simple-text-cleanup
Skill1 starsChanged 43 days agoMITView on GitHub
Clean up text punctuation and readability, such as semicolons, long dashes, ranges, brackets, overloaded sentences, and ellipsis. Use when the user asks to clean up or tidy text, or as the final pass of simple-chinese and simple-cantonese.
In this repository15 other files it gives its agents.
- simple-cantoneseSkill
- simple-checkSkill
- simple-chineseSkill
- simple-cloudflareSkill
- simple-code-reviewSkill
- simple-commitSkill
- simple-debugSkill
- simple-full-refactorSkill
- simple-launchSkill
- simple-orchestratorSkill
- simple-readmeSkill
- simple-refactorSkill
- simple-releaseSkill
- simple-restructureSkill
- simple-supabaseSkill
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 11 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Use a comma when the sentence is short or flows better with one
- Distinctive: line 18
Use a full stop when the sentence is long or has multiple clauses
- Distinctive: line 19
Remove long dashes used as sentence connectors
- Distinctive: line 20
Keep a long dash only as a placeholder glyph for unavailable values
- Distinctive: line 23
Avoid brackets for extra info
- Distinctive: line 26
Leave short or simple sentences alone
- Distinctive: line 27
Do not turn many short sentences into hard stops when a comma reads better
- Distinctive: line 29
Do not use the middle dot character ·
- Distinctive: line 32
Remove decorative emojis in headings and bullets, keep them only when the source clearly uses them on purpose
- Distinctive: line 33
Remove excessive bold and italics, keep them only for real emphasis
- Distinctive: line 34
Remove invisible characters such as zero-width spaces and non-breaking spaces, and collapse double spaces
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Simple Text Cleanup
Clean the given text with the rules below. Keep the meaning, tone, and wording as they are. Only change what a rule requires.
Rules
- Remove all semicolons
- Use a comma when the sentence is short or flows better with one
- Use a full stop when the sentence is long or has multiple clauses
- Remove long dashes used as sentence connectors
- Keep a long dash only as a placeholder glyph for unavailable values
- Hyphens are a separate character, never convert them to or from long dashes
- Replace a long dash in numeric ranges with space hyphen space, such as 8 - 10
- Avoid brackets for extra info
- Work the info into the sentence, or omit it if not essential
- Split a sentence only when it stacks too many clauses
- Leave short or simple sentences alone
- Do not turn many short sentences into hard stops when a comma reads better
- Replace the ellipsis character … with three dots ...
- Do not use the middle dot character ·
- Replace curly quotes with straight quotes in English text
- Replace arrows like → in prose with words, keep them only in diagrams or code
- Remove decorative emojis in headings and bullets, keep them only when the source clearly uses them on purpose
- Remove excessive bold and italics, keep them only for real emphasis
- Remove invisible characters such as zero-width spaces and non-breaking spaces, and collapse double spaces
Do not touch
Code, URLs, file paths, and quoted text.
Output
Return the cleaned text only. If a change is a judgment call, or you are unsure, list it as a suggested edit instead of applying it, and let the user decide.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.