Skills for your AI
Installs, refreshes, re-authenticates, verifies, and configures the OpenCode agent provider (CLI and SDK pinned at 1.18.25) in a NanoClaw project. Use when adding OpenCode as a provider, updating an existing install, signing in again, checking compatibility, o
Writes Opentrons Protocol API v2 Python scripts for Flex and OT-2 liquid handling, hardware modules, labware, and liquid tracking. Use when drafting a protocol file, loading pipettes/labware/modules, writing pipetting commands, scripting module control, labeli
Debug complex issues by generating competing root-cause hypotheses across six failure categories, collecting cited evidence, arbitrating the true cause, and validating fixes. Use when a bug has multiple plausible causes, initial debugging has stalled, or a fix
Provides accurate PocketBase JavaScript/TypeScript SDK code examples and guidance for CRUD, authentication, realtime subscriptions, file handling, batch operations, and query syntax. Use when a user needs SDK snippets or parameter explanations for a PocketBase
Generates detailed Markdown implementation plans for new features or code refactoring, covering analysis, affected files, tests, effort and alternatives. Use when a user describes a new feature or refactoring task, asks for a plan, scope analysis, test coverag
Generates realistic play-by-play sports commentary in traditional, hyped, analytical, or homer announcer styles, with color commentary and next-step recommendations. Use when the user wants commentary for a game or moment, a style rewrite of a draft, added col
Guides reinforcement learning post-training of LLMs with the verl library, covering GRPO, PPO, Megatron backend, datasets, installation, algorithm selection, monitoring and troubleshooting. Use when configuring or debugging verl RL training runs, choosing an R
Provides principal-level software engineering guidance on design, code review, testing strategy, technical debt, risk analysis, requirements, and technical leadership. Use when the user asks about design decisions, requests a code review, plans tests, tracks t
Use when planning and synthesizing product/user research as a method-and-repository discipline — selecting the right method for the goal (generative interviews vs usability test vs concept test vs validation), computing method-based saturation/sample size with
Generates and explains PyLabRobot Python scripts for liquid handlers, plate readers, scales, and lab equipment, including deck layouts, simulation, and protocol validation. Use when writing pipetting protocols, defining deck layouts, integrating analytical equ
Generates pymoo Python code to define multi-objective optimization problems, run NSGA-II/NSGA-III/MOEA-D, visualize Pareto fronts, apply MCDM selection, and handle constraints. Use when a user needs to model an optimization problem, choose an algorithm, plot o
Reviews Python code for common anti-patterns, diagnosing bugs, teaching best practices, drafting team standards, and planning legacy refactors. Use when the user shares Python code for review, describes a mysterious bug, asks how to avoid an anti-pattern, want
Generates pydantic-settings code and guidance for externalizing Python app configuration into typed environment variables, covering typed settings classes, fail-fast validation, local defaults, namespacing, environment-specific behavior, nested groups, secrets
Builds production-ready Python MCP servers with type-safe tools, resources, prompts, transports, and advanced features. Use when starting a new MCP server project, adding or modifying tools and resources, configuring stdio or streamable HTTP transport, debuggi
Designs and implements Python fault-tolerance patterns — retries with exponential backoff and jitter, timeouts, circuit breakers, and decorators that separate infrastructure from business logic. Use when adding retry logic to external calls, excluding permanen
Designs Python context managers and resource cleanup patterns, including class-based, async, decorator, exception suppression, streaming accumulators, string accumulation, stream metrics, and ExitStack. Use when the user needs deterministic resource management
Enforces Python code style, linting, formatting, type checking, naming, imports, docstrings and project documentation standards. Use when setting up ruff or mypy, reviewing Python code for style, writing Google-style docstrings, organizing imports, or creating
Detects code smells, applies safe incremental refactorings, design patterns, performance and legacy-code fixes while preserving behavior. Use when the user asks to clean up, restructure, de-duplicate, or reduce complexity in existing code, or to refactor legac
Integrates the Resend email channel into a chat SDK by copying and registering the adapter, installing the pinned package, validating the build and tests, storing credentials, and wiring the owner's email. Use when setting up Resend email, adding the Resend ch
Generates publication-quality scientific diagrams from natural language descriptions using iterative AI generation with quality review. Use when the user wants a scientific figure, flowchart, pathway, or architecture diagram created for a paper, thesis, grant,
Reviews code changes for AI/ML bias, accessibility barriers, privacy violations, and ethical risk, producing test reports, fix code, and RAI-ADR documentation. Use when a change involves AI/ML decisions, user-facing features, or personal data handling.
Reviews system architecture for security, scalability, reliability, cost, and AI-specific concerns using Well-Architected frameworks, and drafts Architecture Decision Records. Use when a user shares a system design, diagram, or architecture description and ask
Honestly evaluate AI work quality using a two-axis scoring system. Use after completing a task, code review, or work session to get an unbiased assessment. Detects score inflation, forces devil's advocate reasoning, and persists scores across sessions.
Creates, updates, refactors, explains, and debugs .NET Semantic Kernel code grounded in the latest official documentation. Use when building Semantic Kernel .NET projects, plugins, or agents, updating or refactoring existing SK code, explaining SK concepts, wo
