compound-eng-code-reviewStructured code reviews with severity-ranked findings and deep multi-agent mode. Use when performing a code review, auditing code quality, or critiquing PRs,...
Install via ClawdBot CLI:
clawdbot install iliaal/compound-eng-code-reviewGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval(Audited Apr 17, 2026 · audit v1.0
Generated May 22, 2026
Integrate the code-review agent into the CI pipeline to automatically review every pull request. It runs spec compliance checks, code quality scans, and security analysis, providing severity-ranked findings before human review.
Use the agent to analyze a large legacy codebase, identifying architectural issues, dead code, security vulnerabilities, and areas lacking test coverage. The structured review helps prioritize refactoring efforts.
Perform a deep security-focused code review on a fintech app handling payments and PII. The agent checks for injection, authentication flaws, secrets exposure, and race conditions, outputting critical findings.
Maintainers can use the agent to evaluate contributions to open source projects. It ensures changes align with project specs, maintain coding standards, and pass security checks before merging.
For large pull requests spanning multiple modules, the agent triggers deep review with parallel specialists. It suggests splitting the PR if it exceeds size thresholds, reducing review fatigue and defects.
Offer the agent as a subscription-based service integrated with major Git platforms (GitHub, GitLab, Bitbucket). Customers pay per repository or per developer for automated reviews.
Partner with CI/CD providers (Jenkins, CircleCI, GitHub Actions) to offer the agent as a premium plugin. Revenue comes from usage-based fees or a cut of the platform's premium tiers.
Sell to enterprises for mandatory code reviews before production releases, especially in regulated industries. Include compliance reporting and integration with internal ticketing systems.
💬 Integration Tip
Integrate the agent as a GitHub Action or GitLab CI job. For deep review, ensure the agent can access the full diff and project structure; use environment variables for API keys.
Scored May 22, 2026
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
This skill should be used ONLY when the user EXPLICITLY and UNAMBIGUOUSLY requests a Git repository commit-history analysis that produces aggregate collabora...
Spec-first, TDD, subagent-driven software development workflow. Use when: (1) building any new feature or app — triggers brainstorm → plan → subagent executi...
Best practices for Remotion - Video creation in React