⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
pr-review
Review a pull request for correctness, clarity, and test coverage, and leave findings ranked by severity.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
What is ai-registry?
An agent registry stores your organization's AI artifacts and manages their lifecycle. It's the source of truth for the skills and agents your teams share, so everyone works from the same verified version of each skill and agent, no matter what team they're on or coding agent they use. However, registries today are often tied to one ecosystem or one vendor's storage, so only that vendor's tools can read your artifacts, and moving them means a migration.
ai-registry is an open standard that enables anyone to build an open, interoperable agent registry.
- Open format: Today each registry, and each coding agent's own store, has its own format for versions, ownership and approvals, so every client needs a connector per registry. With an open specification, a client integrates once, reads any registry that implements it, and installs into any agent.
- Open storage: Today a registry is tied to its own storage, so its records can only be read through that registry's software. With an open specification, a registry is just a set of files in a defined layout, so you can build one on infrastructure you already have, such as a git repository or an object storage bucket. The aireg CLI reads registries in folders and git repositories today.
Why not just a git repository of skills, or a plugin marketplace?
In a plain repository of skills or a marketplace, everyone gets whatever copy is there when they install, so teammates end up running different copies, and nobody can tell which. A registry can live in a git repository too, but it pins and verifies every version, gives every machine identical bytes, rolls back or yanks a version for everyone, and keeps all your coding agents in sync from one record.
Get started
The easiest way to get started is to follow the Quickstart.
To have your coding agent set up ai-registry for you, paste this prompt into Claude Code, Codex or Cursor:
Set me up with ai-registry: https://github.com/atlanai/ai-registry
The agent follows the setup skill in this repository, skills/ai-registry/SKILL.md. It asks before it installs aireg and the aireg skills, offers to try the example registry, then helps you set up a registry for yourself or your team. The use cases have more prompts to try, from your own coding agents to a whole team.
Install the aireg CLI on macOS or Linux:
curl -fsSL https://aireg.sh/install | sh
On Windows, run this in PowerShell:
irm https://aireg.sh/install.ps1 | iex
Check the installation with aireg --version. To read the install script first, or to install a specific release, see Install the aireg CLI. To run aireg from source, see CONTRIBUTING.md.
Then install the skills and agents from the example registry in this repository into a new project:
mkdir try-aireg && cd try-aireg && git init
aireg registry add github.com/atlanai/ai-registry --path examples/acme-registry
aireg add acme/engineering
aireg list
aireg links them into the folders your coding agents read, and records each exact version in .registry/manifest.lock.yml. aireg add also installs from a plugin marketplace, a site's Agent Skills index, or a folder or repository of skills; see aireg add.
When it runs in a terminal, the installer offers the aireg skills, from the release it installs. They let your coding agent set up, install from and publish to registries for you. To add them later:
aireg registry add github.com/atlanai/ai-registry --path examples/aireg -g
aireg add ai-registry/aireg -g
Roadmap
The ai-registry project currently includes:
- Registry file spec. The specification you can use to implement an agent registry, with its JSON Schemas.
- aireg. A CLI client for the specification that creates registries, publishes to them and installs from them into Claude Code, Codex and Cursor.
- Example registries and checks you can use to verify a registry against the spec.
The spec is a draft (v0.1) and aireg hasn't reached 1.0, so both may still make breaking changes. We plan to add a catalog API for creating, federating and governing registries, and an MCP server that lets an agent read a registry directly.
Contributing
Start with CONTRIBUTING.md, which covers bug reports, spec changes and setting up the CLI. Coding agents should read AGENTS.md.
Everyone taking part follows the Code of Conduct. Report security issues privately, as described in SECURITY.md.
License
ai-registry is licensed under the Apache License 2.0.
// HOW IT'S BUILT
// FILES
3 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.
examples/acme-registry/artifacts/engineering/skill/pr-review/1.1.0/SKILL.md550 B8c8f09a94e64upstream ↗
--- name: pr-review description: Review a pull request for correctness, clarity, and test coverage, and leave findings ranked by severity. license: Apache-2.0 --- # PR review Read the diff, then the tests that cover it. For each change ask three questions: does it do what the description says, could it fail on an input the author did not consider, and is there a test that would catch that failure. Report findings most severe first. Each finding names the file and line, states the defect in one sentence, and gives the input that triggers it.examples/acme-registry/artifacts/engineering/skill/pr-review/1.1.0/artifact.json1.1 KBe83902fca092upstream ↗
{ "apiVersion": "aireg.sh/v1", "kind": "skill", "metadata": { "name": "pr-review", "namespace": "engineering", "version": "1.1.0", "display_name": "PR review", "description": "Review a pull request for correctness, clarity, and test coverage, and leave findings ranked by severity.", "status": "active", "labels": { "category": "engineering" }, "source": { "type": "git", "uri": "https://github.com/acme/skills", "revision": "3f2a9c1e7b4d5a6f8c0e1d2b3a4f5e6d7c8b9a01" }, "created_at": "2026-08-14T09:00:00Z", "created_by": "acme-ci", "digest": "sha256:ffc0420a7a94cf4c97aeed8875187c2208813ad079fb09dda1661d6bb3ca577f" }, "files": [ { "path": "SKILL.md", "digest": "sha256:87c145cfcb1f71178939367a87e917aa39518b96419fca470c722a06b9487f8e", "size": 550, "media_type": "text/markdown", "urls": [ "SKILL.md" ] } ], "spec": { "name": "pr-review", "description": "Review a pull request for correctness, clarity, and test coverage, and leave findings ranked by severity.", "license": "Apache-2.0" }, "relationships": [] }README.mdupstream ↗
Contents are not inlined in the catalog. Open the upstream file.
Plain-text copy, no login: /skill-bundles/atlanai-ai-registry-examples-acme-registry-artifacts-engineering-skill-pr-review.md