them briefly and mention the file path. Include any remaining optional editorial suggestions separately.
When no direct edits are safe, say so and provide a concise list of suggested changes with enough context to find them.
Do not paste the full article back to the user.
© brandur, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (scripts) in .codex/skills/proofread-content of brandur/sorg.
- SKILL.md
- agents/openai.yaml
- scripts/repetition_scan.py
Open the folder on GitHubat commit 3f7daa8
Compare with similar skills
Proofread Content 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 |
|---|---|---|---|---|---|---|
| Proofread Content this skillbrandur/sorg | 525 | — | ~571 | Automated safety check: Pass | MIT | |
| User-Facing Text Cleanupguillaumemeyer/watermarks-remover | 24k | — | ~3.5k | Automated safety check: Pass | MIT | |
| Story Multi-Perspective Reviewzenstory-ai/oh-story-claudecode | 7.4k | 3 repos | ~3k | Automated safety check: Pass | MIT | |
| Chinese Text Humanizerop7418/Humanizer-zh | 19k | — | ~2k | Automated safety check: Pass | MIT | |
| Korean AI-Text Humanizerepoko77-ai/im-not-ai | 5.9k | 1 repos | ~4.5k | Automated safety check: Pass | MIT | |
| Natural Japanese Business Writingcoji/natural-japanese | 1.9k | — | ~2.1k | Automated safety check: Pass | MIT |
Similar skills
Story Multi-Perspective Review
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.
Chinese Text Humanizer
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.
Korean AI-Text Humanizer
epoko77-ai/im-not-ai
Rewrites Korean text written by AI so it reads like a human wrote it, detecting translationese and other AI patterns while leaving the content untouched.
Natural Japanese Business Writing
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.
Defensive Writing Editor
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.
Related
Categories
Questions about Proofread Content
What does Proofread Content do?
Proofread and lightly edit sorg Markdown content before publication. Proofread Content is an agent skill from brandur/sorg. Proofread and lightly edit sorg Markdown content before publication.
When should I use Proofread Content?
Proofread Content fits situations like: the user passes a content file path such as content/nanoglyphs/052-adrift.md; content/articles/.md; content/fragments/.md; another prose-heavy Markdown file and asks for a proofread.
How do I install Proofread Content in Claude Code?
Run `npx skills add brandur/sorg --skill proofread-content -a claude-code`. Or copy the skill folder (.codex/skills/proofread-content in brandur/sorg) into .claude/skills/proofread-content in your project. Claude Code loads it when a task matches its description.
How do I install Proofread Content in Codex?
Run `npx skills add brandur/sorg --skill proofread-content -a codex`. Or copy the skill folder (.codex/skills/proofread-content in brandur/sorg) into .agents/skills/proofread-content in your project. Codex loads it when a task matches its description.
Can I use Proofread Content in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add brandur/sorg --skill proofread-content -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/proofread-content, .gemini/skills/proofread-content, .github/skills/proofread-content and .opencode/skills/proofread-content in your project.
What does Proofread Content need to run?
Going by SKILL.md and its folder, Proofread Content needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Proofread Content access the network?
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.
Is Proofread Content safe to install?
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.
What licence does Proofread Content use?
Proofread Content is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Proofread Content use?
About 571 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Proofread Content?
Skills that share tags, products or a category with Proofread Content: User-Facing Text Cleanup (guillaumemeyer/watermarks-remover, 24k stars), Story Multi-Perspective Review (zenstory-ai/oh-story-claudecode, 7.4k stars), Chinese Text Humanizer (op7418/Humanizer-zh, 19k stars) and Korean AI-Text Humanizer (epoko77-ai/im-not-ai, 5.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Proofread Content?
brandur (a GitHub user) maintains it in brandur/sorg, which has 525 GitHub stars. The repository was last updated on September 17, 2026.
Source: brandur/sorg on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.