agentsclimarketplace

Review community

Skill jentic/jentic-api-scorecard/.claude/skills/review-community

Review a pull request authored by someone other than the current GitHub user, applying the team's diplomatic review-comments tone. Use when the PR author's GitHub login differs from the current user's `gh api user` login. For own PRs, use the built-in /review directly. Detects authorship automatically and refuses on self-authored PRs.From its SKILL.md

Install
npx -y skills add jentic/jentic-api-scorecard --skill review-community

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

  • 21 stars21 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

3.3 KB, as published. Nobody here has run it

/review-community — review someone else's PR with the community tone

This skill wraps the built-in /review command with two additions:

  1. Authorship guard — refuses to run if the PR author's GitHub login matches the current user's. For self-reviews, use /review directly with its default voice.
  2. Tone injection — inlines the diplomatic review-comments style into this turn so the tone applies without flipping the session output style. Activating the style via /config → Output style would replace Claude Code's default software-engineering system prompt; this skill avoids that by overlaying the tone on top of the default.

Tone for this review

The tone, structure, and constraints below are the source of truth for voice and feedback structure. Follow them for every comment drafted in this review.

!cat .claude/output-styles/review-comments.md

Phase 0 — Resolve PR and verify authorship

Run this once and use the values for the rest of the skill. set -e ensures any failed command stops the block; if it stops, surface the error to the user and do not proceed.

set -e

if [ -n "$ARGUMENTS" ]; then
  PR="$ARGUMENTS"
else
  PR=$(gh pr view --json number -q .number)
fi

PR_AUTHOR=$(gh pr view "$PR" --json author -q .author.login)
GH_USER=$(gh api user -q .login)

echo "PR=$PR"
echo "PR_AUTHOR=$PR_AUTHOR"
echo "GH_USER=$GH_USER"

Expected outcomes:

  • gh pr view with no argument fails (no PR for current branch) → stop and ask the user for a PR number or URL. Don't guess.
  • gh api user fails or returns empty $GH_USER → stop. The authorship guard cannot run without a confirmed login. Tell the user to authenticate (gh auth status) and try again.
  • $PR_AUTHOR equals $GH_USER → stop. Tell the user this is their own PR and to use /review directly. Do not proceed.
  • $PR_AUTHOR differs from $GH_USER → continue. State who authored the PR before starting the review, so the user has confirmation the guard saw the right author.

Phase 1 — Run the review

Invoke the built-in /review skill against $PR via the Skill tool. The tone instructions inlined in "Tone for this review" above apply to all comments drafted in this turn.

If the user asks follow-up questions in subsequent turns ("expand point 3," "draft the GitHub comment for line 42"), the inlined tone instructions will not carry over automatically. Re-read the style file when needed. A session-level voice lock is possible via /config → Output style → review-comments, but it replaces Claude Code's default software-engineering system prompt — not recommended unless the whole session is review work.

Out of scope

Severity grouping, technical depth, and what gets flagged remain whatever the built-in /review does — this skill only adds the authorship guard and the tone overlay.

Keep looking

Skills are one crate of 627,801. 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.