LLM & Agents

Ensure AI agents work in an isolated Git worktree to prevent changes to the main working directory. Use when AI is about to make its first code modification in a session, or when the user requests isolated/safe editing. Triggers include starting to edit files, implementing features, or fixing bugs.

Assess quality of PRPs and work-orders using systematic confidence scoring. Use when evaluating readiness for execution or subagent delegation.

Builds AI agents on Cloudflare using the Agents SDK with state management,real-time WebSockets, scheduled tasks, tool integration, and chat capabilities.Generates production-ready agent code deployed to Workers.Use when: user wants to "build an agent", "AI agent", "chat agent", "statefulagent", mentions "Agents SDK", needs "real-time AI", "WebSocket AI", or asksabout agent "state management", "scheduled tasks", or "tool calling".

AI-Agentic Product Owner accountable for maximizing product value through effective Product Backlog management. Use when creating PBIs, ordering backlog, or accepting sprints.

GitHub Actions security and authentication for Claude Code including API keys, OIDC, AWS Bedrock, Google Vertex AI, secrets management, and permission scoping. Use when setting up authentication or discussing security for GitHub Actions workflows.

Skill for analyzing and improving compliance in the dismech knowledge base. Use this skill when checking disorder file completeness, identifying missing fields (ontology terms, evidence, descriptions), understanding weighted priority scoring, and systematically improving knowledge base coverage.

Orchestrate complex multi-agent workflows for development, infrastructure, andresearch. Provides workflow templates, agent sequences, and integration patterns.Use when planning complex projects, coordinating multiple agents, designingAPI development workflows, or infrastructure setup workflows.

Claude Code plugin authoring expert. Creates complete plugin packages with manifests, commands, agents, skills, hooks, and marketplaces following official 2025 schema. Use when creating new plugins, building marketplaces, or packaging skills for distribution.

Standardized inline markers for inter-agent communication. Use when creating handoff annotations for other agents, scanning for pending work from upstream agents, or when the user mentions @HANDOFF markers, agent coordination, or cross-agent communication.

Compare LLM models using the Artificial Analysis API. This skill should be used when the user asks to compare AI models, benchmark LLMs, evaluate model performance, compare pricing between models, or find the best model for a specific use case (coding, math, speed, cost). Triggers on requests like "compare GPT-5 and Claude", "which model is fastest", "cheapest model for coding", "benchmark comparison", "model performance analysis", or "artificial analysis". (user)

AI Developer following TDD principles in AI-Agentic Scrum. Use when implementing PBIs, managing subtasks, or executing the TDD cycle within Scrum.

Create new Claude Code skills with proper SKILL.md format, frontmatter, and best practices. Use when building, scaffolding, or generating a new skill for Claude Code.

Create custom slash commands for popular AI agents (Claude Code, Codex, Gemini CLI). Use when user asks to create slash commands, custom commands, or reusable prompts for AI agent CLIs.

Create, update, validate, and canonicalize Claude Code skills. USE WHEN user wants to create a new skill OR modify an existing skill OR validate skill structure OR fix skill format OR migrate legacy skills.

Code coverage for Rust using LLVM instrumentation with support for multiple output formats and CI integration.Use when measuring test coverage, generating coverage reports, enforcing coverage thresholds, or integrating with codecov/coveralls.Trigger terms: coverage, llvm-cov, code coverage, test coverage, coverage report, codecov, coveralls, branch coverage.

Generate GitHub repository social preview images (Open Graph images).Creates 1280x640 PNG images optimized for social media sharing.Uses nano-banana-pro for AI image generation with GitHub-specific prompts.Use when user mentions: social preview, Open Graph image, OG image,repository image, GitHub preview, social media preview, repo thumbnail,share image, or needs an image for repository settings.

Sync skill definitions to agent proxy files (.agent/workflows/skills.md and .github/copilot-instructions.md). Use after adding, removing, or modifying skills.

Build AI-first applications with RAG pipelines, embeddings, vector databases, agentic workflows, and LLM integration. Master prompt engineering, function calling, streaming responses, and cost optimization for 2025+ AI development.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Specialized skill for testing nondominium Holochain applications with Tryorama, providing comprehensive test patterns, agent simulation workflows, performance testing, and multi-agent scenario testing. Use when writing Tryorama tests, debugging zome interactions, or validating Holochain DNA functionality.