Loading...
Loading...
Found 71 Skills
Review current uncommitted git changes with full file context and produce a structured report with severity levels, actionable fixes, and an approval verdict.
Request peer review with proper context and preparation. Structures review requests with clear description of changes and testing status.
Architecture optimization team skill. Analyzes codebase architecture, designs refactoring plans, implements changes, validates improvements, and reviews code quality via CSV wave pipeline with interactive review-fix cycles.
Multi-layer quality assurance with 5-layer verification pyramid (Rules → Functional → Visual → Integration → Quality Scoring). Independent verification with LLM-as-judge and Agent-as-a-Judge patterns. Score 0-100 with ≥90 threshold. Use when verifying code quality, security scanning, preventing test gaming, comprehensive QA, or ensuring production readiness through multi-layer validation.
Review a GitLab Merge Request and provide findings, and post structured review comments with issue explanation plus pseudo code fixes. Use this skill when asked to review a Gitlab Merge request.
Use Codex CLI for sandboxed auditing, debugging, and autonomous prototyping
Use to review uncommitted changes and recent commits in the working tree. Dispatches 8 specialized review agents in parallel and returns a consolidated report
Multi-agent code review with specialized perspectives (security, performance, patterns, simplification, tests)
Review a spec document against codebase reality, identifying gaps and ensuring sound, robust implementations.
Use this skill when the user asks to review their local git changes, staged or unstaged diffs, or wants a code review before committing. Triggers on "review my changes", "review staged", "review my diff", "check my code", "code review local changes", "review unstaged", "review before commit".
Defense-in-depth verification before declaring any task complete. Run tests, check build, validate changed files, verify no regressions. Applies 4-level adversarial artifact verification (EXISTS > SUBSTANTIVE > WIRED > DATA FLOWS) with goal-backward framing. Use before saying "done", "fixed", or "complete" on any code change. Use for "verify", "make sure it works", "check before committing", or "validate changes". Do NOT use for debugging (use systematic-debugging) or code review (use systematic-code-review).
Fresh-subagent-per-task execution with two-stage review (ADR compliance + code quality). Use when an implementation plan exists with mostly independent tasks and you want quality gates between each. Use for "execute plan", "subagent", "dispatch tasks", or multi-task implementation runs. Do NOT use for single simple tasks, tightly coupled work needing shared context, or when the user wants manual review after each task.