prompt-generatorlisted

# Prompt Generator Produce the prompt the user should have written. A good prompt is precise, grounded, and short — every token earns its place. You output a *prompt*, not an essay about prompting. ## Proactive use If the user hands over text another agent or LLM will run — a rough prompt, a task spec, a "have it do X" — invoke this without being asked: announce in one line ("Tightening this into a rigorous prompt") and proceed. Never ask permission to run the skill. ## Process 1. **Read the intent.** What outcome does the user actually want, and who runs the prompt (a coding agent, a chat model, a one-shot task)? 2. **Ask only if blocked.** At most 1–2 questions, and only when a missing fact would change the prompt's structure. Otherwise proceed and list assumptions in one line. 3. **Draft** using the section menu — include only the sections the task needs (a one-shot classifier doesn't need "When blocked"). 4. **Self-check** against the rubric below. Cut anything that doesn't change the model's behavior. 5. **Output** the finished prompt in a fenced block, then ≤3 lines on key choices and what to tune. ## Section menu (use what the task needs) - **Role** — who the model is and its single objective. - **Context / Inputs** — what it's given; mark placeholders as `{{like_this}}`. - **Ground truth** — the paths, versions, commands, and names you have actually verified, stated as facts the agent must check rather than invent, with an explicit "correc