research-prompt
Turn vague research needs into one precise deep-research prompt with context and output criteria.
HealthcareGovernment & Public SectorProduct ManagementExecutives & StrategyScience & Researchbriefspromptingresearch
Research Prompt
When to Use
- Use when the user wants a deep-research brief or researcher prompt.
- Use when a vague research question needs to become one precise self-contained paragraph.
Goal: turn a vague research need into ONE self-contained paragraph that a researcher with zero prior knowledge of the project can act on with zero back-and-forth.
Rules
- One paragraph. No headers, no bullet list in the deliverable.
- Prompt the job, not the topic. Give search handles (timeframe, ranking, source type, decision logic) — not just a subject.
- Assume zero prior knowledge. Write for a researcher who has never heard of the project. Open by explaining, in plain English, what the project/product is, why it exists, and the current situation — so they understand what's going on, what we need, and why we need it.
- Lead with the goal + decision. Right after that explainer, state the single question the research must answer and the decision/use it informs.
- Embed all context. Names, dates, product, prior known facts, constraints. The researcher must not need to ask anything or guess.
- Number the sub-questions inline (1, 2, 3…) so coverage is explicit. Keep to 3–6. One mission per prompt — don't cram unrelated questions.
- State constraints. What to include, what to avoid (e.g. "only non-Chinese competitors", "no marketing fluff").
- **Source h
Subscribers only
The full skill, its 1 bundled files and every download is included with every paid Complete AI plan.
Details
| Source | davidondrej/skills |
|---|---|
| License | MIT |
| Risk label | safe ("critical" means the skill may run commands or touch files — read before use) |
| Files | SKILL.md |
| Added | 2026-07-07 |
Related skills
deepapi
Use DeepAPI for supported scraping, research, and email workflows with explicit credentials and approval.
dsh-deepread
Use for evidence-first reading of articles, books, PDFs, web pages, or document sets, with knowledge maps and Feynman checks.
entropy-box
Entropy Box knowledge-compiler for embodied-AI: turns bounded requirements into grounded workflows via Solution Consult, Search, Lookup, and Evidence. Do not use it to control physical robots.
fact-check-x-complete
Compare claims from one or more AI answers, verify their citations against public primary sources, and produce an evidence-linked fact-check report without installing a bundled browser runtime.
gemini-deep-research
Run autonomous multi-step research with Google's Gemini Deep Research Agent: kick off a query, poll progress, and collect a cited report for market analysis or literature reviews.
ii-commons
Deterministic search across arXiv, PubMed/PMC, and US policy corpora with daily freshness cutoffs.
