AI Agents & Automation

You are a test automation expert specializing in generating comprehensive, maintainable unit tests across multiple languages and frameworks. Create tests that maximize coverage, catch edge cases, and follow best practices for assertion quality and test organization. Use it to give an agent explicit responsibilities, steps and constraints.

You are an expert TDD orchestrator specializing in comprehensive test-driven development coordination, modern TDD practices, and multi-agent workflow management. Use it to give an agent explicit responsibilities, steps and constraints.

You are a technical analyst. Your job is to scan the project codebase and produce accurate, project-specific documentation used by all downstream agents. Use it to give an agent explicit responsibilities, steps and constraints.

You are a Senior QA Engineer with 15 years of experience in software testing and quality assurance. You are systematic, evidence-driven, and thorough. You test against requirements — you do not modify production code. Use it to give an agent explicit responsibilities, steps and constraints.

Require a human approval signal before an AI agent can post PR reviews, comments, merges, or writes to CI configuration. Built on protect-mcp + Cedar, with every decision producing an Ed25519-signed receipt that verifies offline. Use it to give an agent explicit responsibilities, steps and constraints.

Cryptographic governance for every Claude Code tool call. Each invocation is evaluated against a Cedar policy and produces an Ed25519-signed receipt that anyone can verify offline. Use it to give an agent explicit responsibilities, steps and constraints.

This document contains the full anchored rubrics used by the eval-judge agent (Layer 2) to score skills on each of the four dimensions it assesses. Each dimension uses a 0.0–1.0 scale with five anchor points. The judge interpolates between anchors based on the evidence gathered. Use it to give an agent explicit responsibilities, steps and constraints.

This document is the authoritative reference for how PluginEval measures plugin and skill quality. It covers the three evaluation layers, all ten scoring dimensions, the composite formula, badge thresholds, anti-pattern flags, Elo ranking, and actionable improvement tips. Use it to give an agent explicit responsibilities, steps and constraints.

vector-index-tuning — templates and worked examples captures reusable agent playbook guidance for agent design & orchestration. Use it to give an agent explicit responsibilities, steps and constraints.

similarity-search-patterns — templates and worked examples captures reusable agent playbook guidance for agent design & orchestration. Use it to give an agent explicit responsibilities, steps and constraints.

rag-implementation — detailed patterns and worked examples captures reusable agent playbook guidance for agent design & orchestration. Use it to give an agent explicit responsibilities, steps and constraints.

1. Keep It DRY : Use templates to avoid repetition 2. Validate Early : Check variables before rendering 3. Version Templates : Track changes like code 4. Test Variations : Ensure templates work with diverse inputs 5. Document Variables : Clearly specify required/op. Use it to give an agent explicit responsibilities, steps and constraints.

1. Establish Baseline : Always measure initial performance 2. Change One Thing : Isolate variables for clear attribution 3. Test Thoroughly : Use diverse, representative test cases 4. Track Metrics : Log all experiments and results 5. Validate Significance : Use st. Use it to give an agent explicit responsibilities, steps and constraints.

Few-shot learning enables LLMs to perform tasks by providing a small number of examples (typically 1-10) within the prompt. This technique is highly effective for tasks requiring specific formats, styles, or domain knowledge. Use it to give an agent explicit responsibilities, steps and constraints.

prompt-engineering-patterns — detailed patterns and worked examples captures reusable agent playbook guidance for agent design & orchestration. Use it to give an agent explicit responsibilities, steps and constraints.

Chain-of-Thought (CoT) prompting elicits step-by-step reasoning from LLMs, dramatically improving performance on complex reasoning, math, and logic tasks. Use it to give an agent explicit responsibilities, steps and constraints.

llm-evaluation — detailed patterns and worked examples captures reusable agent playbook guidance for agent design & orchestration. Use it to give an agent explicit responsibilities, steps and constraints.

langchain-architecture — detailed patterns and worked examples captures reusable agent playbook guidance for agent design & orchestration. Use it to give an agent explicit responsibilities, steps and constraints.

Master modern LangChain 1.x and LangGraph for building sophisticated LLM applications with agents, state management, memory, and tool integration. Use it to give an agent explicit responsibilities, steps and constraints.

hybrid-search-implementation — templates and worked examples captures reusable agent playbook guidance for agent design & orchestration. Use it to give an agent explicit responsibilities, steps and constraints.