research-brief

research-brief

You need to compare a few options and hand someone a decision, not a pile of tabs.

When to use

• You're choosing between a few options and someone needs the decision, not your browser history.
• You keep comparing things ad hoc and want the same shape every time so they're easy to revisit.
• A casual "which is better?" actually deserves criteria, trade-offs, and a recommendation.

Prompt template

Goal: compare X and Y for <decision>. Give me a comparative brief with a recommendation.

What you get back

A short comparative brief: the question stated up front, the options scored on one like-for-like set of criteria, the trade-offs called out, and a recommendation with its main risk — structured the same way every time so two briefs read side by side.

Method

The generalised discipline:

1. State the question first — the decision the brief has to serve.
2. One criteria set, applied to every option — no per-option special pleading.
3. Name the trade-off explicitly — what you give up, not just what you gain.
4. Recommend, with the main risk — a brief that won't commit isn't done.

Verify it's working

Confirm the skill actually fires — in your own session, on your own data. No data leaves your machine.

1. Does it fire? Paste the prompt in demo-input.md. You should get the shape shown in expected-output.md.

2. On your data. Run it on your real input.

3. Confirm the shape. Save the output to a file and run:

   node ${CLAUDE_SKILL_DIR}/scripts/check.mjs <your-output-file>
   

   It reports ENGAGED when the output carries this skill's characteristic structure — the deterministic sign it fired. It checks shape, not quality; judge the content yourself.

The check runs entirely locally — nothing leaves your machine. If you want to add to the public "confirmed working" count, opt in explicitly:

node ${CLAUDE_SKILL_DIR}/scripts/check.mjs <your-output-file> --report https://skills-field-guide-proxy.nesper6311.workers.dev --skill research-brief

That sends only an anonymous +1 — never your input, output, or identity.

---

Installed from the public field guide. Customize freely — this is a starting point built from the published projection of research-brief.