Research Communication Skills
Same findings, every audience, nothing lost in translation.
Turns your AI into a research-communication kit builder — assembles a coherent set of skills that turn a paper or report into an accurate summary, clear figures, honest slides, and a plain-language brief, so every audience gets the same findings at their level.

Install it in 3 steps
No sign-up. No CLI tools. Pick your AI, copy one line, paste it over.
Prefer doing it yourself? Buy the skill ($4.99), download the ZIP from your checkout confirmation, unzip it into the directory shown above, restart your AI session — same result. Already bought it? Your AI assistant can download it for you.
What’s inside
One SKILL.md (the playbook) + one starter template. A preview:
Research Communication Skills
When to use
- You have a finished paper, report, or study and need to explain it to people who will never read the original
- Your figures are technically correct and nobody outside your lab can tell what they show
- A funder, policymaker, or executive wants "the two-page version" and you keep handing them the abstract
- You are preparing a talk and your slides are the paper pasted into rectangles
- Journalists, partners, or the public keep misquoting your findings because no plain-language version exists
Workflow
- Scope the kit (input: source study + audiences → output: kit inventory)
Name the source (one paper, one report, one dataset — never a vague "my research") and list every audience that needs a version: peers, funders, decision-makers, press, public. Each audience gets its own skill output, not a resized copy of another audience's. The default kit: paper summary, figure explainer, slide deck, plain-language brief, and Q&A prep. Drop any skill whose audience does not actually exist for this study. - Extract the findings spine (input: source study → output: findings spine)
Distill the study into a spine before any skill is built: research question, method in two sentences, headline result with its exact numbers and uncertainty, what the result does not show, and limitations. Every number keeps its units, sample size, and confidence interval. The spine is the fidelity contract — no kit skill may sharpen a hedged finding into a certainty or drop a caveat to make a slide punchier. - Build the skills in audience order (input: findings spine → output: five working skills)
Build from the most technical audience outward: paper summary first (peers — full precision), then figure explainer (every figure restated in words: what the axes are, what the pattern is, what it means), then slide deck (talk version, one claim per slide, figures rebuilt for projection), then plain-language brief (no jargon, analogies allowed only if they preserve the finding), then Q&A prep (the questions each audience will actually ask, answered at their level). Each skill takes the spine as its only factual input. - Apply the quality bar (input: five draft skills → output: kit that passes every gate)
Test every skill against the same bar: a reader of any output can state the headline result, its uncertainty, and one limitation; no output contradicts another on numbers, direction, or scope; jargon is defined on first use in every output, not just the technical ones; figures in the deck match the figures in the explainer; and the plain-language brief contains zero claims absent from the spine. A kit that fails any gate goes back to the skill that failed.
Template preview
Research Communication Skills — Kit Template
Build the kit in order: spine first, then summary, figures, deck, brief, Q&A.
1. Study brief
Source: {paper / report / dataset title, authors, date} Audiences that need a version: {peers / funders / decision-makers / press / public}
2. Findings spine (fidelity contract)
Numbers ledger: {figure} | {value + units} | {sample size} | {interval} | {source page/section}
3. Kit inventory
4. Quality gate (every skill must pass)
[ ] A reader can state the headline result, its uncertainty, and one limitation [ ] No output contradicts another on numbers, direction, or scope [ ] Jargon defined on first use in every output


