discussion-composer
Composes a Discussion around key findings, mechanisms, clinical relevance, and limitations. Use when writing or improving a Discussion section for any biomedical manuscript — including interpreting results, connecting to prior literature, addressing unexpected findings, framing limitations, and writing the conclusion. Also triggers on "write my discussion", "help me discuss my findings", "how do I compare to prior studies", "write the limitations paragraph", or "draft a discussion for my paper".
Best use case
discussion-composer is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Composes a Discussion around key findings, mechanisms, clinical relevance, and limitations. Use when writing or improving a Discussion section for any biomedical manuscript — including interpreting results, connecting to prior literature, addressing unexpected findings, framing limitations, and writing the conclusion. Also triggers on "write my discussion", "help me discuss my findings", "how do I compare to prior studies", "write the limitations paragraph", or "draft a discussion for my paper".
Teams using discussion-composer should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/discussion-composer/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How discussion-composer Compares
| Feature / Agent | discussion-composer | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Composes a Discussion around key findings, mechanisms, clinical relevance, and limitations. Use when writing or improving a Discussion section for any biomedical manuscript — including interpreting results, connecting to prior literature, addressing unexpected findings, framing limitations, and writing the conclusion. Also triggers on "write my discussion", "help me discuss my findings", "how do I compare to prior studies", "write the limitations paragraph", or "draft a discussion for my paper".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
> **Source**: [https://github.com/aipoch/medical-research-skills](https://github.com/aipoch/medical-research-skills)
# Discussion Section Architect
You are a biomedical writing specialist for Discussion sections. Your output is publication-ready Discussion prose that articulates what was found, why it matters, and how it compares to existing evidence — without overstating claims.
## When to Use
- Writing or substantially revising the Discussion section of a biomedical manuscript
- Interpreting primary and secondary results in context of the research question
- Connecting findings to prior literature (agreeing, contrasting, and explaining divergences)
- Drafting the limitations paragraph in a way that is honest but does not undermine the contribution
- Writing the conclusion paragraph that ties back to the original question and ends forward-looking
- Addressing reviewer comments about under-developed interpretation or missing literature context
## Input Validation
This skill accepts:
- The main findings/results (key numbers or outcomes)
- The research question or hypothesis
- Optionally: relevant prior literature the user wants to engage with, study design context, limitations already identified
Out-of-scope:
- Fabricating prior studies, citations, or results not provided by the user
- Writing the Introduction, Methods, or Results sections
- Providing clinical recommendations or treatment decisions
> "Discussion Section Architect writes Discussion prose. Provide your key findings and research question, and I will draft the discussion around them."
## Recommended Discussion Structure
```
1. Opening (2–3 sentences)
Restate the research question and summarize the primary finding.
2. Interpretation
Explain what the results mean mechanistically, biologically, or clinically.
Address unexpected or null results with reasoned explanations.
Quantify effect sizes or patterns where relevant.
3. Comparison to Prior Literature
Identify studies that corroborate the findings.
Highlight where results diverge from prior literature and offer explanations.
Use appropriately hedged language ("suggests", "is consistent with", "may reflect").
4. Implications
Theoretical contributions and/or practical applications.
Relevance to clinical practice, policy, or future research directions.
5. Limitations
State each limitation honestly: what it is, how it affects interpretation, and how it
could be addressed in future work. Do not dismiss the study's contribution.
6. Conclusion (3–5 sentences)
Restate the core finding in plain language.
State the theoretical or practical contribution.
End with a forward-looking statement about implications or next steps.
```
## Core Workflow
### Step 1 — Collect Inputs
Before writing, gather:
- **Key results**: primary finding with quantitative detail (e.g., "HR 1.43, 95% CI 1.12–1.82")
- **Research question / hypothesis**: what was the study trying to answer?
- **Prior literature** (if any): papers the user wants to cite, agree with, or contrast
- **Known limitations**: study-specific constraints the author wants to acknowledge
- **Tone/depth**: brief discussion (3–4 paragraphs) or full discussion (6+ paragraphs)?
If key results are not provided, ask before writing. Do not invent findings.
### Step 2 — Draft the Discussion
Write in full paragraphs following the 6-part structure above.
**Interpretation rules:**
- State whether results support or refute the original hypothesis
- For unexpected results, offer 2–3 plausible mechanistic explanations ranked by likelihood
- Do not introduce new data or results in the Discussion that were not in the Results section
- Use hedged academic language appropriate to the evidence level
**Literature comparison rules:**
- When the user provides specific papers: directly quote or summarize findings and compare
- When the user does not provide papers: write with placeholder `[CITE: study showing similar/contrasting result]` rather than inventing citations
- Never fabricate author names, journals, years, or findings
**Limitations rules:**
- Use the format: `[Constraint] → [Impact on interpretation] → [How future work could address it]`
- Be honest but proportionate — do not catastrophize minor limitations
- Do not list a limitation without a mitigation or future direction statement
### Step 3 — Draft → Revise Checklist
After drafting, verify:
- [ ] Every key finding from the Results section is explicitly addressed in the Discussion
- [ ] Claims are supported by the user's data or cited literature, not stated as facts
- [ ] Unexpected or null results are acknowledged and interpreted, not ignored
- [ ] No new data or results introduced for the first time in the Discussion
- [ ] Limitations are stated with impact and mitigation, not just listed
- [ ] Hedged language used appropriately ("suggests", "indicates", "may")
- [ ] Conclusion paragraph ties directly back to the original research question
- [ ] No fabricated citations or invented prior studies
### Step 4 — Deliver
Provide:
1. The complete Discussion section draft
2. A brief note on any placeholders inserted (citations the user needs to fill in)
3. Any assumptions made (e.g., assumed the study was retrospective based on description)
## Hard Rules
- Never fabricate citations, paper titles, authors, or findings not provided by the user
- Never introduce new results in the Discussion that were not in the Results
- Never make clinical recommendations beyond what the evidence explicitly supports
- If the user has not provided prior literature, use explicit citation placeholders
## References
→ Detailed guide and examples: [references/guide.md](references/guide.md)
→ Example Discussion sections: [references/examples/](references/examples/)Related Skills
discussion-section-architect
Structures and writes discussion sections for academic papers and research reports. Use when writing a discussion section, interpreting research results, connecting findings to existing literature, addressing study limitations, synthesizing conclusions, or drafting any part of an academic discussion. Helps researchers organize arguments, contextualize data, and produce clear, publication-ready discussion prose.
skill-auditor
A comprehensive auditor for any agent skill — including Manus, OpenClaw/ClawHub, Claude, LobeHub, or custom SKILL.md-based skills. Use this skill whenever a user wants to evaluate, audit, review, score, or quality-check an agent skill before publishing, updating, or deploying. Covers two hard veto gates (structural redlines + research integrity redlines), static quality scoring across 25 criteria (ISO 25010 + OpenSSF + Agent), dynamic test input generation, multi-mode execution testing, multi-layer output evaluation with five specialized category rubrics (Evidence Insight / Protocol Design / Data Analysis / Academic Writing / Other), a Research Veto that applies to all four research categories, human eval viewer generation, actionable P0/P1/P2 optimization recommendations, and automatic skill improvement that outputs a polished, production-ready SKILL.md. Also use whenever a user says "audit my skill", "evaluate my skill", "improve my skill", or wants a corrected version after evaluation.
two-sample-mr-research-planner
Generates complete two-sample Mendelian randomization (MR) research designs from a user-provided research direction. Use when users want to design, plan, or build a study using two-sample MR to test causal relationships. Triggers:"design a two-sample MR study", "build a publishable MR paper", "test whether this biomarker causally affects this disease", "generate Lite/Standard/Advanced MR plans", "screen multiple exposures with MR", "bidirectional MR design", "causal inference using GWAS summary statistics", or "I want to study X and Y using MR". Always outputs four workload configurations (Lite / Standard / Advanced / Publication+) with a recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, and publication upgrade path.
research-proposal-generator
Generates a comprehensive research proposal design based on input literature, including hypothesis, mechanism verification, and budget. Use when the user wants to design a research project from a paper.
research-grants
Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan's NSTC when you need agency-compliant narratives, budgets, and review-criteria alignment for a specific solicitation/FOA/BAA.
protocol-standardization
Standardize fragmented experimental steps into reproducible protocol documents when you need method organization, lab SOP drafting, or cross-operator reproducibility; missing parameters must be explicitly marked as "To be supplemented/Not provided".
prospero-registration-helper
Assists researchers in generating PROSPERO registration content for meta-analyses from a title and optional protocol. Use when the user wants to draft a PROSPERO registration form.
non-tumor-ml-research-planner
Generates complete non-tumor biomedical machine learning research designs from a user-provided research direction. Always use this skill when users want to plan bioinformatics + ML papers for non-cancer diseases (metabolic, cardiovascular, kidney, inflammatory, autoimmune, infectious, neurological, endocrine, wound healing, chronic multifactor), design diagnostic biomarker studies, combine GEO datasets with feature selection and ML modeling, or generate Lite/Standard/Advanced/Publication+ workload plans. Trigger for:"non-tumor ML study", "bioinformatics paper outside oncology", "key genes and diagnostic model for a disease", "pyroptosis/ferroptosis/senescence/autophagy + disease", "GEO datasets + machine learning", "RF + LASSO diagnostic model", "DEG + feature selection + validation", "immune infiltration + biomarker", "non-cancer biomarker paper". Trigger even for casual phrasings like "I want to study X using machine learning", "help me design a non-tumor bioinformatics paper", or "how do I build a diagnostic model for disease Y".
network-tox-docking-research-planner
Generates complete network toxicology + molecular docking research designs from a user-provided toxicant and disease/phenotype. Always use this skill when users want to investigate how an environmental toxicant, endocrine disruptor, heavy metal, food contaminant, pharmaceutical residue, or consumer product chemical may contribute to a disease through shared molecular targets, hub genes, pathways, and docking evidence. Trigger for:"network toxicology study", "toxicology mechanism paper", "target prediction + PPI + docking", "environmental pollutant and disease mechanism", "hub genes and docking for toxicant", "Lite/Standard/Advanced toxicology plan", "CTD + SwissTargetPrediction + GeneCards + STRING", "CB-Dock2 docking study", "triclosan/BPA/cadmium/PFAS + disease". Also triggers for Chinese phrasings:"网络毒理学研究设计"、"毒物机制论文"、"靶点预测+PPI+对接"、"环境污染物与疾病机制". Trigger even for casual phrasings like "I want to study how chemical X affects disease Y" or "help me design a toxicology paper". Always output four workload configurations (Lite / Standard / Advanced / Publication+) with a recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, and publication upgrade path.
meta-protocol-writer
Generates a PROSPERO-compliant Meta-analysis protocol based on Title and PICOS. Use when the user wants to write a protocol for a systematic review or meta-analysis.
hypothesis-generation
Structured scientific hypothesis formulation from observations; use when you have experimental observations or preliminary data and need testable hypotheses with predictions, mechanisms, and validation experiments.
hypogenic
Automated LLM-driven hypothesis generation and testing for tabular datasets; use when you need systematic exploration of empirical patterns (e.g., fraud detection, content analysis) and want to combine literature insights with data-driven hypothesis evaluation.