Loading…
Evidence-based code review of a GitHub PR. Validates PR prerequisites, CI status and log sanity, technical rules (scope, diff coverage ~95%, single-responsibility, no side effects, DRY, ≤30-line methods, ≤4 positional args), system seams, and the security (incl. LLM/agent surface and CI supply chain), data handling and dependency checks, then writes review comments tagged [r]equired / [o]ptional / [f]uture / [c]uriosity. Use when the user says "review this PR", "review PR 123", "security review of this PR", "/pr-review", or asks for a code review of a pull request. Docs-only or proposal PRs need a design-doc review instead.
pr-review is an agent skill entry in ChatHome Skills, sourced from GitHub Skill Search and scored 38/100. PR review in a fixed order. Gate, then orient in the repo, then function-level, system-level and security checks, then write the comments. The order matters: fi. As an agent skill, it packages a reusable instruction set that AI coding agents such as Codex and Claude Code can load to perform this task without hand-written glue code. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding pr-review to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
codex skill install integral-llc/skillsReview the upstream source before running this command.
Downloads a script and pipes it straight into a shell, executing remote code with no review.
curl \| shDispute this flag?Scan coverage: Install metadata and the indexed document body.
Automated signals from install metadata and a bounded skill body — not a full code security audit and not a recursive source or dependency review.
PR review in a fixed order. Gate, then orient in the repo, then function-level, system-level and security checks, then write the comments. The order matters: findings made before r