Cherry Studio PR Review

<!-- Based on https://github.com/Tencent/tgfx/tree/main/.codebuddy/skills/cr -->

<!-- Adapted for agent runtimes and the Cherry Studio tech stack -->

/gh-pr-review — Code Review

Automated code review for local branches, PRs, commits, and files. Detects the review target from arguments, then picks the review engine from diff size and runtime capability. Small diffs use single-agent review (references/local-review.md). Large diffs use the multi-agent reviewer–verifier flow (references/teams-review.md) only when independent subagents are available; otherwise they fall back to single-agent review with that limitation disclosed. PR targets add worktree setup and GitHub submission (references/pr-review.md) around the same engine-selection contract.

Cherry Studio-specific review rules live in references/cherry-review-guidance.md. Target review flows must load that file for code, mixed, architecture-doc, and project-skill reviews so reviewers can apply DataApi, service-boundary, renderer hook, React, UI, and type-contract checks without relying on memory. That reference also defines which internal docs, internal skills, external skills, and official websites to consult for each changed area; load only the relevant subset.

All user-facing text matches the user's language.

Interaction and interruption contract

Apart from the declared categories below, normal review is prompt-free: never ask for mode selection, fix confirmation, finding selection, or submission preview. A leaf flow may request input only when it explicitly declares one of these categories:

• Product decision — in an interactive session, the Product Demand gate may ask the current user for a decision the review cannot derive. In an automated session, record the impact and open decision without deciding for the user.
• Safety or environment blocker — continuing would require destructive action, new authority, or missing external configuration. Declared examples are a dirty/mismatched review worktree, a missing canonical remote, cleanup of unexplained changes, removal of a failed fix patch, and a pending review draft holding comments this run did not confirm. In an interactive session, preserve state and ask only for the decision needed to proceed.
• Explicit maintenance mode — diag and separately requested checklist maintenance are interactive selection flows outside normal review. They may ask for the declared edit selection or persistent checkout/branch target.

An automated session never waits for user input. At a product decision it continues record-only as specified below. At a safety/environment blocker it preserves state, stops the affected flow safely, and reports the exact blocker and required decision. In an explicit maintenance mode it reports candidates or missing destination information, applies no selection-dependent edits, and stops safely. No leaf flow may introduce another prompt category.

Review Stages

Every review runs these stages in order. A later stage reviews only what survived the earlier ones, so a stage never re-litigates an earlier verdict.

This table is the single source of truth for stage scope and references; a leaf flow may not widen, narrow, or re-reference a stage.

Stage applicability follows the changed content, not the commit label: a documentation-only diff still runs stages 3–5 when it changes Cherry architecture docs or project skills, and a code diff that also edits docs runs both reference sets for stages 4–5.

Stage 1: Product Demand gate

First inspect the semantics actually expressed or constrained by the change, then decide whether it affects product semantics, user-visible behavior, or product direction. Change labels are not sufficient evidence: internal refactors and non-user-facing fixes often have no product impact, while user-facing fixes, docs, tests, or tooling can record, lock, or alter product behavior.

When there is product impact, determine whether the direction is already established in the current review context. Treat it as established only when the current user explicitly decided it or an authoritative project artifact explicitly records the accepted behavior and its approval by the responsible project authority, such as a specification, an ADR, or an issue containing a maintainer decision that settles the expected behavior. Do not infer acceptance from issue state, labels, milestone, assignment, or a link from the PR. A change label, PR body, implementation, or test demonstrates author intent or current behavior but does not establish product approval on its own.

Classify the gate into exactly one state:

• No product impact: skip this stage entirely in both interactive and automated runs; say nothing about the skipped gate.
• Established direction: compare the change with the recorded decision. If it aligns, continue without asking for another product decision. If it conflicts, report the product-direction mismatch and stop the whole review immediately — do not run Consumer, Architecture, Implementation, or Style stages, and do not report code findings. Applying an existing decision is not making a new one.
• Open product decision:
  • Interactive session (default): summarize the change's effect on product functionality and semantics, and ask the current user for the unresolved product decision. Do not infer automation from PR authorship, review ownership, or whether the user authored the change. If the user rejects the direction, stop the whole review as above; if the user approves it, continue with the remaining stages.
  • Automated session (explicit only): use this mode only when the invocation prompt or workflow context explicitly identifies a headless, CI, batch, or other automated run. Make no product decision on the user's behalf. Run the remaining stages, and in the final report summarize the product impact, the direction the change takes, and the points needing human confirmation. Never phrase this as product approval having been obtained.

Authority model

A review request authorizes analysis and reporting only. The review target, review depth, and reviewer–verifier confidence never grant execution authority; authority is granted explicitly at invocation time, and execution is prompt-free only after it has been granted:

• Report-only (default): every review, any target — findings are reported with fix guidance. No working-tree edits, no GitHub writes.
• Fix (explicit): granted only by the invocation — fix in $ARGUMENTS or equivalent explicit user wording ("review and fix …"). Local targets only. What each risk level then permits is owned by references/judgment-matrix.md § Handling by Risk Level; this section grants the authority and never restates the mapping. Applying fixes makes the session a coding task, so it must end with the validation selected per § Validation after applied fixes below.
• Submit (explicit): granted only by the invocation — submit in $ARGUMENTS or equivalent explicit user wording. PR flows then submit all confirmed findings without per-comment prompts. Approving or merging always requires its own explicit request.

Validation after applied fixes

Never run local lint, test, or format during a review that edited nothing. When fixes were applied, select the validation matching the changed surface, following AGENTS.md § Operational Rules ("Check what you changed, not the whole repo"), and report the results:

• Docs/markdown-only fixes — including this skill's own files — run pnpm docs:check.
• Code fixes run pnpm lint (which already ends with pnpm format, so never invoke format again) plus the tests covering the change: a per-project wrapper such as pnpm test:main <file> or pnpm exec vitest run <file>. Never pnpm test <path> — that script chains several vitest invocations and the path reaches only the last one.
• Reserve the full pnpm test for a broad change whose affected tests cannot be named, and use pnpm test:lint when the CI-equivalent lint gate matters (pnpm lint tolerates oxlint warnings that CI denies).