LLM & Agents

Interactive planning and execution for complex tasks. Use when breaking down multi-step projects (planning) or executing approved plans through delegation (execution). Planning creates milestones with specifications; execution delegates to specialized agents.

Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.

Claude Code hook system for pre/post tool execution. Triggers on: hooks, PreToolUse, PostToolUse, hook script, tool validation, audit logging.

Opentrons Flex Gripper - automated labware movement between deck locations, modules, waste chute, and off-deck storage with precise positioning and offset control for hands-free plate transfers

Comprehensive guide for using The Force MCP server - a unified interface to 11 AI models(OpenAI, Google, Anthropic, xAI) with intelligent context management, project memory, andmulti-model collaboration. This skill should be used when working with The Force MCP tools,selecting appropriate AI models for tasks, managing context and sessions, using GroupThinkfor multi-model collaboration, or optimizing AI-assisted workflows.

Build, harden, document, and ship MCP servers to Claude standards with FastMCP 2.13+ architecture, disciplined tooling, and release-ready workflows.

Replace with a clear description of what this skill does and when Claude should use it. Be specific about the use cases, tools, or workflows this skill addresses.

This skill should be used when the user asks to "track work across sessions", "create an epic", "manage issue waves", "post a checkpoint", "claim an issue", "recover from compaction", "coordinate multiple agents", "update memory bank", "store large documents", or mentions GitHub Issues as persistent memory, multi-session work, context survival, agent collaboration, SERENA MCP memory, or project-level context. Provides complete protocols for using GitHub Issues as permanent memory that survives context exhaustion, with integrated SERENA MCP memory bank for project-level context and large document storage.

Central authority for Claude Code sandboxing and isolation. Covers sandboxed bash tool, /sandbox command, filesystem isolation (blocked access, custom paths), network isolation (domain restrictions, proxy support), OS-level enforcement (bubblewrap on Linux, Seatbelt on macOS), sandbox configuration options, escape hatches (dangerouslyDisableSandbox, allowUnsandboxedCommands), and sandbox security limitations. Assists with configuring sandbox settings, understanding isolation mechanisms, and troubleshooting sandbox issues. Delegates 100% to docs-management skill for official documentation.

Production-ready code standards following CLAUDE Framework with TDD, security, and quality requirements

Comprehensive Test Coverage and Bug Discovery Workflow (user)

Expert prompt engineering for AI systems. Use when the user wants to write or review prompts for AI, create instructions for AI systems, build system prompts, review or improve existing prompts, optimize AI instructions, or create any form of written communication intended for AI consumption (Claude, GPT, or other LLMs).

Integration skill for Lovable.dev projects. Activates when working with:- Lovable.dev projects with GitHub sync- Supabase Edge Functions that need deployment- Database migrations for Lovable Cloud- Projects with supabase/ directory structure- Any mention of "Lovable", "deploy edge function", "apply migration"Provides exact Lovable prompts for backend operations that can't be done via GitHub alone.

Create event-driven hooks for Claude Code automation. Use when the user wants to create hooks, automate tool validation, add pre/post processing, enforce security policies, or configure settings.json hooks. Triggers: create hook, build hook, PreToolUse, PostToolUse, event automation, tool validation, security hook

Automatically delegate complex, logic-intensive tasks to OpenAI Codex CLI via `codex exec --full-auto`. Claude Code uses this skill to invoke Codex for complex backend logic, intricate algorithms, or persistent bugs. Enables seamless AI-to-AI collaboration where Claude Code analyzes and Codex executes.

Delegate complex tasks to sub-agents for parallel autonomous work. Use when GPU kernel optimization, numerical correctness verification, performance profiling, or long-running validation would benefit from focused independent execution.

Meta-skill for improving and optimizing prompts using Anthropic's prompt engineering best practices. Provides the 4-step improvement workflow (example identification, initial draft, chain of thought refinement, example enhancement), keyword registries for documentation lookup, and decision trees for improvement strategies. Use when improving prompts, optimizing for accuracy, adding chain of thought reasoning, structuring with XML tags, enhancing examples, or iterating on prompt quality. Delegates to docs-management skill for official prompt engineering documentation.

Run the usage query script to retrieve account usage information for GLM Coding Plan. Only use when invoked by usage-query-agent.

Use when implementing Home Assistant integration code - covers Nov 2025 best practices for config flows, coordinators, entities, async patterns, manifest, translations, and project structure. Required reading before writing any HA code.

Vector database selection, embedding storage, approximate nearest neighbor (ANN) algorithms, and vector search optimization. Use when choosing vector stores, designing semantic search, or optimizing similarity search performance.