writing-humanity-pass
Skill2 starsChanged 7 months agoNo licenceView on GitHub
Remove the documented "Signs of AI writing" from a draft and rebuild human texture, calibrated to Sean's voice. Auto-detects voice-bearing vs neutral text and scrubs accordingly. Cuts em dashes, significance inflation, -ing padding, copula avoidance, chatbot artifacts, filler, hedging, and 24 more tells. Pairs with writing-voice-modes (runs as the final pass after a voice write) and runs standalone. Use when asked to "scrub the AI out of this", "make this less AI", "de-slop this draft", "humanize this", "this sounds like AI", "remove AI tells", or when reviewing any draft (yours or agent-generated) that reads like a machine.
In this repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- 2d-animation-principlesSkill
- animation-pipelineSkill
- art-departmentSkill
- artdept-interrogateSkill
- artdept-synthesizeSkill
- brainstorm-front-doorSkill
- comfyui-workflowsSkill
- creative-directorSkill
- frontdoor-interrogateSkill
- frontdoor-synthesizeSkill
- gemini-image-genSkill
- gemini-pencil-animation-image-genSkill
- image-generator-prompt-scienceSkill
- impeccableSkill
- openai-image-genSkill
- prompt-engineeringSkill
- prompt-how-muchSkill
- prompting-beautiful-uiSkill
- screenwriting-modesSkill
- script-writingSkill
- skill-system-masterySkill
- storytelling-architectureSkill
- video-animation-productionSkill
- visual-polish-checklistSkill
- writing-critiqueSkill
- writing-voice-modesSkill
- wwf5dSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “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.
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.

