Self-contained research brief

Writes one self-contained research brief for a human or AI researcher so the next research pass can produce decision-ready, source-backed findings.

Collect Context

State Situation

Define Question

Add Sub-questions

Rule 01

A good research prompt is self-contained enough to hand off without a follow-up exchange.

Rule 02

The research question must map to a decision; otherwise the researcher cannot prioritize evidence.

Rule 03

Primary sources beat forums and social posts; weak signals must not become factual proof.

Rule 04

The brief must force source URLs, specific claims, decision relevance, contradiction handling, and a gap round.

Core lanes from input to output, aligned with the command's real execution path.

Start

Input, scope, route

1 Collect Context Gather the decision, audience, deadline, known facts, constraints, and intended use from conversation or files.
2 State Situation Write project context and situation for a researcher with no prior conversation history.

Work

Agent / skill execution

3 Define Question Define one research question and the concrete decision it will inform.
4 Add Sub-questions Add three to six inline numbered sub-questions that cover the decision without mixing unrelated missions.

Verify

Gate, review, validation

5 Set Evidence Rules Specify source hierarchy, include/avoid constraints, contradiction handling, and gap-round requirements.
6 Define Output Bar Require source URL, specific claim, one-line decision relevance for each finding, and one detailed Markdown result.

Report, handoff, artifact

7 Return Paragraph Return exactly one focused paragraph with no headings, preface, or extra deliverable.

<research topic | decision>

Turn a topic or decision into a handoff-ready research assignment.

Concrete invocations for each flag, subcommand, mode, or route available in the live workflow.

Market decision Recommended

/ak:research-prompt Should we prioritize LinkedIn Ads or Google Search for a B2B SaaS launch?

Use when:: You need a research assignment before choosing a marketing channel.
Expected:: One paragraph brief with context, decision, sub-questions, source rules, and output requirements.

Pricing research

/ak:research-prompt Evidence needed to choose freemium vs free trial for our developer tool

Use when:: A monetization decision needs source-backed research.
Expected:: A handoff-ready research paragraph focused on the decision, evidence needed, and expected output.

Competitive research

/ak:research-prompt Compare referral program mechanics used by top PLG SaaS companies

Use when:: You want another researcher to collect evidence, not guesses.
Expected:: Brief requiring primary sources, contradiction handling, per-finding relevance, and clear citation expectations.

Next