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.

Build GraphQL APIs with schema design, resolvers, and subscriptions. Use when: creating GraphQL server, API with complex queries. Triggers: "graphql", "gql", "apollo", "async-graphql", "strawberry".

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.

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.

Writing and maintaining GitHub issues for the tldraw repository. Use when creating new issues, editing issue titles/bodies, triaging issues, or cleaning up issue metadata (types, labels).

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.

Expert-level insurance systems, underwriting, claims processing, actuarial analysis, risk assessment, and insurtech solutions

Search and analyze your own session logs (older/parent conversations) using jq.

Build AI applications with the Anthropic TypeScript SDK. Use when creating Claude integrations, building agents, implementing tool use, streaming responses, or working with the @anthropic-ai/sdk package.

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.

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

guidance on how to properly do data migrations in Convex

First-time setup for vibereps exercise tracker. Use when user wants to install, configure, or set up vibereps for the first time. Guides through exercise selection, hook configuration, and preferences.

Create GitHub issues following Pollinations team conventions. Use when asked to create issues, track work, or plan features.

Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).

Auto-activate CCS CLI delegation for deterministic tasks. Parses user input, auto-selects optimal profile (glm/kimi/custom) from ~/.ccs/config.json, enhances prompts with context, executes via `ccs {profile} -p "task"` or `ccs {profile}:continue`, and reports results. Triggers on "use ccs [task]" patterns, typo/test/refactor keywords. Excludes complex architecture, security-critical code, performance optimization, breaking changes.

Execute implementation tasks from design documents using markdown checkboxes. Use when (1) implementing features from feature-design-assistant output, (2) resuming interrupted work, (3) batch executing tasks. Triggers on 'start implementation', 'run tasks', 'resume'.

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