Synthesize all accumulated notes and drafts to generate the Discussion and Abstract sections. Sixth step of writer workflow. Requires all notes/*.md files and drafts/introduction.md, methods.md, results.md.
Generates Discussion and Abstract sections by synthesizing all research notes and prior drafts with literature findings. Triggers after completing Introduction, Methods, and Results drafts, using the literature synthesis to connect your results to existing work.
/plugin marketplace add sxg/science/plugin install writer@scienceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Integrates all accumulated notes and prior drafts to generate the Discussion and Abstract sections, connecting findings to the broader literature.
Required files:
scope.md - Research question and key findingsnotes/papers/*.md - Literature notes (from user-provided PDFs)notes/literature-synthesis.md - Aggregated themes and findings (key input!)notes/code-analysis.md - Methods contextnotes/data-analysis.md - Results contextdrafts/introduction.md - For narrative continuitydrafts/methods.md - For methodological contextdrafts/results.md - Findings to discuss[Load all notes and drafts]
│
▼
[Map findings to literature] ─── What supports/contradicts
│
▼
[Draft Discussion] ─── Interpret, compare, contextualize
│
▼
[Draft Abstract] ─── Structured summary
│
▼
[Output] ─── drafts/discussion.md, drafts/abstract.md
Start with notes/literature-synthesis.md - this document already contains:
This synthesis is the primary guide for drafting the Discussion.
Check the Paper Citation Tracker table to see which papers have natural fits planned. Use these as your citation guide.
Important: Only cite papers where they contribute meaningfully. Do not:
Papers marked "Not Applicable" in the tracker should remain uncited. A focused manuscript with relevant citations is better than a cluttered one that forces every paper.
ls notes/papers/*.md notes/*.md
Use individual paper notes for specific quotes and statistics.
The synthesis document provides:
From drafts/results.md and notes/data-analysis.md:
From scope.md:
Use notes/literature-synthesis.md as the starting point - it already contains:
Extend this mapping with our actual results from drafts/results.md:
| Our Finding | Supporting Literature | Contrasting Literature | Notes |
|---|---|---|---|
| [Primary result] | [from synthesis] | [from synthesis] | [why contrast] |
| [Secondary result] | [from synthesis] | None |
For each finding, the synthesis document identifies:
Create drafts/discussion.md following this structure:
# Discussion
## Principal Findings (Paragraph 1)
[Open with main finding - interpret, don't just restate]
This study demonstrates that [interpretation of primary finding].
[Connect to research question from scope.md].
[One sentence on significance].
## Comparison with Literature (Paragraphs 2-3)
[Compare findings to existing work]
Our findings are consistent with [Author et al.], who reported [finding] [citation].
Similarly, [Author2 et al.] demonstrated [related finding] [citation].
[Address any discrepancies]
In contrast to [Author3 et al.], who found [different result] [citation], our study suggests [explanation].
This difference may be attributed to [methodological differences, population differences, etc.].
## Mechanistic Interpretation (Paragraph 4)
[Explain WHY these results might occur]
These findings may reflect [biological/clinical mechanism].
[Author et al.] previously showed that [mechanistic evidence] [citation],
which supports the hypothesis that [explanation].
[If speculative, use appropriate hedging: "may", "might", "could potentially"]
## Clinical/Practical Implications (Paragraph 5)
[What does this mean for practice?]
These results have several implications for [clinical practice / research / etc.].
First, [implication 1].
Second, [implication 2].
[If applicable: These findings suggest that clinicians should consider...]
## Limitations (Paragraph 6)
[Honest but constructive discussion of limitations]
This study has several limitations that should be considered.
First, [limitation 1 with mitigation if possible].
Second, [limitation 2].
[Frame constructively: "While [limitation], [mitigating factor]..."]
Common limitations to address:
- Sample size
- Single-center
- Retrospective design
- Selection bias
- Technical limitations
- Generalizability
## Future Directions (Paragraph 7)
[What should come next?]
Future studies should [specific actionable suggestion].
Prospective validation in [population] is warranted.
Additionally, [another future direction].
---
## Discussion References
[List all citations used in Discussion with note references]
Agreement:
Disagreement:
Extension:
Create drafts/abstract.md:
# Abstract
## Background/Purpose
[2-3 sentences: Gap in knowledge + study objective]
[Clinical/scientific problem]. [What is unknown]. The purpose of this study was to [objective].
## Methods
[3-4 sentences: Design, population, key methods, statistics]
This [study design] included [n] patients from [setting]. [Key methods]. [Primary outcome measure]. [Statistical approach].
## Results
[3-4 sentences: Key findings with numbers]
[Primary finding with statistics]. [Secondary finding]. [Additional notable result].
## Conclusion
[1-2 sentences: Main takeaway + implication]
[Main conclusion]. [Clinical/research implication].
---
**Word Count**: [count]
**Keywords**: [keyword1], [keyword2], [keyword3], [keyword4], [keyword5]
| Section | Target |
|---|---|
| Background | 50-75 words |
| Methods | 75-100 words |
| Results | 75-100 words |
| Conclusion | 25-50 words |
| Total | ~250-300 words |
Adjust based on scope.md target journal requirements.
Based on synthesis, suggest 2-3 title options:
## Suggested Titles
1. [Descriptive]: "[Method/Approach] for [Application]: [Key Finding]"
2. [Question-answer]: "[Research Question]? A [Study Type]"
3. [Finding-focused]: "[Key Finding] in [Population] Using [Method]"
Title guidelines:
Record which papers were cited and which were not.
Update notes/literature-synthesis.md with final citation status:
## Citation Summary
**Generated**: [timestamp]
**Total Papers Provided**: [n]
**Papers Cited**: [n]
**Papers Not Used**: [n]
### Cited Papers
| # | Citation | Section | Purpose |
|---|----------|---------|---------|
| 1 | Smith et al., 2023 | Introduction | Establishes prevalence |
| 2 | Jones et al., 2022 | Discussion | Comparable methodology |
### Papers Not Used
| Paper | Reason |
|-------|--------|
| Brown et al., 2020 | Different population; not directly comparable |
| Lee et al., 2019 | Tangential to our research question |
Note: Not using a paper is acceptable when it doesn't naturally fit. The goal is manuscript quality, not citation count.
Save to:
drafts/discussion.md - Discussion sectiondrafts/abstract.md - Structured abstract with title optionsnotes/literature-synthesis.md - Updated with Citation SummaryReturn to parent skill with summary:
Use when working with Payload CMS projects (payload.config.ts, collections, fields, hooks, access control, Payload API). Use when debugging validation errors, security issues, relationship queries, transactions, or hook behavior.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.