mcpField
R
rubric-writer

rubric-writer

github.com/willoscarDocuments51746 installsUpdated 3w ago
Repository

About rubric-writer

rubric-writer turns existing paper-review evidence artifacts into a structured review document for the final stage of a review pipeline. Its fixed sections and claim or gap references keep major concerns traceable; it does not retrieve literature or re-parse the manuscript.

Key features

  1. 01Render stable review sections
  2. 02Use claims and missing-evidence inputs
  3. 03Link major concerns to claim or gap IDs
  4. 04Produce an explicit recommendation

Use cases

  1. 01Turn review artifacts into REVIEW.md
  2. 02Prepare traceable major concerns
  3. 03Complete the final paper-review stage

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/willoscar/research-units-pipeline-skills --skill rubric-writer

After installing, type/rubric-writerin Claude Code to confirm it loaded.

Bundled filesscripts/run.py

Details

From the project README

Rubric Writer

Triggers & routing

  • Trigger: rubric review, referee report, peer review write-up, 审稿报告, REVIEW.md.
  • Use when: paper-review pipeline 的最后阶段（C3），已有 output/CLAIMS.md + output/MISSING_EVIDENCE.md（以及可选 novelty matrix）。

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

Comments

Markdown supported