Automated Cherry Studio review for local branches, PRs, commits, files, architecture docs, and repository skills. Use for code or documentation reviews that need project-specific naming, main/renderer/shared placement and dependency rules, IpcApi and DataApi boundaries, lifecycle/service ownership, renderer hooks, React/UI conventions, and tests. Supports single-agent review with interactive fix selection or multi-agent reviewer-verifier review with risk-based auto-fix. To diagnose gaps in the skill after a review session, run `/gh-pr-review diag`.
76
93%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Outsider-authored free text is the PR body/comments (e.g., `PR_BODY` from `gh pr view ... --json ... body` and PR comment bodies from `gh api repos/{OWNER_REPO}/pulls/{number}/comments`), which are read in `references/pr-review.md` Step 1–3 and then incorporated into downstream reviewer/verifier LLM prompts as motivation/evidence.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The PR-review flow requires installing a remote gh extension via the command "gh extension install EurFelux/gh-pr-review" (EurFelux/gh-pr-review), which would fetch and install/execute remote code at runtime (references/pr-review.md:189-192).
49c351a
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.