Get a token-efficient overview of any project using the TLDR stack

LLM Tuning Patterns

Analyze brownfield codebase and create initial continuity ledger

Parallel Agent Type Contracts

Automated browser-based document search and retrieval from free public sources

Maps questions to the optimal tldr command. Use this to pick the right layer

Project histories, changelogs, developer interviews, open source

Scan lyrics for pronunciation risks, prevent Suno mispronunciations

AI-powered web search, research, and reasoning via Perplexity

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.

Implement technical plans from thoughts/shared/plans with verification

Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration

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

Get code review from Codex AI for implementation quality, bug detection, and best practices. Use when asked to review code, check for bugs, find security issues, or get feedback on implementation patterns.