natural-writing

Solid

Use when drafting, editing, or reviewing flat, robotic, disconnected, repetitive, performative, overwritten, or overly harsh prose, especially in emails, feedback, criticism, and negotiation.

Code & Development 42 stars 5 forks Updated 5 days ago MIT

Install

View on GitHub

Quality Score: 83/100

Stars 20%
54
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Natural Writing ## Core principle Write like a thoughtful person speaking: connect related ideas; preserve meaning and voice, not punctuation or clause inventory. ### Prefer literal language when it is clearer Remove mannered prose: metaphor or flourish that replaces a clearer literal statement. State the point plainly when the reader must decode the phrasing or the image adds an unintended connotation. Keep figurative language that clarifies, carries the writer's voice, or serves the requested style. ### Attach conditions to their outcome Put conditions and their outcome or decision in one sentence. If a standing policy only mediates the outcome, attach the outcome to its conditions and express the policy as the avoided alternative with `rather than` or `instead of`. Keep it separate when announcing, defending, or changing it is the point. Do not fuse unrelated events, next steps, or deliberate formality. ### Preserve material meaning Preserve facts, commitments, boundaries, requests, numbers, tense, uncertainty, perspective, and tone. A detail is material when removing it changes what the reader believes or does. ## Method 1. Identify reader, purpose, action, and register. 2. Map qualification, contrast, cause, outcome, shared history, consequence, and next step. 3. Rebuild complete spoken thoughts: - Keep qualifications and contrasts with what they change. - Group alternative causes with `or` and carry them into their shared outcome. - Start a new se...

Details

Author
mike-coulbourn
Repository
mike-coulbourn/claude-vibes
Created
9 months ago
Last Updated
5 days ago
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category