Code Review
vinvcn/mattpocock-skills-zh-CN
从固定点（commit、branch、tag 或 merge-base）开始，按 Standards（代码是否符合本仓库记录的编码标准？）和 Spec（代码是否符合来源 issue/spec 的要求？）两个轴线审查变更。两个审查会在并行子代理中运行，并并排报告。适用于用户想审查 branch、PR、进行中的变更，或要求“review since X”时。
Reviews a pull request, staged changes or a file by sending the diff to specialist reviewer agents in parallel, then merges their findings into one compact report.
Install Parallel Specialist PR Review
$ npx skills add poshan0126/dotclaude --skill pr-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install poshan0126/dotclaude pr-review --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/poshan0126/dotclaude.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/pr-review .claude/skills/pr-review && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "pr-review" agent skill from https://github.com/poshan0126/dotclaude/tree/main/skills/pr-review into .claude/skills/pr-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-review", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/poshan0126/dotclaude/tree/main/skills/pr-reviewType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add poshan0126/dotclaude --skill pr-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install poshan0126/dotclaude pr-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/poshan0126/dotclaude.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/pr-review .agents/skills/pr-review && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "pr-review" agent skill from https://github.com/poshan0126/dotclaude/tree/main/skills/pr-review into .agents/skills/pr-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-review", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add poshan0126/dotclaude --skill pr-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install poshan0126/dotclaude pr-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/poshan0126/dotclaude.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/pr-review .cursor/skills/pr-review && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "pr-review" agent skill from https://github.com/poshan0126/dotclaude/tree/main/skills/pr-review into .cursor/skills/pr-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-review", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/poshan0126/dotclaude.git --path skills/pr-review--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add poshan0126/dotclaude --skill pr-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install poshan0126/dotclaude pr-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/poshan0126/dotclaude.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/pr-review .gemini/skills/pr-review && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "pr-review" agent skill from https://github.com/poshan0126/dotclaude/tree/main/skills/pr-review into .gemini/skills/pr-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-review", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install poshan0126/dotclaude pr-reviewInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add poshan0126/dotclaude --skill pr-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/poshan0126/dotclaude.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/pr-review .github/skills/pr-review && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "pr-review" agent skill from https://github.com/poshan0126/dotclaude/tree/main/skills/pr-review into .github/skills/pr-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-review", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add poshan0126/dotclaude --skill pr-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install poshan0126/dotclaude pr-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/poshan0126/dotclaude.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/pr-review .opencode/skills/pr-review && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "pr-review" agent skill from https://github.com/poshan0126/dotclaude/tree/main/skills/pr-review into .opencode/skills/pr-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-review", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
pr-review- GitHub stars
- 870
- Token cost
- ~1.7k tokens
- SKILL.md length
- 745 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- MIT
At a glance
Reviews a pull request, staged changes or a file by sending the diff to specialist reviewer agents in parallel, then merges their findings into one compact report.
- Works in 4 steps: Determine Scope → PR Quality Check (PR path only) → Code Review (fan out to specialists in… → …
- Reviewing a pull request before merge with several specialist perspectives
- SKILL.md covers Verbosity, Step 1: Determine Scope, Step 2: PR Quality Check (PR… and Step 3: Code Review (fan out…, plus 1 more section
- Calls gh and git
What it does
This skill reviews a PR, staged changes or a specific file by fanning the work out to specialist reviewer agents in parallel and merging their findings into one report. Scope comes from the argument: a PR number fetches it with gh, no argument detects a PR for the current branch and falls back to staged and then unstaged diffs, the word staged reviews the staged diff, and a file path reviews that file. If there is nothing to review it says so and stops.
On the PR path it first checks the PR itself: a descriptive title under 72 characters, a description that gives the why and a test plan, size flagged above 500 changed lines, the base branch, CI status and unresolved review comments. A general code reviewer always runs, and other specialists, covering security, performance, silent failures, test quality and docs, join depending on what the diff contains. Output is one line per finding by default, and a verbose option gives full multi-field entries and a fuller synthesis template. Allowed tools are limited to read-only git and gh commands.
When your agent uses it
- Reviewing a pull request before merge with several specialist perspectives
- Checking staged changes before committing
- Reviewing one file for correctness, security and test quality
Example prompts
- “Review PR 123 and give me a compact report.”
- “Review my staged changes in verbose mode.”
- “Review src/auth/session.ts for security problems and silent failures.”
Requirements
- The gh command-line tool for pull request reviews
- Pre-approved tools (allowed-tools): Bash(git diff *), Bash(git log *), Bash(gh pr view *), Bash(gh pr diff *), Bash(gh pr checks *), Bash(gh api *)
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 94b84b9. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
Bash(git diff *)Bash(git log *)Bash(gh pr view *)Bash(gh pr diff *)Bash(gh pr checks *)Bash(gh api *)
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
ghgit
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Parallel Specialist PR Review loads about 1.7k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 745 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from poshan0126/dotclaude at commit 94b84b9, republished under its MIT licence (© poshan0126). 745 words, ~1,734 tokens.
Download SKILL.mdSave it as
.claude/skills/pr-review/SKILL.md (or your agent's skills folder).- name
- pr-review
- description
- Review code changes or a pull request. Delegates to specialist agents (code quality, security, performance, silent failures, test quality, docs) in parallel.
- allowed-tools
- Bash(git diff *), Bash(git log *), Bash(gh pr view *), Bash(gh pr diff *), Bash(gh pr checks *), Bash(gh api *)
- argument-hint
- [PR number | staged | file path | omit to auto-detect]
- disable-model-invocation
- true
Review code changes by delegating to specialist agents in parallel and synthesizing a unified report. Works with PRs, staged changes, or specific files.
Verbosity
Check $ARGUMENTS for the word verbose. Strip it from the argument string before parsing the rest.
- Default: terse output. Each finding is one line (
file:line: issue (fix: hint)). Synthesis report stays compact. verbose: full breakdown. Each finding gets the multi-field block (Severity, Confidence, etc.). Synthesis report uses the full template.
When dispatching reviewers in Step 3, include the word verbose in each Task call's prompt only if the user asked for it. Otherwise omit; the reviewers default to terse.
Step 1: Determine Scope
Parse $ARGUMENTS to determine what to review:
- PR number (e.g.,
123or#123): fetch withgh pr view $ARGUMENTS. This is the full PR review path (includes PR quality checks in Step 2). - No argument: try
gh pr viewto detect a PR for the current branch. If a PR exists, use it. If not, fall back togit diff --cached(staged), thengit diff(unstaged). staged: reviewgit diff --cached. If nothing staged, fall back togit diff.- File path: review that specific file's current state.
If there are no changes to review, say so and stop.
Step 2: PR Quality Check (PR path only)
Skip this step if reviewing staged changes or a file. Jump to Step 3.
When reviewing a PR, fetch and check:
- PR title, description/body, author, base branch, head branch
gh pr diff $NUMBERfor the full diffgh pr checks $NUMBERfor CI statusgh api repos/{owner}/{repo}/pulls/$NUMBER/commentsfor review comments
Review the PR itself before the code:
- Title: descriptive and under 72 chars?
- Description: explains the why? Includes a test plan? Flag if empty or template-only.
- Size: count changed files and lines. Flag if >500 lines changed (suggest splitting).
- Base branch: targeting the right branch?
- CI status: passing, failing, or pending? If failing, note which checks. Fix CI first.
- Unresolved comments: list open review threads with file:line and comment text.
Step 3: Code Review (fan out to specialists in parallel)
Decide which reviewers apply by reading the diff content, not just file paths:
| Reviewer | When to include |
|---|---|
code-reviewer | Always. Universal correctness pass. |
silent-failure-hunter | Any diff touching error handling, catch blocks, fallbacks, retries, or async flows. In practice: almost every code diff. Skip only for pure-docs, config-only, or static-asset diffs. |
pr-test-analyzer | Tests were added or changed, OR behavior changed without any test change (that absence is itself the finding). Skip for pure-docs or config diffs. |
security-reviewer | Auth, input handling, queries, tokens, session management, file path construction, SQL or HTML or template strings. |
performance-reviewer | Endpoints, DB queries, loops over collections, caching, connection management. Skip for pure-docs, config-only, or static-asset diffs. |
doc-reviewer | .md changes, significant docstring or JSDoc changes, API docs. |
Show full SKILL.md (284 more words)Show less
Dispatch all applicable reviewers in PARALLEL. Send one message that contains one Agent/Task tool call per applicable reviewer. Do NOT invoke them sequentially. Parallel dispatch cuts wall-clock time from N times the slowest review to roughly the slowest single review, with no extra token cost. Each call looks like:
Agent(subagent_type: "code-reviewer",
prompt: "Review <scope>. <verbose?> Output one confidence score (0-100) per finding.")Ask every reviewer to attach a confidence score per finding — Step 4 uses them.
If only one reviewer applies (a pure-docs diff, for example), a single Task call is fine. Skip the parallel pattern when there's nothing to parallelize.
While the reviewers run, you can read the PR description, recent CI logs, or open comments to enrich the synthesis in Step 4. Don't wait idly.
Step 4: Synthesize Report
Use the terse template by default. Use the verbose template only if the user passed verbose.
Default (terse)
For PR reviews:
## PR Review: #[number]: [title]
[base] -> [head]. [N files, +X/-Y lines]. CI: [pass | fail: <checks>]. PR quality: [ok | issues: <list>].
### Findings ([N])
- [agent] file:line: issue (fix: hint)
- [agent] file:line: issue (fix: hint)
### Verdict
[Ready to merge | Needs changes: <one-line blocker>]For non-PR reviews (staged or file):
## Review ([scope])
[N findings from <agents>]:
- [agent] file:line: issue (fix: hint)
- [agent] file:line: issue (fix: hint)If no findings, output a single line: "No issues found across [agents]."
Verbose (when the user passed verbose)
For PR reviews:
## PR Review: #[number]: [title]
**Author**: [author] | **Base**: [base] -> **Head**: [head] | **Changed**: [N files, +X/-Y lines]
### PR Quality
- Title: [ok / needs improvement]
- Description: [ok / missing test plan / empty]
- Size: [ok / large, consider splitting]
- CI: [passing / failing, list failures]
- Unresolved comments: [none / list]
### Code Review
#### Critical / High
- [Agent] File:Line: issue
#### Medium
- [Agent] File:Line: issue
#### Low
- [Agent] File:Line: issue
### Verdict
[Ready to merge / Needs changes, summarize blockers]For non-PR reviews (staged or file):
## Review Summary
**Scope**: [staged changes / file path]
**Agents run**: [list]
### Critical / High
- [Agent] File:Line: issue
### Medium / Low
- [Agent] File:Line: issue
### Passed
- [areas with no issues]Merging, confidence, and deconfliction (both templates)
- Deduplicate findings that overlap between agents; attribute the merged finding to the agent with the most specific evidence.
- Confidence buckets: 90-100 → report as findings to act on; 80-89 → report under a
Considersubheading; anything an agent shipped below 80 shouldn't exist — drop it. - Deconfliction: when two agents flag the same lines with different fixes, prefer the more specific domain — security-reviewer over code-reviewer on input handling; performance-reviewer over code-reviewer on complexity if the path is hot, code-reviewer otherwise; silent-failure-hunter over code-reviewer on error handling. Never present two conflicting fixes for the same lines without saying which to apply.
- Attribute each finding to the agent that found it.
© poshan0126, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/pr-review of poshan0126/dotclaude.
Open the folder on GitHubat commit 94b84b9
Compare with similar skills
Parallel Specialist PR Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Parallel Specialist PR Review this skillposhan0126/dotclaude | 870 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Code Reviewvinvcn/mattpocock-skills-zh-CN | 4.7k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Aif Reviewunxed/f4 | 243 | — | ~3.3k | Automated safety check: Pass | BSD-3-Clause | |
| Open Code Review CLIalibaba/open-code-review | 46k | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| GitHub Review Iterationprisma/orm | 48k | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Understand Diff AnalysisEgonex-AI/Understand-Anything | 86k | — | ~1.4k | Automated safety check: Pass | MIT |
Similar skills
Aif Review
unxed/f4
Perform code review on staged changes or a pull request. An agent skill from unxed/f4.
Open Code Review CLI
alibaba/open-code-review
Runs the ocr command-line tool to review Git changes, a commit or a branch comparison with an AI model, returning line-level comments and optionally applying fixes.
- Official
GitHub Review Iteration
prisma/orm
Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.
Understand Diff Analysis
Egonex-AI/Understand-Anything
Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.
Code Review
flutter/flutter
Performs a comprehensive, multi-step code review of pull requests or local code changes, using iterative refinement (generation, critique, synthesis) to ensure high-quality, actionable feedback.
More from poshan0126/dotclaude
All 14 skills in this repoSession Catchup and Handoff
poshan0126/dotclaude
Rebuilds working context after /clear by reading a handoff note and the branch's git state, or writes that handoff note before a session ends.
Context Budget Check
poshan0126/dotclaude
Estimates the per-turn token cost of a project's .claude folder and CLAUDE.md, split into always-loaded, path-scoped and invoked-only files, and flags what runs over budget.
Codebase Onboarding Tour
poshan0126/dotclaude
Builds a quick mental model of an unfamiliar codebase by dispatching read-only Explore subagents and merging their findings into one brief.
dotclaude Project Setup
poshan0126/dotclaude
Scans a codebase, interviews you, and installs only the justified Claude Code rules, hooks, agents and skills, tailored to the project's stack.
Ship Changes
poshan0126/dotclaude
Walks through commit, push and pull request creation for the current changes, asking you to confirm the files, message, push and PR text at each step.
Interview-Driven Spec Writer
poshan0126/dotclaude
Interviews you about scope, behavior, edge cases and verification, then writes a self-contained SPEC.md that a fresh session can implement without this conversation.
Related
Works with
Categories
Questions about Parallel Specialist PR Review
What does Parallel Specialist PR Review do?
Reviews a pull request, staged changes or a file by sending the diff to specialist reviewer agents in parallel, then merges their findings into one compact report. This skill reviews a PR, staged changes or a specific file by fanning the work out to specialist reviewer agents in parallel and merging their findings into one report. Scope comes from the argument: a PR number fetches it with gh, no argument detects a PR for the current branch and falls back to staged and then unstaged diffs, the word staged reviews the staged diff, and a file path reviews that file.
When should I use Parallel Specialist PR Review?
Parallel Specialist PR Review fits situations like: reviewing a pull request before merge with several specialist perspectives; checking staged changes before committing; reviewing one file for correctness, security and test quality.
How do I install Parallel Specialist PR Review in Claude Code?
Run `npx skills add poshan0126/dotclaude --skill pr-review -a claude-code`. Or copy the skill folder (skills/pr-review in poshan0126/dotclaude) into .claude/skills/pr-review in your project. Claude Code loads it when a task matches its description.
How do I install Parallel Specialist PR Review in Codex?
Run `npx skills add poshan0126/dotclaude --skill pr-review -a codex`. Or copy the skill folder (skills/pr-review in poshan0126/dotclaude) into .agents/skills/pr-review in your project. Codex loads it when a task matches its description.
Can I use Parallel Specialist PR Review in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add poshan0126/dotclaude --skill pr-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pr-review, .gemini/skills/pr-review, .github/skills/pr-review and .opencode/skills/pr-review in your project.
What does Parallel Specialist PR Review need to run?
Going by SKILL.md and its folder, Parallel Specialist PR Review needs the command-line tools its instructions call (gh and git). Our summary lists: The gh command-line tool for pull request reviews. Its frontmatter pre-approves these tools: Bash(git diff *), Bash(git log *), Bash(gh pr view *), Bash(gh pr diff *), Bash(gh pr checks *), Bash(gh api *).
Does Parallel Specialist PR Review access the network?
SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Parallel Specialist PR Review safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Parallel Specialist PR Review use?
Parallel Specialist PR Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Parallel Specialist PR Review use?
About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Parallel Specialist PR Review?
Skills that share tags, products or a category with Parallel Specialist PR Review: Code Review (vinvcn/mattpocock-skills-zh-CN, 4.7k stars), Aif Review (unxed/f4, 243 stars), Open Code Review CLI (alibaba/open-code-review, 46k stars) and GitHub Review Iteration (prisma/orm, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Parallel Specialist PR Review?
poshan0126 (a GitHub user) maintains it in poshan0126/dotclaude, which has 870 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on August 27, 2026.
Source: poshan0126/dotclaude on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.