prompt-reviewerlisted

Review and refine prompts to improve clarity, specificity, token efficiency, and missing context. Use this skill whenever the user hands you a prompt as an artifact and asks for feedback — regardless of the target model (Claude, ChatGPT, Midjourney, system prompts, etc.). Trigger when the user says "review this prompt", "improve my prompt", "refine this prompt", "make this prompt better", "is this prompt clear", "check this system prompt", "optimize this prompt", "fix my prompt", "critique this prompt", or any similar phrasing where a prompt is the subject of review rather than the instruction itself. Supports three modes: default (single-pass), --deep (guided dialogue), --variants (three rewrites). Also trigger when the user uses "--deep" or "--variants" flags alongside a prompt.
jzills/Claude-Marketplace · ★ 0 · AI & Automation · score 63

Install: claude install-skill jzills/Claude-Marketplace

# Prompt Reviewer This skill reviews prompts as artifacts — whether written for Claude, ChatGPT, Midjourney, system prompts, or any other AI tool — and returns an improved version. Three modes are available: - **Default** (no flag): single-pass analysis + one optimized rewrite - **`--deep`**: guided dialogue to understand context before refining - **`--variants`**: generates three rewrites with different trade-offs --- ## Step 1: Detect Mode Check whether the user included a flag: - No flag → run **Default mode** - `--deep` present → run **Deep mode** - `--variants` present → run **Variants mode** - No prompt provided → ask: "Please share the prompt you'd like me to review." If no flag is present and the prompt is longer than ~200 words or is clearly a multi-part system prompt, suggest `--deep` before proceeding: > "This looks like a complex prompt — I can run `--deep` for a guided review that asks about your intent and constraints first. Want that, or should I proceed with the default single-pass review?" If the user does not explicitly confirm `--deep`, proceed with Default mode. --- ## Default Mode Analyze the prompt across five dimensions. For each, give a one-line finding: mark ✓ (no issue) or describe the specific problem. | Dimension | What to check | |-----------|--------------| | **Clarity** | Is the intent unambiguous? Could it be misread? | | **Specificity** | Are there vague terms (e.g., "good", "helpful", "brief") that should be made precise? | | **T