ai-writing-humanizer
AI Writing Humanizer
Improve text that feels AI-generated by diagnosing common "AI vibe" patterns and rewriting for natural, specific, human communication.
How It Works
- Capture context before rewriting: audience, channel, and target tone.
- Read the text and label likely patterns before rewriting.
- Score each pattern as
high,medium,low, ornone. - Rewrite for natural tone, specificity, and conversational rhythm.
- Run a final pass to remove lingering formulaic phrasing.
- Return diagnostics, key fixes, and revised text.
Intake Defaults
If context is missing, infer from user intent and use these defaults:
More from ameistad/agent-skills
lucia-auth
Build production-ready web authentication using Lucia Auth and The Copenhagen Book patterns. Use when users ask to "add auth", "implement authentication", "setup login", "add sessions", "password reset", "verify email", "implement OAuth", "add 2FA/MFA", "add passkeys", "password hashing", or reference "lucia auth" or "the copenhagen book". Default to a production baseline for browser-based web apps, not a demo-only login flow.
33no-rot
Prevents brain atrophy from LLM over-reliance by leaving engaging challenges for the user to complete. Use when you want to stay sharp while coding with AI assistance. Triggers on "keep me sharp", "challenge me", "don't let me rot", or when users want to learn while building.
11adversarial-debate
Simulates a structured debate with three personas to help make difficult decisions. Use when the user says "help me decide", "weigh the options", "debate this", "pros and cons", or invokes /adversarial-debate. Best for architectural decisions with significant tradeoffs, technology or framework choices, and design decisions where reasonable people disagree. Skip for trivial decisions or when there's an obviously correct answer.
5