← ClaudeAtlas

ccc-prompt-fixlisted

Fix and sharpen a prompt. Diagnoses it against the 6 prompt-quality patterns, returns a tightened rewrite with the reasoning, and suggests the right library prompt for your task.
KevinZai/commander · ★ 6 · AI & Automation · score 74
Install: claude install-skill KevinZai/commander
# $ccc-prompt-fix — Auto Prompt Fixer Take a rough prompt and hand back a sharper one — with the *why*, so you learn the pattern instead of just copying the fix. Grounded in the **Claude Code prompt library** (`skills/claude-code-library/`): 52 field-tested prompts + the 6 patterns behind all of them. > **This is a coach, not a black box.** Every rewrite names which pattern it applied, so the next prompt you write yourself is already better. ## Modes | You type | It does | |----------|---------| | `$ccc-prompt-fix <your prompt>` | **Fix** — diagnose + rewrite that prompt | | `$ccc-prompt-fix last` | Fix the **last prompt you sent** this session (read from the transcript) | | `$ccc-prompt-fix for <task>` | **Suggest** — pull the best matching prompt from the library for that task | | `$ccc-prompt-fix score <prompt>` | **Score** — rate 0–6 on the patterns, no rewrite (quick gut-check) | | `$ccc-prompt-fix` (no args) | Ask (via AskUserQuestion) which of the above you want | ## The rubric — the 6 patterns (from the library) Diagnose every prompt against these. A missing pattern is a fix opportunity; not every prompt needs all six, but each *absent* one is a question to ask. 1. **Outcome, not steps** — says *what*, lets Claude find the *how*. ❌ "open X, change Y, then Z" ✅ "add rate limiting to the public API; keep existing tests green" 2. **A way to check its own work** — includes run/test/compare/verify so it iterates instead of stopping at *looks done*. ✅ "write the migr