Boost efficiency with task automation and organizers.
Help users who struggle with prompt design by turning their vague questions or tasks into high-quality, structured Japanese YAML prompts. Ask clarifying questions with examples when information is missing, then output the final prompt as a YAML code block.
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 an agent's capabilities with specialized knowledge, workflows, or tool integrations.
The Glue of the PM Brain. Owns task lifecycle, brain dump triage, reconciliation, and archive automation. Use for
Manages context across multiple agents and long-running tasks. Use when coordinating complex multi-agent workflows or when context needs to be preserved across sessions. Essential for projects exceeding 10k tokens.
Activates when the user asks about Agent Skills, wants to find reusable AI capabilities, needs to install skills, or mentions skills for Claude. Use for discovering, retrieving, and installing skills.
Build multi-step LLM agents for the Continuum system. Use when creating agent definitions with nodes, edges, tools, and execution flows. Triggers on requests to "create an agent", "build a workflow", "design an agent graph", or when discussing Continuum agent architecture. Supports parallel execution, conditional routing, tool integration, and structured outputs.
Invoke external AI CLIs via native Task agents (Claude, Codex, Gemini, Cursor). Primary mode for multi-provider orchestration with fork-terminal fallback for auth.
Create custom slash commands for workflow automation in OpenCode. Use when creating commands, automating workflows, or when user mentions slash commands, custom commands, /command patterns, or workflow automation.
Message Batches API for Claude with 50% cost savings on bulk processing. Activate for batch jobs, JSONL processing, bulk analysis, and cost optimization.
Enables autonomous context management for codebases through claude.md files. Use when creating, maintaining, or synchronizing AI agent context. Provides tools and workflows for monitoring context health, detecting staleness, and updating intelligently. Helps Claude work proactively as a context manager.
Use when creating, improving, or reviewing Claude Code skills. Covers frontmatter, tool use patterns, file structure, hooks, and CC platform limitations. Also invoke superpowers:writing-skills for CSO and testing workflow.
This skill should be used when the user asks to "execute plan with beads", "implement with persistent tracking", "bead-driven execution", "run plan with subagents", "track tasks across sessions", "use beads for planning", or wants planning + subagents + beads + code review unified. Orchestrates writing-plans, executing-plans, and investigation skills with beads integration for persistent cross-session tracking.
Handle support tickets, FAQ responses, and customer emails. Creates help docs, troubleshooting guides, and canned responses. Use PROACTIVELY for customer inquiries or support documentation.
Guide for creating Claude Code hooks - shell commands that execute at specific lifecycle events (SessionStart, SessionEnd, PreToolUse, PostToolUse, etc.). Use when users want to automate actions, add validation, logging, or integrate external tools into Claude Code workflows.
Generate structured requirements from natural language. No API key required - uses Claude Code OAuth.
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.
Create custom Claude Code sub-agents with specialized expertise and tool access. Use when you need to build reusable agents for specific tasks like code review, debugging, data analysis, or domain-specific workflows.
Collaboratively refine ideas through structured questioning - helping both Claude understand and the user crystallize their thinking. Use when the user provides an idea, feature request, Linear ticket, or concept that needs fleshing out. Triggers on requests like "interview me about X", "help me spec out Y", "I have an idea for Z", or when explicitly invoked. Output format adapts to context (update existing artifacts, create new specs, or just synthesize insights).
This skill should be used when the user asks about "JSON flags", "token IDs", "cross-tool references", "progressive detail", "response optimization", "human and LLM readable", "automation flags", "confidence-based detail", or discusses optimizing MCP responses for both human and machine consumption. Provides patterns for human/LLM readable responses with automation-friendly structures.
Create distinctive, production-grade web interfaces with high design quality. Use for components, pages, dashboards, and full applications that need to stand out from generic AI aesthetics.
Use when the user wants to create a new Claude Code skill, build a custom skill, or needs help structuring skill instructions. Guides users through creating properly formatted skills with YAML frontmatter, clear descriptions, and comprehensive instructions.
Scaffolds a new Python agent for autonomous AI tasks in 'src/agents/'. Agents are autonomous components that handle complex operations (resume analysis, job matching, KSC generation). Use when asked to create a new AI agent or automation component.
Ideas Mode specialist - handles organisation, tagging, canvas layouts, and creative capture workflows for the calm creative workspace.
