About synthesis-writer
synthesis-writer turns an evidence-review extraction table into a structured narrative for evidence-review authors. It keeps conclusions grounded in extracted data and includes sections for bias, supported conclusions, and evidence gaps.
Key features
- 01Convert extraction tables into narrative
- 02Render stable report sections
- 03Bound conclusions to source data
- 04Address bias and evidence gaps
Use cases
- 01Draft an evidence-review synthesis
- 02Summarize findings by theme
- 03Report risk of bias and evidence gaps
Install
Copy the command and run it in a terminal.
$
npx skills add https:/ / github.com/ willoscar/ research-units-pipeline-skills --skill synthesis-writerAfter installing, type/synthesis-writerin Claude Code to confirm it loaded.
Bundled filesscripts/run.py
Details
From the project READMESynthesis Writer
Triggers & routing
- Trigger: synthesis, evidence synthesis, systematic review writing, 综合写作, SYNTHESIS.md.
- Use when:
evidence-review完成 screening+extraction(含 bias 评估)后进入写作阶段(C5)。 - Skip if: 还没有
papers/extraction_table.csv(或 protocol/screening 尚未完成)。 - Network: none.
- Guardrail: 以 extraction table 为证据底座;明确局限性与偏倚;不要在无数据支撑时扩写结论。
Transforms the extraction table into the final evidence-review narrative.
Input
papers/extraction_table.csv
Optional:
output/PROTOCOL.mdDECISIONS.md
Output
output/SYNTHESIS.md
Contract
The synthesis must include stable sections:
## Included studies summary## Findings by theme## Risk of bias## Supported conclusions## Needs more evidence
Script boundary
scripts/run.py should:
- summarize extracted evidence conservatively
- keep conclusions bounded by table contents
- render the stable section structure
It should not invent findings not grounded in the extraction table.
Acceptance
- output exists
- includes all stable sections
- stays table-grounded and bounded
Non-goals
- upstream extraction repair
- free-form speculative discussion
Comments
Markdown supported