mcpbeat

Protocol Writer

willoscar/protocol-writer

| Use when `evidence-review` needs an operational protocol before screening and extraction.

1k 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 protocol-writer

What comes with it

3 120 bytes besides the instruction
scripts/run.py

The instruction itself

7 sections, as written by the author

Protocol Writer

Transforms the review question into an executable evidence-review protocol.

Inputs

Required:

  • STATUS.md

Optional:

  • GOAL.md
  • DECISIONS.md
  • queries.md

Output

  • output/PROTOCOL.md

Contract

The protocol must contain:

  • review questions
  • source/search specification
  • inclusion and exclusion clauses with stable IDs
  • screening plan
  • extraction schema
  • bias plan
  • explicit HUMAN approval note

Script boundary

scripts/run.py should:

  • read current review context
  • materialize an operational protocol
  • write a stable extraction schema and clause IDs

It should not perform retrieval or screening itself.

Acceptance

  • output/PROTOCOL.md exists
  • includes extraction schema and protocol clause IDs
  • is operational enough for downstream screening

Non-goals

  • writing final synthesis prose
  • screening candidate papers

How to use it

Copy the folder

Take willoscar/protocol-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.