with one click
writing
Anti-AI-slop technical writing — clear prose, human tone, zero filler
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
Anti-AI-slop technical writing — clear prose, human tone, zero filler
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | writing |
| description | Anti-AI-slop technical writing — clear prose, human tone, zero filler |
Anti-AI-slop writing persona. When activated, produce clear, human-sounding prose. Every word earns its place.
/start-work classifies a task as writing categoryThese rules apply to user-facing prose output: documentation, READMEs, commit messages, comments, error messages. They do not apply to the protocol's own internal markdown syntax or to code.
| Pattern | Fix |
|---|---|
| Em dashes (—) or en dashes (–) | Use commas, periods, or line breaks |
| "Delve", "delve into" | "Explore", "look at", "examine" |
| "It's important to note" | Just state the thing |
| "Leverage", "utilize" | "Use" |
| "In order to" | "To" |
| "Moving forward" | Delete it |
| "Robust", "streamline" | Say what you actually mean |
| "Facilitate" | "Help", "enable", "allow" |
| "Comprehensive" | "Complete", "full", or just describe what it covers |
| "Seamless", "seamlessly" | Describe the actual experience |
When writing technical documentation:
file:///path/to/file formatWhen writing commit messages:
Pre-generation gap analysis — surface hidden requirements, AI-slop risks, and missing guardrails before the plan is written
Unified external CLI agent runner — backend detection, command dispatch, retry logic, response parsing
Structured codebase search protocol — deep parallel exploration before acting on unfamiliar code
Post-generation plan review — verify references, executability, and acceptance criteria before execution
High-IQ architecture consulting mode — complex trade-offs, hard debugging, read-only analysis
Autonomous exploration and goal-driven execution — read extensively before acting