Source: https://github.com/aipoch/medical-research-skills
Lay Summary for Cross-Disciplinary Teams
Converts technical research into a structured summary that clinical, wet-lab,
bioinformatics, product, and management teams can rapidly read and act on.
Position in the Research Pipeline
This skill sits midstream:
- Upstream (should exist first): Clear research question, defined objectives,
structured results, result narrative
- This skill: Translates that clarified content for non-specialist readers
- Downstream (natural next steps): Slide Deck for Lab Meeting, Graphical
Abstract Generator, Reviewer Response Drafter
If the user's research content is still vague or unstructured, prompt them to
clarify objectives and key findings first. A lay summary built on unclear input
will sound smooth but be factually imprecise — worse than no summary.
Step 1 — Gather Input
Ask the user to provide any of:
- Abstract, introduction, or results section
- Key findings in their own words
- A study summary or internal report
Also ask: Who is the primary audience?
mixed (default) — all teams listedclinical — clinicians, medical staffwet-lab — bench scientists, experimentalistsbioinformatics — computational scientists, data analystsproduct — product managers, translational teamsmanagement — leadership, funders, executives
If unspecified, use mixed and include all relevant audience bullets.
Step 2 — Extract Core Structure
Before writing, internally map the input to these five elements:
| Element |
What to find |
| Study goal |
Why was this done? What problem does it address? |
| System / population |
What was studied? (patients, cells, datasets, samples…) |
| Main finding |
What did the data show? Be specific — avoid vague positives. |
| Evidence boundary |
What can this support? What remains uncertain or untested? |
| Next action |
What should each team know or do because of this? |
If any element is missing from the input, note it in the output and invite the
user to fill in the gap.
Step 3 — Write the Lay Summary
Use the output template in assets/output-template.md.
Writing principles:
- No unexplained acronyms — define on first use or remove
- Evidence boundary must be explicit: distinguish finding from interpretation
- Each audience bullet should be actionable, not just descriptive
- Quantify findings where possible ("3-fold higher", "in 4 of 6 subtypes")
- The summary must stand alone without access to the original paper
For audience-specific language guidance, read references/audience-guide.md.
Step 4 — Quality Check
Before delivering output, verify:
If a check fails, revise before presenting.
References
assets/output-template.md — the standard 6-section output template with examplereferences/audience-guide.md — language and framing guidance per audience type
1---2name: lay-summary-for-cross-disciplinary-teams3description: Rewrites technical research content into a structured lay summary that cross-disciplinary teams can quickly understand and act on. Use when the user wants to explain research to colleagues outside their specialty — clinicians, wet-lab scientists, bioinformaticians, product managers, or leadership. Trigger on: "lay summary", "explain my research to the team", "non-technical summary", "cross-disciplinary summary", "translate my findings", "align our team on the study", or any request to communicate research goals, findings, or next steps to a mixed or non-specialist audience. Part of the AIPOCH Academic Writing skill hub. Sits midstream: after research content is clarified, before downstream deliverables like slide decks or graphical abstracts.4license: MIT5---6> **Source**: [https://github.com/aipoch/medical-research-skills](https://github.com/aipoch/medical-research-skills)
7
8# Lay Summary for Cross-Disciplinary Teams
9
10Converts technical research into a structured summary that clinical, wet-lab,
11bioinformatics, product, and management teams can rapidly read and act on.
12
13## Position in the Research Pipeline
14
15This skill sits **midstream**:
16
17- **Upstream** (should exist first): Clear research question, defined objectives,
18 structured results, result narrative
19- **This skill**: Translates that clarified content for non-specialist readers
20- **Downstream** (natural next steps): Slide Deck for Lab Meeting, Graphical
21 Abstract Generator, Reviewer Response Drafter
22
23If the user's research content is still vague or unstructured, prompt them to
24clarify objectives and key findings first. A lay summary built on unclear input
25will sound smooth but be factually imprecise — worse than no summary.
26
27---
28
29## Step 1 — Gather Input
30
31Ask the user to provide any of:
32- Abstract, introduction, or results section
33- Key findings in their own words
34- A study summary or internal report
35
36Also ask: **Who is the primary audience?**
37- `mixed` (default) — all teams listed
38- `clinical` — clinicians, medical staff
39- `wet-lab` — bench scientists, experimentalists
40- `bioinformatics` — computational scientists, data analysts
41- `product` — product managers, translational teams
42- `management` — leadership, funders, executives
43
44If unspecified, use `mixed` and include all relevant audience bullets.
45
46---
47
48## Step 2 — Extract Core Structure
49
50Before writing, internally map the input to these five elements:
51
52| Element | What to find |
53|---|---|
54| **Study goal** | Why was this done? What problem does it address? |
55| **System / population** | What was studied? (patients, cells, datasets, samples…) |
56| **Main finding** | What did the data show? Be specific — avoid vague positives. |
57| **Evidence boundary** | What can this support? What remains uncertain or untested? |
58| **Next action** | What should each team know or do because of this? |
59
60If any element is missing from the input, note it in the output and invite the
61user to fill in the gap.
62
63---
64
65## Step 3 — Write the Lay Summary
66
67Use the output template in `assets/output-template.md`.
68
69Writing principles:
70- No unexplained acronyms — define on first use or remove
71- Evidence boundary must be explicit: distinguish finding from interpretation
72- Each audience bullet should be actionable, not just descriptive
73- Quantify findings where possible ("3-fold higher", "in 4 of 6 subtypes")
74- The summary must stand alone without access to the original paper
75
76For audience-specific language guidance, read `references/audience-guide.md`.
77
78---
79
80## Step 4 — Quality Check
81
82Before delivering output, verify:
83
84- [ ] No naked jargon or undefined acronyms
85- [ ] Finding is accurate — not overstated, not undersold
86- [ ] Evidence boundary is clearly hedged
87- [ ] Each audience bullet is actionable
88- [ ] Summary reads cleanly to someone with no domain knowledge
89
90If a check fails, revise before presenting.
91
92---
93
94## References
95
96- `assets/output-template.md` — the standard 6-section output template with example
97- `references/audience-guide.md` — language and framing guidance per audience type
gabrielmoreira