mcpbeat

Rubric Writer

willoscar/rubric-writer

| Use when `paper-review` has claims plus evidence gaps and needs the final referee-style report.

985 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 rubric-writer

What comes with it

2 523 bytes besides the instruction
scripts/run.py

The instruction itself

7 sections, as written by the author

Rubric Writer

Transforms review evidence artifacts into the final paper-review deliverable.

Inputs

Required:

  • output/CLAIMS.md
  • output/MISSING_EVIDENCE.md

Optional:

  • output/NOVELTY_MATRIX.md
  • DECISIONS.md

Output

  • output/REVIEW.md

Contract

The review must expose stable sections:

  • ### Summary
  • ### Novelty
  • ### Soundness
  • ### Clarity
  • ### Impact
  • ### Major Concerns
  • ### Minor Comments
  • ### Recommendation

Every major concern must cite its claim_id or gap_id. This is the

traceability interface consumed by the paper-review scorecard.

Script boundary

scripts/run.py should:

  • read prior review artifacts
  • render the stable rubric sections
  • keep the review bounded and traceable

It should not re-parse the manuscript from scratch or perform retrieval.

Acceptance

  • output/REVIEW.md exists
  • includes all stable rubric sections
  • recommendation is explicit

Non-goals

  • deep manuscript parsing
  • novelty retrieval
  • writing an author rebuttal

How to use it

Copy the folder

Take willoscar/rubric-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.