Create a new underwriting agent (assets, credit, collateral) following established patterns. Use when implementing new agents, extending the system with new document analysis capabilities, or understanding how agents work.

Standards for creating redteam plugins and graders. Use when creating new plugins, writing graders, or modifying attack templates.

Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.

Manage semantic versioning, changelog generation, and release notes. Auto-generates entries from completed issues or git diff.

Aggressive evidence-based audit to verify project claims match implementation reality

Create and maintain Claude Code agents/subagents (.claude/agents/*.md) with YAML frontmatter (name/description/tools/model/permissionMode/skills/hooks), least-privilege tool selection, delegation patterns (Task), context budgeting, and safety best practices.

LangGraph development for stateful multi-agent applications, cyclic workflows, conditional routing, human-in-the-loop patterns, and persistent state management. Use for complex AI orchestration, agent coordination, and production-grade agentic systems.

Create your LiveKit Agents skill from official documentation, then learn to improve it throughout the chapter

MCP Agent Mail - mail-like coordination layer for coding agents with memorable identities, inbox/outbox, searchable threads, advisory file reservations, pre-commit guards, and human-auditable Git artifacts. The backbone of multi-agent workflows.

Systematically deconstruct written content into verifiable claims, validate each using search/documentation, and facilitate informed discussion through structured interviewing.

Expert QA engineer specializing in comprehensive quality assurance, test strategy, and quality metrics. Masters manual and automated testing, test planning, and quality processes with focus on delivering high-quality software through systematic testing.

This skill should be used when the user asks about "job status", "check if request completed", "cancel request", "why is my request taking so long", "poll for result", "batch requests", "retry failed request", "request timeout", "async operations", "job lifecycle", "manual polling", or needs advanced control over SDK async operations, manual job polling, batch processing, retry logic, or job cancellation.

Audit Solana programs (Anchor or native Rust) for security vulnerabilities. Use when reviewing smart contract security, finding exploits, analyzing attack vectors, performing security assessments, or when explicitly asked to audit, review security, check for bugs, or find vulnerabilities in Solana programs.

Use when configuring Docker environments for act, selecting runner images, managing container resources, or troubleshooting Docker-related issues with local GitHub Actions testing.

Expert developer experience optimizer specializing in build performance, tooling efficiency, and workflow automation. Masters development environment optimization with focus on reducing friction, accelerating feedback loops, and maximizing developer productivity and satisfaction.

Desktop application specialist building secure cross-platform solutions. Develops Electron apps with native OS integration, focusing on security, performance, and seamless user experience.

Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.

Start voice calls via the OpenClaw voice-call plugin.

Zero-tolerance alignment verification protocol. Alignment is binary - elements are either in line or they're not. Report exact measurements, no tolerances, no "close enough."

Analyze and optimize JavaScript bundle size, identify large dependencies, and improve load times. Use when bundles are large, investigating performance issues, or optimizing frontend assets.