Cherry-studio gh-pr-review

Automated code review for local branches, PRs, commits, and files. Supports single-agent review with interactive fix selection, or multi-agent deep review with reviewer-verifier adversarial mechanism and risk-based auto-fix.

install

source · Clone the upstream repo

git clone https://github.com/CherryHQ/cherry-studio

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/CherryHQ/cherry-studio "$T" && mkdir -p ~/.claude/skills && cp -r "$T/.agents/skills/gh-pr-review" ~/.claude/skills/cherryhq-cherry-studio-gh-pr-review && rm -rf "$T"

manifest: .agents/skills/gh-pr-review/SKILL.md

source content

/gh-pr-review — Code Review

Automated code review for local branches, PRs, commits, and files. Detects review mode from arguments and routes to the appropriate review flow — either quick single-agent review with interactive fix selection, or multi-agent deep review with risk-based auto-fix.

All user-facing text matches the user's language. All questions and option selections MUST use your interactive dialog tool (e.g. AskUserQuestion) — never output options as plain text. Do not proceed until the user replies. When presenting multi-select options: ≤4 items → one question. >4 items → group by priority or category (each group ≤4 options), then present all groups as separate questions in a single prompt.

Route

Run pre-checks, then match the first applicable rule top-to-bottom:

```
git branch --show-current
```
→ record whether on main/master.
```
git status --porcelain
```
→ record whether uncommitted changes exist.
Check whether the current environment supports Agent tool with parallel subagents (agent teams).

#	Condition	Action
1	`$ARGUMENTS` is `diag`	→ `references/diagnosis.md`
2	`$ARGUMENTS` is a PR number or URL containing `/pull/`	→ `references/pr-review.md`
3	Agent teams NOT supported	→ `references/local-review.md`
4	Uncommitted changes exist	→ `references/local-review.md`
5	On main/master branch	→ `references/local-review.md`
6	Everything else	→ Question below

Each

→

means:

Read

the target file and follow it as the sole remaining instruction. Ignore all sections below. Do NOT review from memory or habit — each target file defines specific constraints on how to obtain diffs, apply fixes, and submit results.

Question

Ask a single question: "Agent Teams is available (multiple agents working in parallel). Enable multi-agent review with reviewer–verifier adversarial mechanism and auto-fix?" Provide 4 options:

Option	Description
Teams + auto-fix low & medium risk (recommended)	Multi-agent review; auto-fix most issues, only confirm high-risk ones (e.g., API changes, architecture).
Teams + auto-fix low risk	Multi-agent review; auto-fix only the safest issues (e.g., null checks, typos, naming). Confirm everything else.
Teams + auto-fix all	Multi-agent review; auto-fix everything. Only issues affecting test baselines are deferred.
Single-agent + manual fix	Single-agent review; interactively choose which issues to fix afterward.

Hand off

Option	→	FIX_MODE
Teams + auto-fix low & medium risk (recommended)	`references/teams-review.md`	low_medium
Teams + auto-fix low risk	`references/teams-review.md`	low
Teams + auto-fix all	`references/teams-review.md`	full
Single-agent + manual fix	`references/local-review.md`	—

Pass

$ARGUMENTS

to the target file. For teams-review, also pass

FIX_MODE

(low / low_medium / full).