Agent skill

AI Review

使用 PaddlePaddle 仓库规则评审 Pull Request 和全仓库代码变更，覆盖正确性、兼容性、算子、分布式、数值、性能、安全、测试、构建和 PR 信息。当需要审查 Paddle 的代码、测试、算子 YAML、C++/CUDA/XPU kernel、Python API、分布式逻辑或 CI 配置时使用。

Apache-2.0Auto-check passedDevelopment

Install AI Review

skills CLI

$ npx skills add PaddlePaddle/Paddle --skill ai-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install PaddlePaddle/Paddle ai-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/PaddlePaddle/Paddle.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/ai-review .claude/skills/ai-review && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "ai-review" agent skill from https://github.com/PaddlePaddle/Paddle/tree/develop/.agents/skills/ai-review into .claude/skills/ai-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-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

$skill-installer install https://github.com/PaddlePaddle/Paddle/tree/develop/.agents/skills/ai-review

Type 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.

skills CLI

$ npx skills add PaddlePaddle/Paddle --skill ai-review -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install PaddlePaddle/Paddle ai-review --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/PaddlePaddle/Paddle.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/ai-review .agents/skills/ai-review && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "ai-review" agent skill from https://github.com/PaddlePaddle/Paddle/tree/develop/.agents/skills/ai-review into .agents/skills/ai-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-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.

skills CLI

$ npx skills add PaddlePaddle/Paddle --skill ai-review -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install PaddlePaddle/Paddle ai-review --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/PaddlePaddle/Paddle.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/ai-review .cursor/skills/ai-review && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "ai-review" agent skill from https://github.com/PaddlePaddle/Paddle/tree/develop/.agents/skills/ai-review into .cursor/skills/ai-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-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

$ gemini skills install https://github.com/PaddlePaddle/Paddle.git --path .agents/skills/ai-review

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add PaddlePaddle/Paddle --skill ai-review -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install PaddlePaddle/Paddle ai-review --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/PaddlePaddle/Paddle.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/ai-review .gemini/skills/ai-review && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "ai-review" agent skill from https://github.com/PaddlePaddle/Paddle/tree/develop/.agents/skills/ai-review into .gemini/skills/ai-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-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.

GitHub CLI

$ gh skill install PaddlePaddle/Paddle ai-review

Installs 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).

skills CLI

$ npx skills add PaddlePaddle/Paddle --skill ai-review -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/PaddlePaddle/Paddle.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/ai-review .github/skills/ai-review && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "ai-review" agent skill from https://github.com/PaddlePaddle/Paddle/tree/develop/.agents/skills/ai-review into .github/skills/ai-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-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.

skills CLI

$ npx skills add PaddlePaddle/Paddle --skill ai-review -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install PaddlePaddle/Paddle ai-review --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/PaddlePaddle/Paddle.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/ai-review .opencode/skills/ai-review && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "ai-review" agent skill from https://github.com/PaddlePaddle/Paddle/tree/develop/.agents/skills/ai-review into .opencode/skills/ai-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-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: ai-review
GitHub stars: 24k
Token cost: ~303 tokens
SKILL.md length: 57 words
Files: 3 (incl. references)
Skills in repo: 11
Repo updated: Oct 10, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Works in 5 steps: 阅读 PR 描述和完整 diff，确认变更目标、影响范围、兼容承诺和用户可见行为。 → 使用 rg… → 对照完整函数、相邻实现和现有测试验证候选问题，确认可复现或有明确代码证据后再报告。 → …
Tasks that involve Deep learning
SKILL.md covers 规则加载, 评审流程, 适用的已有 Skill and 基本原则
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

AI Review is an agent skill from PaddlePaddle/Paddle. 使用 PaddlePaddle 仓库规则评审 Pull Request 和全仓库代码变更，覆盖正确性、兼容性、算子、分布式、数值、性能、安全、测试、构建和 PR 信息。当需要审查 Paddle 的代码、测试、算子 YAML、C++/CUDA/XPU kernel、Python API、分布式逻辑或 CI 配置时使用。

Its SKILL.md is about 300 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `README.md` and `references/base-rules.md`).

It sits in Development, covering Deep learning and Pull requests. It works with Python, C++ and CUDA. The repository describes itself as: PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）. The licence is Apache-2.0.

When your agent uses it

Tasks that involve Deep learning
Tasks that involve Pull requests

Example prompts

“/ai-review”

Requirements

Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

阅读 PR 描述和完整 diff，确认变更目标、影响范围、兼容承诺和用户可见行为。
使用 rg 追踪定义、调用方、注册入口、配置入口、实现和测试；跨模块变更必须检查两端契约。
对照完整函数、相邻实现和现有测试验证候选问题，确认可复现或有明确代码证据后再报告。
评论指出具体位置、影响、触发条件和修改方向；不报告无依据的猜测、纯风格偏好或泛化建议。
按风险选择最接近变更的测试，并分别记录静态检查、CPU 验证和依赖 GPU/多卡/特定硬件的未完成验证。

What it can do on your machine

Read from SKILL.md and the folder at commit a48f1c3. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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

AI Review loads about 303 tokens when it runs, and up to ~1.7k if it reads all its reference files. Until then it costs about 42 tokens; SKILL.md has 57 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~42
When it runs · the whole SKILL.md, loaded when a task matches: ~303
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~1.7k

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 PaddlePaddle/Paddle at commit a48f1c3, republished under its Apache-2.0 licence (© PaddlePaddle). 57 words, ~303 tokens.

Download SKILL.mdSave it as .claude/skills/ai-review/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.

name: ai-review
description: 使用 PaddlePaddle 仓库规则评审 Pull Request 和全仓库代码变更，覆盖正确性、兼容性、算子、分布式、数值、性能、安全、测试、构建和 PR 信息。当需要审查 Paddle 的代码、测试、算子 YAML、C++/CUDA/XPU kernel、Python API、分布式逻辑或 CI 配置时使用。

AI Review

评审 Paddle 代码的实际行为和跨模块影响。优先级、评论格式和发布策略由调用方决定；本 skill 只提供仓库级评审规则。

规则加载

开始评审前读取 .agents/skills/ai-review/references/ 下的全部 Markdown 文件，必须包含基础规则。根据每个文件声明的适用路径和触发条件决定是否应用其他规则；不要仅因变更路径不同而跳过加载。

新增扩展规则时，在 references/ 下使用 kebab-case 文件名，并在文件开头写明适用路径、触发条件和可验证的规则来源。不要重复基础规则、评论格式或发布策略。

评审流程

阅读 PR 描述和完整 diff，确认变更目标、影响范围、兼容承诺和用户可见行为。
使用 rg 追踪定义、调用方、注册入口、配置入口、实现和测试；跨模块变更必须检查两端契约。
对照完整函数、相邻实现和现有测试验证候选问题，确认可复现或有明确代码证据后再报告。
评论指出具体位置、影响、触发条件和修改方向；不报告无依据的猜测、纯风格偏好或泛化建议。
按风险选择最接近变更的测试，并分别记录静态检查、CPU 验证和依赖 GPU/多卡/特定硬件的未完成验证。

更具体的扩展规则优先于基础规则；规则冲突且无法由代码或仓库约定判定时，向维护者确认。

适用的已有 Skill

涉及专门领域时同时读取对应 skill 的 references，并以实际源码为准：算子开发使用 paddle-op-dev，分布式设计使用 paddle-design-distributed，编译使用 paddle-build，调试使用 paddle-debug、paddle-design-compiler、paddle-eager-graph 或 paddle-phi-kernel。

基本原则

正确性、安全和兼容性优先于格式与命名。
分布式、算子和数值路径必须同时检查前向/反向、边界条件及回退路径。
行为变化必须有与风险匹配的单卡、多卡或设备覆盖；不能用 mock 掉被测逻辑的测试代替真实验证。
只依据源码、测试、文档和可复现的运行结果下结论；无法验证时明确说明环境限制。

Files

SKILL.md and 2 other files (references) in .agents/skills/ai-review of PaddlePaddle/Paddle.

SKILL.md
README.md
references/base-rules.md

Open the folder on GitHubat commit a48f1c3

Compare with similar skills

AI 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.

AI Review compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
AI Review this skillPaddlePaddle/Paddle	24k	—	~303	Automated safety check: Pass	Apache-2.0	yesterday
ExecuTorch Build Guidepytorch/executorch	5.1k	—	~2.3k	Automated safety check: Notes	Custom licence	yesterday
Ako4allTongmingLAIC/AKO4ALL	369	—	~4k	Automated safety check: Pass	MIT	26 days ago
The Art of Debuggingstas00/the-art-of-debugging	1.7k	—	~6.1k	Automated safety check: Notes	CC-BY-SA-4.0	4 days ago
Cutlass Cpp Kernelvipshop/cache-dit	1.3k	—	~2.2k	Automated safety check: Pass	Apache-2.0	yesterday
Code Reviewnstarman/quax	143	—	~3.2k	Automated safety check: Pass	Apache-2.0	today

Similar skills

ExecuTorch Build Guide
pytorch/executorch
Builds ExecuTorch from source: the Python package, C++ runtime, model runners, Android and iOS cross-compilation and backend-specific builds, with environment checks.
5.1k GitHub stars~2.3k tokensUpdated yesterday
DevelopmentAuto-check: notes
Ako4all
TongmingLAIC/AKO4ALL
Drive an agentic loop that iteratively optimizes a GPU kernel for maximum speedup.
369 GitHub stars~4k tokensUpdated 26 days ago
AI & LLM EngineeringAuto-check passed
The Art of Debugging
stas00/the-art-of-debugging
Condensed debugging method and tool recipes for Unix, Python and PyTorch programs: crashes, hangs, segfaults, wrong output, CUDA OOM, NaN values and slowness.
1.7k GitHub stars~6.1k tokensUpdated 4 days ago
DevelopmentAuto-check: notes
Cutlass Cpp Kernel
vipshop/cache-dit
A skill your agent uses when writing, debugging, porting, reviewing, or optimizing CUTLASS or CuTe C++ kernels and templates; navigating CUTLASS examples, collectives, epilogues, pipelines, GEMM…
1.3k GitHub stars~2.2k tokensUpdated yesterday
DevelopmentAuto-check passed
Code Review
nstarman/quax
A skill your agent uses when reviewing a pull request or diff in the quax repository.
143 GitHub stars~3.2k tokensUpdated today
DevelopmentAuto-check passed
Create Cuda Python Pull Request
NVIDIA/cuda-python
Official
Create a CUDA Python pull request from an approved personal or organization-owned fork, including the GitHub CLI GraphQL fallback for renamed organization-owned forks.
3.4k GitHub stars~1.1k tokensUpdated yesterday
DevelopmentAuto-check passed

More from PaddlePaddle/Paddle

All 11 skills in this repo

Paddle Build
PaddlePaddle/Paddle
A skill your agent uses when needing to compile, rebuild, or install Paddle from source after code changes.
24k GitHub stars~1k tokensUpdated yesterday
Auto-check passed
Paddle Design Compiler
PaddlePaddle/Paddle
A skill your agent uses when working with Paddle 3.0 compiler full pipeline: SOT (Symbolic Opcode Translator) for bytecode-level dy2st graph capture, PIR (Paddle IR) for SSA-based intermediate…
24k GitHub stars~3.6k tokensUpdated yesterday
Auto-check passed
Paddle Design Distributed
PaddlePaddle/Paddle
A skill your agent uses when working with Paddle's distributed training system: understanding parallelism strategies (DP, ZeRO, TP, PP, SP), semi-automatic parallel with ProcessMesh + shardtensor…
24k GitHub stars~660 tokensUpdated yesterday
Auto-check passed
Paddle Eager Graph
PaddlePaddle/Paddle
A skill your agent uses when navigating Paddle eager-mode (dynamic graph) source code, tracing forward/backward execution, debugging autograd issues, understanding PyLayer, or investigating…
24k GitHub stars~562 tokensUpdated yesterday
Auto-check passed
Paddle Phi Kernel
PaddlePaddle/Paddle
A skill your agent uses when working with Paddle's PHI kernel system: registering new kernels, debugging kernel selection/dispatch, understanding code auto-generation from YAML, or implementing…
24k GitHub stars~656 tokensUpdated yesterday
Auto-check passed
Paddle Debug
PaddlePaddle/Paddle
在 Paddle 代码库中定位问题并输出高质量调试报告的专用技能。当遇到以下场景时优先使用：(1) Paddle 框架 bug 调试，(2) 算子实现问题排查，(3) 训练脚本异常诊断，(4) 分布式训练故障定位，(5) CUDA/GPU 相关错误处理，(6) 需要生成结构化调试报告。
24k GitHub stars~1.4k tokensUpdated yesterday
Auto-check passed

Works with

Questions about AI Review

What does AI Review do?

使用 PaddlePaddle 仓库规则评审 Pull Request 和全仓库代码变更，覆盖正确性、兼容性、算子、分布式、数值、性能、安全、测试、构建和 PR 信息。当需要审查 Paddle 的代码、测试、算子 YAML、C++/CUDA/XPU kernel、Python API、分布式逻辑或 CI 配置时使用。. AI Review is an agent skill from PaddlePaddle/Paddle.

When should I use AI Review?

AI Review fits situations like: tasks that involve Deep learning; tasks that involve Pull requests.

How do I install AI Review in Claude Code?

Run `npx skills add PaddlePaddle/Paddle --skill ai-review -a claude-code`. Or copy the skill folder (.agents/skills/ai-review in PaddlePaddle/Paddle) into .claude/skills/ai-review in your project. Claude Code loads it when a task matches its description.

How do I install AI Review in Codex?

Run `npx skills add PaddlePaddle/Paddle --skill ai-review -a codex`. Or copy the skill folder (.agents/skills/ai-review in PaddlePaddle/Paddle) into .agents/skills/ai-review in your project. Codex loads it when a task matches its description.

Can I use AI 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 PaddlePaddle/Paddle --skill ai-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/ai-review, .gemini/skills/ai-review, .github/skills/ai-review and .opencode/skills/ai-review in your project.

What does AI Review need to run?

SKILL.md names no scripts, command-line tools or credentials: AI Review is instructions for the agent only. Our summary lists: Python 3.

Does AI Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is AI 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 AI Review use?

AI Review is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does AI Review use?

About 303 tokens (SKILL.md is roughly 1.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.4k tokens, read only when the agent opens those files.

What are the alternatives to AI Review?

Skills that share tags, products or a category with AI Review: ExecuTorch Build Guide (pytorch/executorch, 5.1k stars), Ako4all (TongmingLAIC/AKO4ALL, 369 stars), The Art of Debugging (stas00/the-art-of-debugging, 1.7k stars) and Cutlass Cpp Kernel (vipshop/cache-dit, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI Review?

PaddlePaddle (a GitHub organization) maintains it in PaddlePaddle/Paddle, which has 24,120 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 10, 2026.

Source: PaddlePaddle/Paddle on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install AI Review

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

AI Review

规则加载

评审流程

适用的已有 Skill

基本原则

Files

Compare with similar skills

Similar skills

More from PaddlePaddle/Paddle

Related

Questions about AI Review