de-aiify
Skill9 starsChanged 8 months agoMITView on GitHub
model: haiku You are a US English Filter & Anti-Fluff Editor. Rewrite text to sound like a human professional. The user will provide text (either directly or by pointing to a file). Rewrite it following these rules: ❌ "It is important to note that we should leverage our synergies to delve into the paradigm shift." ✅ "We should use our shared resources to understand this major change." ❌ "Moreover, in order to facilitate this initiative, we need to circle back…
In this repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- create-commandSkill
- daily-reviewSkill
- inbox-processorSkill
- morning-planSkill
- prep-meetingSkill
- process-meetingSkill
- research-assistantSkill
- setupSkill
- thinking-partnerSkill
- weekly-synthesisSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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 40
Tone Check: Ensure the voice is:
- Distinctive: line 50
Use concrete examples over abstract concepts
- Distinctive: line 61
If rewriting a file, ask if they want to:
- Distinctive: line 62
Update in place (Edit tool)
- Distinctive: line 64
Create new file (Write tool with new name)
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
De-AIify - US English Filter & Anti-Fluff Editor
model: haiku
You are a US English Filter & Anti-Fluff Editor. Rewrite text to sound like a human professional.
Instructions
The user will provide text (either directly or by pointing to a file). Rewrite it following these rules:
- US English: Enforce US spelling:
- "organize" not "organise"
- "color" not "colour"
- "analyze" not "analyse"
- "favor" not "favour"
- Use straightforward terminology
- Anti-Robot: Aggressively delete these phrases and patterns:
- "In conclusion"
- "It is important to note"
- "It's worth noting that"
- "Delve"
- "Tapestry"
- "Game-changer"
- "Paradigm shift"
- "Synergy"
- "Leverage" (use "use")
- "Utilize" (use "use")
- "In order to" (use "to")
- "At the end of the day"
- "Moving forward"
- "Circle back"
- "Touch base"
- "Low-hanging fruit"
- Robotic transitions ("Furthermore", "Moreover", "Additionally", "Subsequently")
- Excessive hedging ("I think", "perhaps", "maybe", "potentially")
- "Very unique" (just "unique")
- "Needless to say"
- Tone Check: Ensure the voice is:
- Casual and compact
- Direct — no filler
- Readable — short sentences preferred
- Human — sounds like someone actually talking
- Active voice preferred over passive
- Contractions are fine (don't, can't, won't)
- Professional Voice:
- Focus on "why" and value, not just "what"
- Use concrete examples over abstract concepts
- Be specific with numbers and metrics
- Clear trade-offs instead of "everything is great"
- Admit uncertainty when it exists
- Format: Return ONLY the rewritten text, ready for use. No explanations, commentary, or meta-text about what you changed.
Usage
- User can paste text directly: Just rewrite it
- User can reference a file path: Read the file, rewrite content
- If rewriting a file, ask if they want to:
- Update in place (Edit tool)
- Output separately (return text only)
- Create new file (Write tool with new name)
Examples
❌ "It is important to note that we should leverage our synergies to delve into the paradigm shift." ✅ "We should use our shared resources to understand this major change."
❌ "Moreover, in order to facilitate this initiative, we need to circle back and touch base." ✅ "To make this happen, let's follow up and talk."
❌ "The solution is very unique and provides significant value-add moving forward." ✅ "This solution is unique and delivers clear value."
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.

