Agent skill
de-ai-ify
Rewrite AI-generated text to sound natural and human-written
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/de-ai-ify-davidroliverba-architectkb
SKILL.md
/de-ai-ify
Strip AI-sounding patterns from generated text and rewrite to be natural, direct, and human.
Usage
/de-ai-ify <note path> # Rewrite a specific note
/de-ai-ify --section <heading> # Rewrite only a specific section
/de-ai-ify --clipboard # Rewrite text from clipboard context
Instructions
-
Read the target note or receive the text to rewrite
-
Identify AI patterns — flag any of the following:
Filler phrases to remove:
- "Let's dive into...", "Let's explore..."
- "I'd be happy to..."
- "It's worth noting that..."
- "It's important to understand..."
- "In today's rapidly evolving..."
- "This is a great question"
- "As we can see..."
- "Moving forward..."
Hedging to reduce:
- "It could potentially..." → state directly or remove
- "This might suggest..." → "This suggests..." or cut
- "It's possible that..." → state the thing or qualify once
- Stacking qualifiers: "perhaps", "maybe", "somewhat", "arguably"
Structural patterns to fix:
- Excessive bullet points where prose would be clearer
- Every paragraph opening with a transition word
- Formulaic "In conclusion..." / "To summarise..." wrap-ups
- Numbered lists for things that aren't sequential
- Restating the question before answering it
Tone patterns to adjust:
- Overly enthusiastic ("fantastic", "incredible", "amazing")
- Corporate-bland ("leverage", "synergise", "drive value")
- Sycophantic agreement before every response
-
Rewrite the flagged sections:
- Keep the author's intent and meaning
- Use active voice, concrete language
- Prefer shorter sentences
- Let the content speak — cut throat-clearing
- Preserve any technical accuracy and wiki-links
- Maintain frontmatter unchanged
-
Show the diff — present before/after for each changed section so the user can review
-
Apply changes only after user confirms
Guidelines
- Do NOT change frontmatter, wiki-links, or Dataview queries
- Do NOT remove content — only rephrase
- Do NOT add new content or expand the text
- Preserve the author's voice where it comes through
- When in doubt, cut rather than rephrase
- UK English throughout
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?