scientific-communication
Skill2 starsChanged 30 days agoMITView on GitHub
Shape scientific talks, posters, pitches, public explanations, and delivery. Exclude manuscript editing, figure-only design, and plotting-code fixes.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- jjfroehlich/agent-handbook-for-life-science-researchword for word, first seen Oct 9, 2026
Other versions1 project uses a version of this.
Word for word · 1
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- career-developmentSkill
- data-visualization-and-figuresSkill
- grant-writingSkill
- life-science-research-handbookSkill
- literature-reading-and-synthesisSkill
- mentoring-management-and-lab-cultureSkill
- publishing-and-peer-reviewSkill
- research-strategy-and-project-designSkill
- scientific-feedbackSkill
- scientific-writingSkill
The file
Files
Scientific Communication
Purpose
Help agents shape scientific content for its audience and medium: a connected talk, readable slides or poster, a listener-specific opening, or an evidence-based answer to a question. A research briefing can cover several decisions without forcing them into one discovery story.
Use this skill when
- The user asks for help with a scientific talk, seminar, conference presentation, poster, chalk talk, elevator pitch, research story, or public-facing explanation.
- The artifact is a slide outline, slide deck, poster layout, spoken script, title, abstract-for-a-talk, presentation plan, or Q&A preparation note.
- The user needs structure, cuts, visual hierarchy, delivery rehearsal, audience adaptation, or a short spoken version of research.
- The user asks for a communication review rather than manuscript editing, figure publication review, grant strategy, or peer-review response.
Do not use this skill when
- The user primarily needs manuscript prose, paper organization, cover letters, or reviewer responses.
- The task is only about choosing or coding a data visualization for a publication figure.
- The request is about research strategy, experimental design, citation management, or conference logistics without a communication artifact.
- The user wants generic public-speaking motivation rather than concrete scientific communication work.
Core workflow
- Establish the requested artifact/intervention, actual audience familiarity, purpose, medium and time/space limit from the supplied context. Ask only for missing facts that could change the work. A local edit does not require a planning questionnaire or a single invented main message.
- Diagnose the main failure mode: unclear premise, overloaded detail, weak audience bridge, unreadable visuals, poor format fit, or unprepared delivery/Q&A.
- Route to the narrowest useful playbook. Open only the needed reference unless the artifact spans formats.
- When structure or density needs work, make cuts before polish. Retain decisive comparisons, controls, prerequisites and claim-changing uncertainty; move genuinely secondary details to usable backup, notes or conversation. If important evidence does not fit a story, change the story or scope. A methods critique or unresolved update may need several independent threads.
- Produce a concrete artifact: revised outline, slide-by-slide plan, poster redesign, pitch script, chalk-talk board plan, Q&A prep list, or prioritized checklist.
- Preserve actual quantities, chronology, credit and work status. Do not invent benefits, completed controls, discovery history, resources, causal links, audience responses or permission to fill a template. Distinguish proposed revisions from implemented work and inspect the actual artifact before certifying its appearance or operation.
Reference routing
references/talk-structure.md: Open for seminars, conference talks, thesis talks, or slide order problems.references/slide-design.md: Open for slide density, visual hierarchy, figure adaptation, text-heavy slides, or deck mechanics.references/posters.md: Open for conference posters, digital posters, poster walkthroughs, or poster redesign.references/chalk-talks.md: Open for faculty interview chalk talks, board-based research plans, or highly interactive research vision sessions.references/elevator-pitches.md: Open for short spoken summaries, networking pitches, lay explanations, or timed project introductions.references/storytelling.md: Open when the user needs narrative framing, audience memory, tension, explanation, or a stronger through-line.references/delivery-and-qa.md: Open for rehearsal, vocal/physical delivery, question handling, nerves, timing, or audience interaction.references/public-and-media.md: Open for a public explanation's genre/channel, communication program, release/access decision, media interview or controversy response. Keep legal, clinical and institutional determinations with the appropriate authority.- Open
references/handbook-access.mdwhen a fuller explanation or worked example would help with the current task. Inspect the actual image or rendered HTML when judging visual appearance. checklists/talk-review.md: Use for a fast final review of a talk or deck.checklists/poster-review.md: Use for a final poster review before print, upload, or presentation.examples/communication-feedback-examples.md: Open when the user needs a model output pattern.
Quality bar
- Advice must be medium-specific and audience-specific.
- The answer must include concrete cuts, ordering, visual hierarchy, rehearsal moves, or Q&A moves.
- The agent must preserve scientific uncertainty while still making the communication sharper.
- Methods, notes, scripts, topic/question titles, static digital posters and informative answers without an ask remain valid when the task calls for them. No story, performance style, result quota or fixed practice dose is compulsory.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

