Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
462 skills found
Foundational architectural principles for MoAI-ADK, featuring TRUST 5, SPEC-First TDD, delegation patterns, and token-efficient agent orchestration workflows.
Official MoonBit language reference, syntax guide, and coding conventions for building high-performance software projects.
Generate optimized SQL queries from natural language. Supports BigQuery, PostgreSQL, MySQL, and Snowflake. Analyze database schemas, interpret business requirements, and output ready-to-run queries with explanations.
Resume a paused experimental loop by restoring branch context, loading configuration, reading history, and identifying optimization patterns for continued iteration.
Performs a structured five-stage code review covering requirements, correctness, code quality, testing, and security. Provides actionable, categorized feedback (Blocker/Major/Minor/Nit) to improve PR quality.
Apply reality-first coding standards: intentional naming, focused functions, guard clauses, and deterministic side effects, with no speculative features.
Framework for multi-agent collaboration using the Google A2A protocol. Enables messaging, task delegation, and cross-agent coordination for CLI-based AI tools.
A specialized skill for surgical code refactoring. Improves maintainability, reduces technical debt, and applies design patterns without altering external behavior.
A specialized decision-making agent for complex architectural choices, task planning, and error resolution within the orchestration system.
Autonomous multi-team codebase improvement agent with specialized modes: narrow (goal-directed), broad (hypothesis-divergent), and sweep (quality-focused).
Automated session cleanup and documentation tool. Proactively updates CLAUDE.md, detects automation patterns, extracts insights, and organizes pending tasks.
Expert guidance for Claude Messages API: structured outputs, prompt caching, tool use, and migration from deprecated Claude 3.x models to 4.5. Prevents common API errors.