Project histories, changelogs, developer interviews, open source

Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.

Generate comprehensive PR descriptions following repository templates

Agentica server + Claude proxy setup - architecture, startup sequence, debugging

Release preparation workflow - security audit → E2E tests → review → changelog → docs

Comprehensive testing workflow - unit tests ∥ integration tests → E2E tests

Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".

Unified math capabilities - computation, solving, and explanation. I route to the right tool.

Formal theorem proving with research, testing, and verification phases

Implement technical plans from thoughts/shared/plans with verification

Reviews code for bugs, security issues, performance problems, and best practices. Use when reviewing PRs, checking code quality, or auditing changes.

Comprehensive fullstack development skill for building complete web applications with React, Next.js, Node.js, GraphQL, and PostgreSQL. Includes project scaffolding, code quality analysis,...

Build deep architectural understanding through ultra-granular code analysis. Use when doing security audits, code reviews, or getting oriented in an unfamiliar codebase.

Repo Updater - Multi-repo synchronization with AI-assisted review orchestration. Parallel sync, agent-sweep for dirty repos, ntm integration, git plumbing. 17K LOC Bash CLI.

Reviews pull requests and code changes for quality, security, and best practices. Use when user asks for code review, PR review, or mentions reviewing changes.

Analyze code complexity, cyclomatic complexity, maintainability index, and code churn using metrics tools. Use when assessing code quality, identifying refactoring candidates, or monitoring technical debt.

Maintain high code quality through formatting, linting, and static analysis using rustfmt, clippy, and cargo audit. Use to ensure consistent code style and catch common mistakes.

Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling,...

Use when building MCP servers or clients that connect AI systems with external tools and data sources. Invoke for MCP protocol compliance, TypeScript/Python SDKs, resource providers, tool functions.

Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation...