Automação

Review changed code (diff, files, or directory) against layered, stack-aware checklists plus plan- and lesson-aware dynamic checks. Stateless side-skill — chat-only output, no plan-lifecycle status, no persistent report.

Generate runnable verification scripts for components. Orchestrates assertion-patterns and component-patterns to produce executable scripts.

Principles for multi-agent workflow execution. Use when coordinating agents, accepting or rejecting agent work, executing producer-critic-learner cycles, or running any multi-phase orchestrated task.

Context-aware chat about the project: discuss plans, retros, lessons, and code; navigate the vault; and handle chores (frontmatter tweaks, status flips, inline plan or code edits) without invoking the heavier skills. Opens every session with a vault status summary.

Use when you need to diagnose the health of a team-shinchan project setup. Runs 7 deterministic checks (workflow state, hooks config, core scripts, runtime files, test directory) and reports PASS/WARN/FAIL per check with remediation hints.

Use when you need persistent looping until a task is fully complete.

Auto-activate for litestar_mcp imports, LitestarMCP, MCPConfig, MCPController, @mcp_tool, @mcp_resource, JSON-RPC route exposure, route filtering, or OAuth/Guard-protected MCP endpoints. Use when exposing Litestar routes as MCP tools or resources. Not for non-Litestar MCP servers or FastAPI/Django MCP integrations.

Use when you want to manually add new learnings or rules to memory.

Build backend API endpoints, services, and database changes. Use for backend-only work like new API routes, business logic, database schema changes, or microservice patterns. Activates the Architecture Council for significant API decisions.

Use when you need to detect or remove AI slop from text — filler openers, hedge stacks, redundant qualifiers, and emoji clusters. Scans stdin or a file and optionally rewrites clean output.

Transform a plan_creation plan_v{N}.md into a structured tasks.yaml + per-WP workpackages/*.yaml using parallel Sonnet sub-agents. Use after plan-creation finishes when you need execution-friendly task structure.

Use when you need deep analysis of code, bugs, performance, or architecture issues.