agentleFS
sd0xdevsd0xdev/sd0x-dev-flow/skills/de-ai-flavor/SKILL.md

de-ai-flavor

Skill192 starsChanged 37 days agoMITView on GitHub

Remove AI artifacts from documents. Use when: cleaning AI-generated text, removing tool names, fixing boilerplate patterns. Not for: doc review (use doc-review), doc refactoring (use doc-refactor). Output: cleaned document preserving original intent.

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are 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.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All tool names removed

    line 47

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

De-AI-Flavor Skill

Trigger

  • Keywords: de-ai, remove AI traces, humanize document, de-ai-flavor, humanize

When NOT to Use

  • Co-Authored-By in CHANGELOG (Git convention)
  • Documents discussing AI technology (topic itself requires it)
  • Quoting others' AI-related content
  • Variable/function names in code

Usage

/de-ai-flavor docs/xxx.md           # Process specified file
/de-ai-flavor docs/                 # Process all .md in directory
/de-ai-flavor                       # Process .md in git diff

Detection Rules

TypePatternAction
Tool namesClaude/Codex/GPT/AI assistantRemove
Boilerplate"Let me...", "First...then...", "In conclusion"Rewrite
Over-structuringOne sentence per heading, too many #### levelsSimplify
Service tone"Hope this helps", "If you have questions..."Remove
Self-description"Next I will...", "I will proceed to..."Remove
Iteration leaks"Round 1/Round 2/Round N"Rewrite

Workflow

Scan file -> Mark AI traces -> Remove/Rewrite/Simplify -> Output summary

Verification

  • All tool names removed
  • Boilerplate rewritten to natural tone
  • Structure not overly flat or nested

Output Format

## De-AI-Flavor Results

**File**: `docs/xxx.md`

| Line | Original              | Change                  | Reason           |
| ---- | --------------------- | ----------------------- | ---------------- |
| 15   | Let me explain...     | Removed                 | AI self-description |
| 32   | Claude suggests...    | Changed to "Suggest..." | Tool name        |

**Stats**: Removed 3 tool names | Rewrote 5 boilerplate | Simplified 2 structures

Examples

Input: /de-ai-flavor docs/tech-spec.md
Action: Scan -> Remove "Claude suggests" -> Rewrite "Let me explain" -> Output summary
Input: This document feels very AI-generated, please clean it up
Action: Detect git diff -> Mark AI traces -> Batch process -> Output stats

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.