Contenu du pack

Un fichier SKILL.md (le guide pratique) + un modèle de départ. Aperçu :

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

1. 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.
2. 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.
3. 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.
4. 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.
5. Compose the communication workflow (input: passing kit → output: audience-by-audience sequence)
   Wire the skills into the order the study travels: summary circulates to peers for a fact-check first, figures get rebuilt once and reused everywhere, deck carries the talk, brief goes to funders and press with the deck, Q&A prep readies you for each audience's questions. Define the handoffs: peer corrections update the spine once, and every skill inherits the fix — never patch one output and leave the others stale.
6. Maintain the kit (input: corrections, replications, follow-up questions → output: updated spine and skills)
   When a correction, erratum, or follow-up study lands, update the spine and regenerate every affected output. Log the questions audiences actually asked — they are the best guide to which skill needs a clearer version next time. Archive superseded outputs so nobody quotes the old numbers.

Aperçu du modèle

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

Le pack de compétence lui-même (SKILL.md + modèle) est rédigé en anglais.

Acheter le pack complet — $4.99 Pro — les 511 compétences