LLM & Agents

Engineers effective prompts using systematic methodology. Use when designing prompts for Claude, optimizing existing prompts, or balancing simplicity, cost, and effectiveness. Applies progressive disclosure and empirical validation to prompt development.

Scaffold new Claude Code skills with correct frontmatter, directory layout, contracts, and validation assets.

Coordinate with other AI agents via project-local Maildir messaging. Use when operating in tandem mode with Claude, Gemini, or other agents. Enables claiming tasks, reporting completion, handling blocks, and synchronizing work across terminals.

Enables autonomous pattern recognition, storage, and retrieval at project level with self-learning capabilities for continuous improvement

Performance tuning for AgentDB across indexing, storage, and query paths.

---

Optimize prompts for clarity, structure, determinism, and epistemic hygiene with explicit confidence ceilings.

Drive iterative refinement loops with evidence capture, evaluation checkpoints, and stop conditions for skills, prompts, or agents.

Comprehensive prompt iteration workflow for debugging and improving Langfuse prompts. Analyzes codebase usage, sets up reproducible tests, runs iterative refinement cycles with user feedback. Use when user says "prompt X isn't working right", "improve prompt", "iterate on prompt", "refine prompt", or "test prompt changes".

Rule 07: Testing. Use when writing tests, reviewing test coverage, or setting up testing.

Stratégie de Tests React. Use when writing tests, reviewing test coverage, or setting up testing.

Testing Flutter - Stratégie Complète. Use when writing tests, reviewing test coverage, or setting up testing.

Orchestrate multi-phase project implementation using background Claude agents for isolated development, review, and integration.

OpenAI API via curl. Use this skill for GPT chat completions, DALL-E image generation, Whisper audio transcription, embeddings, and text-to-speech.

Plan, generate, and validate documentation using Prompt Architect clarity patterns and routing to doc-generator subskills.

Cross-model performance optimization and scaling configurations for autonomous agents

Manage Git worktrees for parallel Claude Code development. Use this skill when engineers ask to "create a worktree", "run parallel Claude sessions", "work on multiple features simultaneously", or need help with worktree management.

Use this skill when the user wants to run performance benchmarks, compare languages, or test the compute-average-income implementations.

Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.

Generate and iteratively harden prompts and templates using frozen evaluation harnesses and adversarial validation.