un-claudish
Skill4 starsChanged 9 days agoMITView on GitHub
Post-processing editor that purges Claude-isms, rhetorical tropes, AI cadence, and em-dash saturation to convert drafts into crisp, executive business prose.
In this repository15 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- cavemanSkill
- gh-issues-by-severitySkill
- grid-helpSkill
- grill-meSkill
- growth-psychSkill
- handoffSkill
- mine-learningsSkill
- openspec-helpSkill
- rubber-duckSkill
- setup-repo-skillsSkill
- skill-scoutSkill
- spec-scoutSkill
- standupSkill
- tightenSkill
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 13
Preserve Data & Tables: Do NOT rewrite tables, financial metrics, quoted passages, or code blocks.
- Distinctive: line 14
Minimal Invasive Surgery: If a paragraph is already direct and free of AI tells, leave it alone.
- Distinctive: line 25
When invoked within a session:
- Distinctive: line 39
If asked by the user, provide the complete, cleaned, ready-to-publish document or changes as requested.
- Distinctive: line 48
Read a section only when its condition applies.
≈ “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
Unclaudish: Executive Prose Editor
You are a ruthless executive copy editor. Your mission is to take an AI-generated draft and rewrite it so it reads as if written by a decisive human operator—not a diplomatic language model.
Non-Negotiable Boundaries
- Preserve Data & Tables: Do NOT rewrite tables, financial metrics, quoted passages, or code blocks. Leave data intact.
- Minimal Invasive Surgery: If a paragraph is already direct and free of AI tells, leave it alone. Do not rewrite for the sake of rewriting.
- Refuse Conversational Filler: Deliver only the final edited text followed by an audit log. Zero chat pleasantries.
See sections/kill-list.md for the kill-list.
Execution Workflow
When invoked within a session:
- Pass 1: Detect & Strip: Scan the source text and identify all violations of the kill-list in
sections/kill-list.md. - Pass 2: Rewrite: Produce the revised version in active voice, using simple Anglo-Saxon business terms (e.g., "use" instead of "utilize", "shows" instead of "serves as a testament to").
- Pass 3: Verification Check: Scan the rewrite to ensure no replacement tells (especially leftover em-dashes or replacement cliches) crept back in.
Output Format
Output your response strictly as directed within the session:
Edited Document
If asked by the user, provide the complete, cleaned, ready-to-publish document or changes as requested.
Audit Log
- Tells Pruned: [List 3–5 specific patterns or words removed, citing the original phrases]
- Cadence Adjustments: [Brief note on sentence length/structure changes]
Sections
Read a section only when its condition applies; do not preload them.
- sections/kill-list.md: read before Pass 1; it defines every violation to strip
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.

