agentsclimarketplace
Sign in

Review response matrix

Skill StaryMoon/review-response-matrix-skill/skills/review-response-matrix

Convert peer-review text into a traceable reviewer-comment matrix and response draft with stable IDs, categories, priorities, evidence fields, manuscript locations, owners, and completion status. Use for conference rebuttals, journal revisions, artifact reviews, design reviews, or any multi-comment response process.From its SKILL.md

Install
npx -y skills add StaryMoon/review-response-matrix-skill --skill review-response-matrix

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.6 KB, 267 tokens by cl100k_base, as published. Nobody here has run it

Review Response Matrix

Turn every reviewer concern into a trackable unit. Preserve the original wording; summaries help navigation but must never replace the source comment.

Workflow

  1. Save the complete reviews as Markdown or plain text. Keep reviewer headings when available.
  2. Initialize the matrix:
python3 scripts/build_response_matrix.py reviews.md --output output/review-response
  1. Inspect matrix.csv. Correct comment boundaries before drafting responses.
  2. For each ID, fill response, action, evidence, and manuscript_location. Use not_applicable only with a reason.
  3. Run validation after editing:
python3 scripts/build_response_matrix.py --validate output/review-response/matrix.csv
  1. Use response-draft.md as a working document, then adapt it to venue length and formatting rules.

Quality rules

  • Do not invent experiments, numbers, citations, or manuscript changes.
  • Quote enough of the original comment to make the response auditable.
  • Separate acknowledgement, answer, evidence, and manuscript change.
  • Mark promises as planned, not done.
  • Keep stable IDs when comments are reordered.

See references/response-patterns.md for concise response structures.

What ships with it: 3 files

7.3 KB alongside SKILL.md, 1 of them executable

agents/

references/

scripts/

Gives 0 of the 12 instructions most review quality skills give in 267 tokens

Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-07

  • Ask questions one at a timein 81 of 1048, across 64 files
  • Provide a recommended answer for each questionin 73 of 1048, across 50 files
  • Explore the codebase instead of asking answerable questionsin 66 of 1048, across 42 files
  • Resolve dependencies between decisions one-by-onein 42 of 1048, across 17 files
  • Interview the user relentlessly about the planin 38 of 1048, across 13 files
  • Order findings by severityin 31 of 1048
  • Resolve each branch of the decision treein 27 of 1048, across 5 files
  • Run a grilling sessionin 26 of 1048, across 5 files
  • Update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 11 files
  • Propose precise canonical terms for vague languagein 25 of 1048, across 7 files
  • Create documentation files lazilyin 24 of 1048, across 5 files
  • Assign severity to every findingin 24 of 1048

Said here and by no other author read

  • Save complete reviews as markdown or plain text
  • Initialize the matrix using build script
  • Inspect generated matrix and correct comment boundaries
  • Fill response, action, evidence, and manuscript location fields
  • Run validation after editing the matrix
  • Separate acknowledgement, answer, evidence, and manuscript change

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,144. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.