LLM & Agents

Estrategia de Testes React. Use when writing tests, reviewing test coverage, or setting up testing.

Tavily AI search API integration via curl. Use this skill to perform live web search and RAG-style retrieval.

Plan LLM fine-tuning and evaluation experiments. Use when the user wants to design a new experiment, plan training runs, or create an experiment_summary.yaml file.

Practical vector search design on AgentDB for production retrieval and RAG.

Don't Repeat Yourself (DRY) and Never Reinvent the Wheel (NRtW) - core b00tprinciples. Use existing libraries, leverage Rust via PyO3 instead of duplicatinglogic in Python, and contribute to upstream projects rather than fork privately.

Estrategia de Testing React. Use when writing tests, reviewing test coverage, or setting up testing.

Generate highly detailed, Midjourney-style image prompts optimized for the FLUX 1.1 Pro model on Replicate. Transform basic user descriptions into rich, cinematic prompts with professional photography qualities, dramatic lighting, and editorial-quality aesthetics. Use when users request image generation, need prompt enhancement, or want Midjourney-quality outputs via FLUX 1.1 Pro.

Use when cooking or planning meals, troubleshooting recipes, learning culinary techniques (knife skills, sauces, searing), understanding food science (Maillard reaction, emulsions, brining), building flavor profiles (salt/acid/fat/heat balance), plating and presentation, exploring global cuisines and cultural food traditions, diagnosing taste problems, requesting substitutions or pantry hacks, planning menus, or when users mention cooking, recipes, chef, cuisine, flavor, technique, plating, food science, seasoning, or culinary questions.

Write integration and unit tests for this codebase. Generate test files following repo patterns. Use when adding tests, improving coverage, writing test cases, or creating test suites.

Check agent configuration coverage across hierarchy levels and phases. Use to ensure complete agent system coverage.

. Use when writing tests, reviewing test coverage, or setting up testing.

MANDATORY skill when KeyError or schema errors occur. Fetch actual prompt schemas instead of guessing. Use for debugging traces and understanding AI model behavior.

Validates test coverage and quality by checking behavior focus, identifying gaps, and ensuring >80% statement coverage. Use when task file is in testing/ directory and requires test validation before marking complete. Adds minimal tests for genuinely missing edge cases.

Use proactively when you need to implement features or fix bugs using strict Test-Driven Development (TDD) methodology. This agent should be activated for any coding task that requires writing new functionality, refactoring existing code, or ensuring comprehensive test coverage, but should not be used for any design-related tasks. The agent excels at breaking down complex requirements into testable increments and maintaining high code quality through disciplined TDD cycles. Use this agent proactively or if the user mentions 'TDD', 'tdd' or 'Test Driven Development'.

Split large tasks across multiple Claude Code sessions or branches. Coordinate parallel work with merge gates. Use when task is too large for one session, want parallel work, or need to split work across branches.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches superpowers:code-reviewer subagent to review implementation against plan or requirements before proceeding

Use Gemini to find existing solutions before building from scratch. Leverages Google Search grounding to discover code examples, libraries, and best practices to avoid reinventing the wheel.

Create test cases for functions and modules. Use when implementing TDD or improving coverage.

Test agent delegation patterns to verify hierarchy and escalation paths. Use after modifying agent structure.

AgentDB Persistent Memory Patterns operates on 3 fundamental principles: