Code Review

Trust Score 83/100

Automated code review guidance focusing on security, correctness, and maintainability; used to validate changes before committing.

triggers:code reviewsecurity checkpre-commitreview filesvalidate changescode qualityreviewer

GitHub SKILL.md

What it does

This skill provides a structured, standards-driven code review workflow for AI agents. It instructs the agent to preload project coding and security standards, run a targeted file or diff review, and return findings organized by severity (CRITICAL, HIGH, MEDIUM, LOW) with concrete diffs and remediation steps. The skill emphasizes security and blocks commits on critical or high-severity issues.

When to use it

Use this skill when code has been written and needs validation before committing or when a user explicitly requests a security or quality review of files, diff ranges, or feature branches. Ideal for pre-merge checks and automated CI review agents.

What's included

Scripts: none indicated in the repo bundle (has_scripts=false)
References: none bundled (has_references=false)
Instructions: Step-by-step process to preload standards, invoke /code-review against files or diffs, analyze and structure findings, and prescribe fixes including patch diffs. Guidance on when to stop, fix, and re-run.

Compatible agents

Best suited for agent setups that support isolated reviewer subagents and file-level invocation (e.g., Claude Code or similar code-reviewer agents).

Audit Summary

A purely instructional code-review skill with no bundled scripts. Provides a well-structured framework for security/correctness/style reviews with severity levels and a subagent invocation pattern. Relies on external context files (.opencode/context/core/standards/) that aren't bundled, making it incomplete standalone. Specific to the OpenAgentsControl framework's fork context pattern.

Watch Out

Requires external context files (.opencode/context/core/standards/) that aren't included
Designed for OpenAgentsControl's fork/subagent pattern — not portable to other agent frameworks
$ARGUMENTS interpolation assumes specific runtime behavior

Notes

Clean skill with no security concerns. Well-written instructions but essentially a structured prompt template rather than an automated tool. Missing the referenced standards files makes it incomplete without the parent repo context. The 'common rationalizations' table is a nice touch for encouraging review discipline.

Information

Repository: openagentscontrol
Stars: 3,976
Installs: 0

Trust Score

Overall83

Security95

Code Quality72

Architecture68

Usefulness55

Related Skills

Development Worktree

Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.

Readwise Reader Document Management

Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.

Bounty Hunter — Atlas

Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.

Junshi — Research Advisor

Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.

TradeOS

Natural-language driven CEX trading and portfolio management for agents: API key vaulting, multi-exchange orders, DCA, arbitrage scanning, alerts and security r

Full Stack Builder

End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.

ezBookkeeping API Tools

Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi

Feishu Voice Sender

Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.

Back to Skills