Devils Advocate
Use when reviewing PRs, evaluating design proposals, assessing technical plans, stress-testing assumptions, looking for overlooked failure modes, or adding pushback before a decision.
Docgen
Use when generating documentation, writing API docs, documenting modules or components, creating README content, building reference guides, or documenting many files with explicit coverage tracking.
Flow Memory Keeper
Use at task, phase, flow, sync, archive, finish, revise, or failure checkpoints to keep Flow specs clean, capture learnings and failures, elevate durable patterns, and refine this skill with project-specific nuances
Deepthink
Use when a problem resists quick answers, debugging stalls, analysis feels shallow, confidence is low, hypotheses are competing, reasoning loops repeat, or a hard problem needs evidence tracking.
Flow Planning
Use when drafting PRDs, researching, planning, refining, revising, or creating .agents/specs/<flow_id>/spec.md worksheets for Flow.
Architecture Critic
Use when evaluating architecture, component boundaries, coupling, cohesion, abstractions, large refactors, new layers, maintainability risks, or design choices with long-term structural consequences.
Flow Execution
Use when implementing Flow tasks from Beads or spec.md, claiming ready work, applying TDD, recording task notes, committing, and syncing after task state changes.
Perspectives
Use when analyzing tradeoffs, comparing approaches, weighing options, assessing risks, stress-testing conclusions, identifying blind spots, or applying multiple viewpoints to a decision.
Tracer
Use when tracing execution paths, mapping dependencies, understanding unfamiliar code, following data flow, investigating end-to-end behavior, debugging call chains, or deciding which files to read next.
Flow Setup
Use when initializing Flow in a repo, configuring .agents, installing or checking Beads bd, setting local-only sync policy, or creating first project context files.
Security Auditor
Use when reviewing authentication, authorization, user input, secrets, API keys, database queries, file uploads, session management, external API calls, OWASP risks, or data handling attack surface.
Performance Analyst
Use when reviewing hot paths, slow code, database queries, N+1 risks, memory usage, loops, I/O, caching strategy, concurrency, latency-sensitive paths, or resource efficiency.
Flow
Use when a repository has .agents, when the user asks for Flow lifecycle routing, Beads-backed task memory, spec-first planning, TDD implementation, sync/status, review, finish, archive, or /flow:* help.
Flow Completion
Use when reviewing, finishing, archiving, reverting, validating, or cleaning up Flow work after implementation or phase completion.
Apilookup
Use when work depends on current external API behavior, SDK docs, framework versions, breaking changes, migration guides, changelogs, release notes, deprecations, or syntax that may have changed.
Flow Sync Status
Use when syncing Beads state to markdown, checking Flow status, refreshing context docs, validating task markers, or reporting ready/blocked Flow work.
Litestar Mcp
Litestar plugin for Model Context Protocol (MCP) — expose route handlers as MCP tools and resources for AI agents.
Consensus
Use when comparing architectural choices, technology options, build-vs-buy decisions, feature proposals, high-impact tradeoffs, multi-team decisions, hard-to-reverse choices, or risk-heavy alternatives.
Challenge
Use when questioning claims, pushing back on assumptions, sanity-checking decisions, evaluating confident assertions, avoiding reflexive agreement, or answering prompts like \"are you sure?\