Loading...
Loading...
Found 40 Skills
Review a Memory Bank with fresh-context specialists and produce a prioritized fix list.
Use when work is validated and ready to submit, to push to main and create PR for agent review
Coordinate multi-perspective project, code, docs, design, or delivery reviews into focused recommendations. Use for multiple subagents, perspectives, named roles like UI/UX, DevOps, architecture, security, docs, or integrated feedback before changes.
Orchestrates design workflows by routing work through brainstorming, multi-agent review, and execution readiness in the correct order. Prevents premature implementation, skipped validation, and unreviewed high-risk designs.
Multi-agent quality improvement review with constructive feedback. Provides suggestions for best practices, code quality, alternatives, and performance optimization.
Review a Ralph plan and bd graph for defects via a subagent.
Adversarial senior-engineer review for agent-generated plans, designs, and architectures. Treats the current output as junior work, constructs a senior reviewer whose domain expertise comes from live codebase research plus web research of current best practices, diagnoses altitude failures (too vague or too granular), then rewrites the plan into a scoped, state-of-the-art version. Use when the user says "junior to senior", "senior review", "review this like a staff engineer", when a plan feels hand-wavy or lost in details, or before committing to any agent-written plan.
After the task execution is completed, prompt the user to open a new Agent to review the uncommitted git code. Athletes should not act as referees; proceed with the wrap-up only after the review is approved.
Orchestrate copy exploration. Brief, generate 5 distinct approaches, adversarial review, iterate to 90+ composite, present catalog, user selects, execute.
Validates optimization plan via parallel multi-agent review (Codex + Gemini) before execution. GO/NO-GO verdict.
Comprehensive Elixir/Phoenix code review with optional parallel agents
Use to review uncommitted changes and recent commits in the working tree. Dispatches 8 specialized review agents in parallel and returns a consolidated report