mcpbeat

Synthesis Writer

willoscar/synthesis-writer

| Use when `evidence-review` has completed extraction and needs a bounded narrative synthesis.

686 tokens
context cost
the whole folder, loaded on every use
2
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
496
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/WILLOSCAR/research-units-pipeline-skills --skill synthesis-writer

What comes with it

1 303 bytes besides the instruction
scripts/run.py

The instruction itself

7 sections, as written by the author

Synthesis Writer

Transforms the extraction table into the final evidence-review narrative.

Input

  • papers/extraction_table.csv

Optional:

  • output/PROTOCOL.md
  • DECISIONS.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

How to use it

Copy the folder

Take willoscar/synthesis-writer from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.