Loading...
Loading...
Found 258 Skills
Invokes Gemini CLI as a second opinion. Use for reviewing plans, code, architectural decisions, AND for analyzing large volumes of content that benefit from Gemini's 1M+ token context window.
Use when writing instructions that guide Claude behavior - skills, CLAUDE.md files, agent prompts, system prompts. Covers token efficiency, compliance techniques, and discovery optimization.
Writing conventions for scannable, token-efficient skills and prompts. Use when creating or reviewing SKILL.md files, AGENTS.md files, or any markdown-based agent instruction documents.
Evaluates and optimizes agent skills using a DSPy-powered GEPA (Generate/Evaluate/Propose/Apply) loop. Loads scenario YAML files as DSPy datasets, scores outputs with pattern-matching metrics, and optimizes prompts via BootstrapFewShot or MIPROv2 teleprompters. Also generates new scenario YAML files from skill descriptions.
Model Context Protocol (MCP) server development and AI/ML integration patterns. Covers MCP server implementation, tool design, resource handling, and LLM integration best practices. Use when developing MCP servers, creating AI tools, integrating with LLMs, or when asking about MCP protocol, prompt engineering, or AI system architecture.
Expert prompt engineering for Google Veo 3.2 (Artemis engine). Use when the user wants to generate a video with Veo 3.2, needs help crafting cinematic prompts, or mentions Veo, Google video generation, or Artemis engine.
Replace with a clear description of what this skill does and when Claude should use it. Be specific about trigger words and use cases.
Amazon Bedrock Prompt Management for creating, versioning, and managing prompt templates with variables, multi-variant A/B testing, and flow integration. Use when creating reusable prompt templates, managing prompt versions, implementing A/B testing for prompts, integrating prompts with Bedrock Flows, optimizing prompt engineering, or building production prompt catalogs.
Analyze and improve existing prompts for better performance
Generate PhD-level expert agent prompts for Claude Code. Creates comprehensive 500-1000 line agents with detailed patterns, code examples, and best practices. Triggers on: spawn agent, create agent, generate expert, new agent, agent genesis.
Build, validate, and deploy LLM-as-Judge evaluators for automated quality assessment of LLM pipeline outputs. Use this skill whenever the user wants to: create an automated evaluator for subjective or nuanced failure modes, write a judge prompt for Pass/Fail assessment, split labeled data for judge development, measure judge alignment (TPR/TNR), estimate true success rates with bias correction, or set up CI evaluation pipelines. Also trigger when the user mentions "judge prompt", "automated eval", "LLM evaluator", "grading prompt", "alignment metrics", "true positive rate", or wants to move from manual trace review to automated evaluation. This skill covers the full lifecycle: prompt design → data splitting → iterative refinement → success rate estimation.
Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests). Do NOT use when you need to validate or calibrate the judge — use validate-evaluator instead.