| name | prompt |
| description | Use when a request aimed at an AI is vague, rushed, or under-specified and the user wants it sharpened — "improve my prompt", "fix this prompt", "how should I ask for this" — or before firing an expensive task off a thin prompt. About prompts for an AI, not about optimizing code. |
MasterMind — Prompt
The single biggest lever on AI output quality is the prompt. Most weak results aren't a model failure —
they're an under-specified request. This skill rewrites a user's rough ask into a prompt an AI will
execute well: clear intent, only the context that matters, structured, and token-efficient. Grounded in
Anthropic's prompt-engineering guidance (~/.mastermind/engineering/core/agent-loop.md, product-sense.md).
First: get the real intent
If the goal is ambiguous, ask one or two sharp questions before rewriting — the rewrite carries only
requirements the user actually implied. You sharpen their intent; it stays theirs.
The rewrite checklist (apply what fits — keep it lean)
- Lead with the task. State the goal in the first line, plainly. Treat the AI like a sharp new
hire: say exactly what "done" looks like.
- Give load-bearing context only — the why, the audience, the stack/constraints, what already
exists. Cut backstory that doesn't change the output.
- Be explicit and concrete. Replace vague adjectives ("nice", "modern", "clean") with specifics
(what, for whom, which constraints, which examples to match).
- Structure it. Separate the parts —
context / task / requirements / output format —
with headings or XML-ish tags (<context>…</context>) so the model can parse roles of text.
- Show an example, not just a description. Add one short example of the desired output (or a
reference to match) when words alone are ambiguous — few-shot beats adjectives.
- Set the role when it sharpens tone/expertise ("You are a senior accessibility engineer…").
- Pin the output contract — format, length, what to include/exclude, and any must-nots.
- Ask for reasoning on hard/analytical tasks ("think step by step before answering").
Token efficiency (efficient ≠ lossy)
Cut politeness padding, redundancy, and repeated context; compress prose to bullets; keep every
detail that changes the output and no more. Fewer tokens and a sharper signal — not a shorter prompt
that drops requirements.
Output
Return, in this order:
- The optimized prompt — ready to paste, in a copyable block.
- What changed & why — 2–4 bullets (e.g. "added output format; cut 3 lines of backstory; made
'fast' concrete = <2.5s LCP").
- Open questions — anything still genuinely ambiguous the user should decide.
Flag any change of scope out loud. If the request implies a product/business decision, surface it rather
than guessing (product-sense.md).
