Primary Instruction Protocol for Senior Engineering Agents. Expert in Cognitive Architectures, Memory Systems, and 2026 Context Engineering (Updated for v0.27.0).
Select optimal LLM(s) for a task based on skill requirements, budget, and constraints. Uses the `which-llm` CLI to query Artificial Analysis benchmarks enriched with capability data from models.dev.
Execute approved beads using sub-agent model. Each bead is a work package - agent loads surgical context, designs, implements, and verifies. Continues until feature complete.
PostgreSQL architecture and design patterns skill covering database schema design, partitioning strategies (range, list, hash, multi-level), high availability architectures (streaming replication,...
Create and execute PRPs (Product Requirements Prompts) for feature implementation using Context Engineering principles. Use when planning new features, initializing PRP setup, executing existing...
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows,...
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows,...
This skill should be used when fixing bugs, implementing features, debugging issues, or making code changes. Ensures understanding of code flow before implementation by: (1) Tracing execution path...
Transform Claude Code into an autonomous software engineer using Context Engineering. Use when starting a new project, planning features, building code, verifying work, or documenting decisions....
Expert security analyst using ALL MCP servers. Uses Memory for known vulnerabilities, UltraThink for threat modeling, search MCPs for CVEs, and MongoDB for audit logs.
Use MCP servers on-demand via the mcp CLI tool - discover tools, resources, and prompts without polluting context with pre-loaded MCP integrations
Build neuro-symbolic LLM applications with Synalinks framework. Use when working with DataModel, Program, Generator, Module, training LLM pipelines, in-context learning, structured output, JSON...
Fast workflow for small changes, bug fixes, and UI tweaks that don't require full feature development. Uses sub-agent orchestration with model selection (Sonnet 4.5 orchestrator, Haiku 4.5...
Networking systems for multiplayer building games. Use when implementing networked construction, delta synchronization, client prediction, or conflict resolution. Server-authoritative model with...
Create technical diagrams using Mermaid syntax for architecture, sequences, ERDs, flowcharts, and state machines. Use for visualizing system design, data flows, and processes. Triggers: diagram,...
Delegates code review, debugging, and alternative implementation comparisons to Google Gemini CLI (`gemini`) via a JSON bridge script (default model: `gemini-3-pro-preview`). Supports headless...
Creates and modifies Claude Code sub-agents following best practices. Use when user requests creating, updating, modifying, improving, or editing sub-agents. Triggers include "create/make/new...
Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or...
Expertise in real-time multiplayer networking, lag compensation, and authoritative server architectureUse when "multiplayer game, netcode, client-server game, P2P networking, lag compensation,...
Reviews Wish SSH server code for proper middleware, session handling, and security patterns. Use when reviewing SSH server code using charmbracelet/wish.