Agent skill

Review PR

Review a libuipc pull request end-to-end: checkout the PR, summarize changes, list files for the human reviewer, and perform a domain-aware AI review covering physics correctness, backend…

Apache-2.0Auto-check passedDevelopment

Install Review PR

skills CLI

$ npx skills add spiriMirror/libuipc --skill review-pr -a claude-code

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

GitHub CLI

$ gh skill install spiriMirror/libuipc review-pr --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/spiriMirror/libuipc.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/review-pr .claude/skills/review-pr && 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 "review-pr" agent skill from https://github.com/spiriMirror/libuipc/tree/main/.cursor/skills/review-pr into .claude/skills/review-pr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-pr", 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/spiriMirror/libuipc/tree/main/.cursor/skills/review-pr

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 spiriMirror/libuipc --skill review-pr -a codex

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

GitHub CLI

$ gh skill install spiriMirror/libuipc review-pr --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/spiriMirror/libuipc.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.cursor/skills/review-pr .agents/skills/review-pr && 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 "review-pr" agent skill from https://github.com/spiriMirror/libuipc/tree/main/.cursor/skills/review-pr into .agents/skills/review-pr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-pr", 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 spiriMirror/libuipc --skill review-pr -a cursor

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

GitHub CLI

$ gh skill install spiriMirror/libuipc review-pr --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/spiriMirror/libuipc.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.cursor/skills/review-pr .cursor/skills/review-pr && 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 "review-pr" agent skill from https://github.com/spiriMirror/libuipc/tree/main/.cursor/skills/review-pr into .cursor/skills/review-pr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-pr", 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/spiriMirror/libuipc.git --path .cursor/skills/review-pr

--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 spiriMirror/libuipc --skill review-pr -a gemini-cli

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

GitHub CLI

$ gh skill install spiriMirror/libuipc review-pr --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/spiriMirror/libuipc.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.cursor/skills/review-pr .gemini/skills/review-pr && 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 "review-pr" agent skill from https://github.com/spiriMirror/libuipc/tree/main/.cursor/skills/review-pr into .gemini/skills/review-pr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-pr", 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 spiriMirror/libuipc review-pr

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 spiriMirror/libuipc --skill review-pr -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/spiriMirror/libuipc.git skills-src && mkdir -p .github/skills && cp -r skills-src/.cursor/skills/review-pr .github/skills/review-pr && 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 "review-pr" agent skill from https://github.com/spiriMirror/libuipc/tree/main/.cursor/skills/review-pr into .github/skills/review-pr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-pr", 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 spiriMirror/libuipc --skill review-pr -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 spiriMirror/libuipc review-pr --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/spiriMirror/libuipc.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.cursor/skills/review-pr .opencode/skills/review-pr && 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 "review-pr" agent skill from https://github.com/spiriMirror/libuipc/tree/main/.cursor/skills/review-pr into .opencode/skills/review-pr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-pr", 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: review-pr
GitHub stars: 335
Token cost: ~1.7k tokens
SKILL.md length: 504 words
Files: 1
Skills in repo: 16
Repo updated: Oct 3, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Review a libuipc pull request end-to-end: checkout the PR, summarize changes, list files for the human reviewer, and perform a domain-aware AI review covering physics correctness, backend…

Works in 5 steps: Checkout and fetch metadata → Present summary to the human reviewer → AI review — libuipc-specific checklist → …
The user provides a PR number
SKILL.md covers Architecture primer (read… and Workflow
Calls gh

What it does

Review PR is an agent skill from spiriMirror/libuipc. Review a libuipc pull request end-to-end: checkout the PR, summarize changes, list files for the human reviewer, and perform a domain-aware AI review covering physics correctness, backend architecture, C++ style, GPU code, and Python bindings. Optionally post review comments via gh. Use when the user provides a PR number, asks to review a PR, or wants to inspect a libuipc GitHub PR.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Pull requests and Backend development. It works with C++, Python and GitHub. The repository describes itself as: A Modern Python and C++20 Library of Unified Incremental Potential Contact. The licence is Apache-2.0.

When your agent uses it

The user provides a PR number
Asks to review a PR
Wants to inspect a libuipc GitHub PR

Example prompts

“/review-pr”

Requirements

Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Checkout and fetch metadata
Present summary to the human reviewer
AI review — libuipc-specific checklist
Output format
Post comments via gh (when asked)

What it can do on your machine

Read from SKILL.md and the folder at commit 9c748a7. 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
Shell commands in SKILL.md call:
- gh
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use gh, 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

Review PR loads about 1.7k tokens when it runs. Until then it costs about 99 tokens; SKILL.md has 504 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~99
When it runs · the whole SKILL.md, loaded when a task matches: ~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 spiriMirror/libuipc at commit 9c748a7, republished under its Apache-2.0 licence (© spiriMirror). 504 words, ~1,742 tokens.

Download SKILL.mdSave it as .claude/skills/review-pr/SKILL.md (or your agent's skills folder).

name: review-pr
description: Review a libuipc pull request end-to-end: checkout the PR, summarize changes, list files for the human reviewer, and perform a domain-aware AI review covering physics correctness, backend architecture, C++ style, GPU code, and Python bindings. Optionally post review comments via `gh`. Use when the user provides a PR number, asks to review a PR, or wants to inspect a libuipc GitHub PR.

libuipc PR Review

Architecture primer (read before reviewing)

libuipc is a GPU-accelerated Incremental Potential Contact (IPC) simulation library (C++20 + optional Python/pybind11).

Layer split:

Layer	Path	Role
Core	`src/core/`, `include/uipc/`	Engine lifecycle, Scene/World, geometry attribute ECS
Geometry	`src/geometry/`	Mesh algorithms; libigl, TBB, Octree, embedded C++ METIS
Constitution	`src/constitution/`	Material / constraint implementations
I/O	`src/io/`	Scene + mesh serialisation
Sanity check	`src/sanity_check/`	Pre-sim scene validation
Backends	`src/backends/<name>/`	Physics engines as runtime-loaded MODULE DLLs
Pybind	`src/pybind/`	Thin pybind11 wrapper; mirrors C++ submodules

Backend plugin ABI (src/backends/common/module.h):

Exports: uipc_init_module, uipc_create_engine, uipc_destroy_engine
Base classes: SimEngine → ISimSystem → subsystem folders (affine_body/, finite_element/, contact_system/, collision_detection/, etc.)
RMR (Reporter–Manager–Receiver) data-oriented design; avoid heavy OOP in backend code

CUDA backend subsystems (most review-sensitive): affine_body/, finite_element/, contact_system/, collision_detection/, distance_system/, active_set_system/, inter_primitive_effect_system/, engine/ (Newton + augmented-Lagrangian step in advance_al.cu)

Workflow

1. Checkout and fetch metadata

bash

gh pr checkout <PR_NUMBER>
gh pr view <PR_NUMBER> --json title,body,author,baseRefName,headRefName,headRefOid,repository,url,additions,deletions,changedFiles
gh pr diff <PR_NUMBER> --name-only

2. Present summary to the human reviewer

## PR #<N>: <title>
Author: <author>   Branch: `<head>` → `<base>`
URL: <url>
Stats: +<add> / -<del> across <N> files

### Description
<body>

### Files to review  (grouped by subsystem)
#### Backend — CUDA physics
  src/backends/cuda/affine_body/...
  src/backends/cuda/finite_element/...
  ...
#### Core / Public API
  include/uipc/...
  src/core/...
#### Geometry / Constitution
  src/geometry/...   src/constitution/...
#### Python bindings
  src/pybind/...   python/src/uipc/...
#### Build / CMake
  CMakeLists.txt   src/backends/.../CMakeLists.txt
#### Tests
  apps/tests/...   python/tests/...

3. AI review — libuipc-specific checklist

Run gh pr diff <PR_NUMBER> and check every area below that is touched.

Fast fail

All expected internal invariants are checked with UIPC_ASSERT where feasible
All user-facing inputs are validated with UIPC_ASSERT_THROW

C++20 style

C-style code is forbidden unless unavoidable (e.g., DLL export signatures)
Raw pointer parameters are forbidden unless unavoidable; prefer span<T>
const std::string& parameters are forbidden; use std::string_view instead
Multiple inheritance is forbidden; separate concerns into distinct classes

CUDA / GPU code

GPU buffer arguments use muda::BufferView / muda::TripletMatrixView (or equivalent view types) instead of raw pointers
Raw pointer parameters are forbidden in device code unless unavoidable

Constitution / material

New constitutions implement required IConstitution-family interface
Material parameters validated / clamped (no negative stiffness, density, etc.)

Public C++ API (`include/uipc/`)

No breaking changes to public headers without a version bump or deprecation notice
New public classes/functions follow existing naming: CamelCase types, snake_case functions, m_ prefix for members
#pragma once present; no <windows.h>-style global macros leaked

Show full SKILL.md (209 more words)Show less

C++ style (`.clang-format` enforced)

4-space indent, 80-column limit
Allman braces ({ on its own line)
Left-aligned pointers (int* p, not int *p)
No using namespace std; in headers

CMake

New backend follows uipc_add_backend(name) macro in src/backends/CMakeLists.txt
New CMake options added to the root CMakeLists.txt option block with sensible defaults
file(GLOB ...) patterns extended if new source subdirs added

Python bindings (`src/pybind/` + `python/`)

Check whether new features expose a public API that should be mirrored in the Python bindings
New C++ types exposed via matching pybind submodule (mirrors C++ namespace)
__init__.py import chain not broken (pyuipc → init() → config["module_dir"])
Python-side tests added under python/tests/ for new pybind surface

Tests

C++ tests use Catch2 macros; added via uipc_add_test in the appropriate apps/tests/<subsystem>/CMakeLists.txt
Regression tests added for bug fixes

4. Output format

Each finding must have a sequential number (1, 2, 3 … across all severity tiers) and a clickable local file link constructed from the absolute repo path + relative file path. Use this markdown link format for every citation:

[filename.ext:LINE](ABSOLUTE_REPO_PATH/relative/path/to/file.ext)

For example, if the repo is at /home/user/libuipc and the file is src/backends/cuda/affine_body/foo.cu at line 42:

[foo.cu:42](/home/user/libuipc/src/backends/cuda/affine_body/foo.cu)

Full output template:

## AI Review — PR #<N>

### Summary of changes
<one paragraph>

### Findings

🔴 Critical (must fix)
**#1** — [filename.ext:LINE](ABSOLUTE_PATH/relative/path/filename.ext)
Description of the issue and why it matters.

**#2** — [filename.ext:LINE](ABSOLUTE_PATH/relative/path/filename.ext)
Description.

🟡 Suggestion
**#3** — [filename.ext:LINE](ABSOLUTE_PATH/relative/path/filename.ext)
Description.

🟢 Nice-to-have
**#4** — [filename.ext:LINE](ABSOLUTE_PATH/relative/path/filename.ext)
Description.

### Checklist coverage
(tick the items above that were verified or N/A)

5. Post comments via `gh` (when asked)

General review comment / request changes / approve:

bash

gh pr review <PR_NUMBER> --comment   --body "..."
gh pr review <PR_NUMBER> --request-changes --body "..."
gh pr review <PR_NUMBER> --approve   --body "LGTM"

Inline comment on a specific line:

bash

gh api repos/<OWNER>/<REPO>/pulls/<PR_NUMBER>/comments \
  --method POST \
  -f path="<FILE_PATH>" \
  -f body="Your comment" \
  -F line=<LINE_NUMBER> \
  -f side="RIGHT" \
  -f commit_id="<HEAD_REF_OID>"

Run gh auth status first if commands fail.

Files

Just SKILL.md in .cursor/skills/review-pr of spiriMirror/libuipc.

Open the folder on GitHubat commit 9c748a7

Compare with similar skills

Review PR 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.

Review PR compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Review PR this skillspiriMirror/libuipc	335	—	~1.7k	Automated safety check: Pass	Apache-2.0	5 days ago
Code Review Skillawesome-skills/code-review-skill	2.1k	—	~2.8k	Automated safety check: Notes	MIT	1 mo ago
Create Cuda Python Pull RequestNVIDIA/cuda-python	3.4k	—	~1.1k	Automated safety check: Pass	Apache-2.0	today
pybind11 Release Preparationpybind/pybind11	18k	—	~1.7k	Automated safety check: Pass	Custom licence	today
pybind11 Release Publicationpybind/pybind11	18k	—	~2.5k	Automated safety check: Pass	Custom licence	today
Ghbubbuild/bub	1.7k	—	~798	Automated safety check: Pass	Apache-2.0	yesterday

Similar skills

Code Review Skill
awesome-skills/code-review-skill
Provides comprehensive code review guidance for React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, Java 8, PHP, Ruby, Rails, Python, Django, FastAPI, Go, C/.NET, Kotlin, Swift, Dart…
2.1k GitHub stars~2.8k tokensUpdated 1 mo ago
DevelopmentAuto-check: notes
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 today
DevelopmentAuto-check passed
pybind11 Release Preparation
pybind/pybind11
Opens the pybind11 release-preparation pull request: picking the release base, bumping the version in common.h and integrating the changelog, following docs/release.rst.
18k GitHub stars~1.7k tokensUpdated today
DevelopmentAuto-check passed
pybind11 Release Publication
pybind/pybind11
Walks a maintainer through publishing a pybind11 release after the preparation PR merges, with preflight checks, confirmations before each push and a GitHub release.
18k GitHub stars~2.5k tokensUpdated today
DevelopmentAuto-check passed
Gh
bubbuild/bub
GitHub CLI skill for interacting with GitHub via the gh command line tool.
1.7k GitHub stars~798 tokensUpdated yesterday
DevelopmentAuto-check passed
GitHub Fork and PR Submission
jxxghp/MoviePilot
Submits code changes as a GitHub pull request through an isolated Git clone, reusing or creating your fork and pushing only after you confirm the real diff.
12k GitHub stars~1.1k tokensUpdated today
DevelopmentAuto-check: notes

Questions about Review PR

What does Review PR do?

Review a libuipc pull request end-to-end: checkout the PR, summarize changes, list files for the human reviewer, and perform a domain-aware AI review covering physics correctness, backend…. Review PR is an agent skill from spiriMirror/libuipc. Review a libuipc pull request end-to-end: checkout the PR, summarize changes, list files for the human reviewer, and perform a domain-aware AI review covering physics correctness, backend architecture, C++ style, GPU code, and Python bindings.

When should I use Review PR?

Review PR fits situations like: the user provides a PR number; asks to review a PR; wants to inspect a libuipc GitHub PR.

How do I install Review PR in Claude Code?

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

How do I install Review PR in Codex?

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

Can I use Review PR 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 spiriMirror/libuipc --skill review-pr -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-pr, .gemini/skills/review-pr, .github/skills/review-pr and .opencode/skills/review-pr in your project.

What does Review PR need to run?

Going by SKILL.md and its folder, Review PR needs the command-line tools its instructions call (gh). Our summary lists: Python 3.

Does Review PR access the network?

SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Review PR 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 Review PR use?

Review PR 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 Review PR use?

About 1.7k tokens (SKILL.md is roughly 7k 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 Review PR?

Skills that share tags, products or a category with Review PR: Code Review Skill (awesome-skills/code-review-skill, 2.1k stars), Create Cuda Python Pull Request (NVIDIA/cuda-python, 3.4k stars), pybind11 Release Preparation (pybind/pybind11, 18k stars) and pybind11 Release Publication (pybind/pybind11, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review PR?

spiriMirror (a GitHub organization) maintains it in spiriMirror/libuipc, which has 335 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 3, 2026.

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

Install Review PR

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

libuipc PR Review

Architecture primer (read before reviewing)

Workflow

1. Checkout and fetch metadata

2. Present summary to the human reviewer

3. AI review — libuipc-specific checklist

Fast fail

C++20 style

CUDA / GPU code

Constitution / material

Public C++ API (include/uipc/)

C++ style (.clang-format enforced)

CMake

Python bindings (src/pybind/ + python/)

Tests

4. Output format

5. Post comments via gh (when asked)

Files

Compare with similar skills

Similar skills

More from spiriMirror/libuipc

Related

Questions about Review PR

Public C++ API (`include/uipc/`)

C++ style (`.clang-format` enforced)

Python bindings (`src/pybind/` + `python/`)

5. Post comments via `gh` (when asked)