LLM & Agents

Find where potential customers discuss problems online and extract their language patterns. Provides starting points for community research, not exhaustive coverage.

Router skill for DiPeO frontend (React, visual editor, GraphQL integration, TypeScript types). Use when task mentions React components, diagram editor, GraphQL hooks, or type errors. For simple tasks, handle directly; for complex work, escalate to dipeo-frontend-dev agent.

Manage coordinator daemon tasks, approve/reject work, monitor autonomous agents. Use when user asks to delegate tasks, check task status, review agent work, manage the coordinator, or use GitHub-driven approval workflow.

Guide for designing effective memory architectures in Letta agents. Use when users need help structuring memory blocks, choosing between memory types, or optimizing memory management patterns.

Router skill for DiPeO runtime Python code (execution handlers, service architecture, domain models, LLM infrastructure). Use when task mentions node handlers, EventBus, ServiceRegistry, Envelope pattern, or domain logic. For simple tasks, handle directly; for complex work, escalate to dipeo-package-maintainer agent.

Use when generating options or clarifying a build/fix request—pull constraints from the user, list varied approaches, then narrow with them to pick a plan. For code reviews, use briefly to confirm expectations, then hand off to the agent flow.

Reviews code diffs (uncommited changes written by the agent) or new files(untracked files) for Python type hinting and structural principle compliance. Use this skill when user say review code diffs or new files or want to check code quality(when file is a python file). Requires explicit user confirmation before applying any modifications to ensure code quality and safety.

LLM evaluation and testing patterns including prompt testing, hallucination detection, benchmark creation, and quality metrics. Use when testing LLM applications, validating prompt quality, implementing systematic evaluation, or measuring LLM performance.

Analyzes code to identify untested functions, low coverage areas, and missing edge cases.Use when reviewing test coverage or planning test improvements.Generates specific test suggestions with example templates following amplihack's testing pyramid (60% unit, 30% integration, 10% E2E).Can use coverage.py for Python projects.

Shared configuration patterns for project setup commands. Provides security hooks, Claude framework structure templates, and framework detection patterns used across multiple setup commands.

Extracts key learnings from conversations, debugging sessions, and failed attempts.Use at session end or after solving complex problems to capture insights.Automatically suggests updates to: DISCOVERIES.md (learnings), PATTERNS.md (reusable solutions), new agent creation (repeated workflows).Ensures knowledge persists across sessions.

Generates and improves tests following TDD principles. Activates when new features are implemented, test coverage is low, or user requests tests. Ensures comprehensive test coverage with unit, integration, and edge case tests.

Use when building CLI tools, implementing argument parsing, or adding interactive prompts. Invoke for CLI design, argument parsing, interactive prompts, progress indicators, shell completions. Keywords: CLI, terminal, command-line, commander, click, cobra.

Creates, refines, and validates Claude Code skills following amplihack philosophy and official best practices. Automatically activates when building, creating, generating, or designing new skills.

Use for PR/code reviews and any task that benefits from a dedicated tmux sub-agent with per-task git worktrees; default path for reviewing diffs (read diff → summarize → run checks/tests) with automated monitoring.

Multi-agent consensus voting with domain-weighted expertise for critical decisions requiring structured validation

Use when designing prompts for LLMs, optimizing model performance, building evaluation frameworks, or implementing advanced prompting techniques like chain-of-thought, few-shot learning, or structured outputs.

6-phase investigation workflow for understanding existing systems. Auto-activates for research tasks.Optimized for exploration and understanding, not implementation. Includes parallel agent deploymentfor efficient deep dives and automatic knowledge capture to prevent repeat investigations.

{Brief description for Claude Code skill invocation. Include primary triggers and capabilities.}

Comprehensive knowledge of Claude Agent SDK architecture, tools, hooks, skills, and production patterns. Auto-activates for agent building, SDK integration, tool design, and MCP server tasks.