You are an elite firmware analyst with deep expertise in embedded systems security, IoT device analysis, and hardware reverse engineering. You operate within authorized contexts: security research, penetration testing with authorization, CTF competitions, and educational purposes. Use it to give an agent explicit responsibilities, steps and constraints.

risk-metrics-calculation — detailed patterns and worked examples captures reusable agent playbook guidance for quant & financial systems. Use it to give an agent explicit responsibilities, steps and constraints.

backtesting-frameworks — detailed worked examples captures reusable agent playbook guidance for quant & financial systems. Use it to give an agent explicit responsibilities, steps and constraints.

Advanced workflows including Docker integration, lockfile management, performance optimization, tool comparison, common workflows, tool integration, troubleshooting, best practices, migration guides, and command reference. Use it to give an agent explicit responsibilities, steps and constraints.

Comprehensive guide to using uv, an extremely fast Python package installer and resolver written in Rust, for modern Python project management and dependency workflows. Use it to give an agent explicit responsibilities, steps and constraints.

For advanced patterns including async testing, monkeypatching, temporary files, conftest setup, property-based testing, database testing, CI/CD integration, and configuration files, see references/advanced-patterns.md. Use it to give an agent explicit responsibilities, steps and constraints.

Advanced testing patterns including async code, monkeypatching, temporary files, conftest setup, property-based testing, database testing, CI/CD integration, and configuration. Use it to give an agent explicit responsibilities, steps and constraints.

Comprehensive guide to implementing robust testing strategies in Python using pytest, fixtures, mocking, parameterization, and test-driven development practices. Use it to give an agent explicit responsibilities, steps and constraints.

Design well-organized Python projects with clear module boundaries, explicit public interfaces, and maintainable directory structures. Good organization makes code discoverable and changes predictable. Use it to give an agent explicit responsibilities, steps and constraints.

For advanced optimization techniques including NumPy vectorization, caching, memory management, parallelization, async I/O, database optimization, and benchmarking tools, see references/advanced-patterns.md. Use it to give an agent explicit responsibilities, steps and constraints.

Advanced optimization techniques including NumPy vectorization, caching, memory management, parallelization, async I/O, database optimization, and benchmarking tools. Use it to give an agent explicit responsibilities, steps and constraints.

Before adding complexity, ask: does a simpler solution work?. Use it to give an agent explicit responsibilities, steps and constraints.

Consistent code style and clear documentation make codebases maintainable and collaborative. This skill covers modern Python tooling, naming conventions, and documentation standards. Use it to give an agent explicit responsibilities, steps and constraints.

Decouple long-running or unreliable work from request/response cycles. Return immediately to the user while background workers handle the heavy lifting asynchronously. Use it to give an agent explicit responsibilities, steps and constraints.

A reference checklist of common mistakes and anti-patterns in Python code. Review this before finalizing implementations to catch issues early. Use it to give an agent explicit responsibilities, steps and constraints.

Never block the event loop with synchronous operations. A single blocking call stalls all concurrent tasks. Use it to give an agent explicit responsibilities, steps and constraints.

Comprehensive guidance for implementing asynchronous Python applications using asyncio, concurrent programming patterns, and async/await for building high-performance, non-blocking systems. 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.