Browse Skills

Greploop iteratively fixes a PR, MR, or Perforce changelist until Greptile returns a 5/5 confidence score with no unresolved comments. Use it when you want to trigger review, apply actionable feedback, and repeat until the review is clean.

Challenge Mode Reviews pushes for rigorous scrutiny before approving changes. Use it to question Ecto migrations, LiveView events, OTP designs, and PR readiness with proof and edge-case checks.

Codex Loop runs a bounded Codex CLI review, applies approved fixes, verifies them, and re-reviews until clean or rounds run out. Use it before a PR when you want an external critic on Elixir/Phoenix changes.

Codex Panel A/B runs one holistic Codex review and three focused passes on the same branch diff, then classifies findings as duplicates, real misses, or false positives. Use it on a fresh branch before any Codex review has run.

Constraint Debug invokes the Elixir/Phoenix Ecto constraint debugger through the /ecto:constraint-debug alias. Use it when you need help diagnosing constraint-related database errors in an Elixir Phoenix app.

Docs Check validates plugin agents, skills, hooks, and config against the latest Claude Code documentation. Use it before releases or on a schedule to catch breaking changes, deprecations, and new features.

Ecto N+1 Check invokes the Phoenix plugin’s N+1 query checker for Elixir/Ecto code. Use it explicitly when reviewing code for repeated database queries and performance issues.

LiveView Assigns Audit inspects LiveView socket assigns for memory bloat, unused assigns, and missing temporary_assigns. Use it when LiveView memory grows or you need to tighten assign usage.

Phoenix Boundaries analyzes Phoenix module dependencies and context coupling with mix xref. Use it to check cross-context calls, boundary violations, and architecture before refactoring or splitting modules.

Project Health Audit runs a project-wide check of architecture, performance, security, tests, and dependencies. Use it before releases, after refactors, or when you need a quick view of overall codebase health.

Debug RLS helps troubleshoot Row-Level Security issues in Butterbase when users see access denied errors, wrong rows, or policy failures. It uses role simulation to test how policies behave for anon, user, and service requests.

Skill Simplify analyzes a skill file for redundancy, trims descriptive content, and checks that functional elements are still intact. Use it when simplifying or optimizing a skill without losing behavior.