全部能力

/em -postmortem — Honest Analysis of What Went Wrong

>

Persistent memory systems for LLM conversations including

Read, write, and browse the AgentHub message board for agent coordination.

P7 Senior Engineer mode — solution-driven execution under P8 supervision. Use when user says 'P7模式', '方案驱动', or when spawned as sub-task executor by P8.…

Board meeting preparation for the adversarial scenario, not the friendly one. Forces numbers-cold mastery, anticipates hard questions, builds a narrative that…

>

AI驱动的多格式SVG内容生成系统。将源文档（PDF/DOCX/URL/Markdown）转换为高质量SVG页面，并通过多角色协作导出为PPTX。当用户要求"create PPT"、"make presentation"、"生成PPT"、"做PPT"、"制作演示文稿"或提及"ppt-master"时使用。

P9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself. Use when user says 'P9模式', 'tech-lead', '帮我管理这个项目', '任务拆解', or when…

>

/em -hard-call — Framework for Decisions With No Good Options

All-in-one project configuration and health management. Sets up new projects (settings.local.json, CLAUDE.md, .gitignore), audits existing projects…

Analyze compensation — benchmarking, band placement, and equity modeling. Trigger with "what should we pay a [role]", "is this offer competitive", "model this…

Provides patterns to implement persistence layers with Spring Data JPA. Use when creating repositories, configuring entity relationships, writing queries…

BullMQ expert for Redis-backed job queues, background processing,

Merge the winning agent's branch into base, archive losers, and clean up worktrees.

Build and configure personal AI agents with memory, personality, and autonomy using OpenHanako on Electron.

Queries Hyperliquid market data using the Grimoire venue CLI. Use when you need mids, books, metadata, open orders, or a withdrawal call.

Evaluate and rank agent results by metric or LLM judge for an AgentHub session.

Interactive onboarding that learns your communication style, audiences, and data sources to configure personalized status briefings. Paste in examples of…