prompt-optimizelisted

# /prompt-optimize — Optimize a Prompt for DQIII8/Pipeline Analyze and optimize a prompt for maximum effectiveness in the DQIII8 ecosystem (LLM routing, scene director, TTS, Telegram bot, or agent instructions). ## Usage ``` /prompt-optimize [the prompt text or file path] ``` ## Your Task Given the prompt in `$ARGUMENTS`: ### 1. Classify the prompt type - **LLM routing prompt** (sent to Ollama/Groq/Claude) - **Image generation prompt** (sent to fal.ai flux-general) - **TTS prompt** (narration text for ElevenLabs) - **Agent instruction** (agent .md system prompt) - **Telegram bot message** (user-facing output) ### 2. Evaluate on 5 dimensions (score 0-10 each) | Dimension | What to check | |-----------|---------------| | **Clarity** | Unambiguous intent, no vague instructions | | **Specificity** | Concrete examples, exact formats, numbers | | **Conciseness** | No filler words, no redundant instructions | | **Output contract** | Explicit format (JSON/markdown/text) stated | | **Edge cases** | Handles empty input, failure, ambiguity | ### 3. Produce optimized version Apply these DQIII8-specific improvements: **For LLM prompts:** - Add `Output ONLY JSON (no markdown):` if structured output needed - Include exact field names in the output contract - State the model tier this will run on (Haiku/Sonnet/Groq) **For image prompts (fal.ai):** - Lead with cinematographer style reference - Include shot_type + camera_angle early in the prompt - End with `no text no watermarks