prompt-auditlisted

Audit a prompt the user is about to send to Claude (or another coding AI) for completeness and effectiveness. Use this skill whenever the user shares a prompt and asks for feedback — phrases like "is this prompt good", "audit my prompt", "review this prompt", "will Claude understand this", "improve this prompt", "is this enough context". Also trigger proactively when you notice the user is about to dispatch a vague, under-specified, or over-constrained prompt for non-trivial work. Checks the 6 essential elements (goal, scope, existing patterns, constraints, verification, done definition), flags what's missing, explains why each gap matters, and produces an improved rewrite. Treat this skill as the litmus test for "Be Claude's PM" — if the prompt fails the audit, the work that follows will probably fail too.
appleboy/skills · ★ 0 · AI & Automation · score 60

Install: claude install-skill appleboy/skills

# prompt-audit Most AI-coding failures trace back to thin prompts. A prompt that takes 30 seconds to write and 2 minutes for Claude to "execute" produces code that takes 2 hours to fix. This skill catches that before it happens. ## When to use Use whenever the user is evaluating, drafting, or about to send a prompt for non-trivial coding work. Triggers include: - "Is this prompt good?" - "Audit / review / check my prompt" - "Will Claude understand this?" - "How do I improve this prompt?" - The user pastes a prompt and asks anything about it - You notice the user is about to send a vague prompt for a complex task — proactively offer to audit it Don't audit: - Single-line throwaway prompts the user is happy with - Pure conversation / clarification messages (not actual task prompts) ## The six essential elements A good coding prompt for non-trivial work has all six. Missing any one drops the success rate noticeably. | # | Element | What it answers | Why it matters | |---|---|---|---| | 1 | **Goal** | What problem are we solving? Who uses the result? | Without a goal, Claude optimizes the wrong thing | | 2 | **Scope** | Which files / modules can change? Which can't? | Without scope, Claude touches things it shouldn't | | 3 | **Existing patterns** | What in the codebase should we mimic? | Without patterns, Claude reinvents conventions inconsistently | | 4 | **Constraints** | Performance, dependencies, compatibility | Without constraints, Claude makes choices the user won'