分析 Windows 崩溃转储文件（.dmp），诊断 MaaEnd 及其依赖项（MaaFramework、MXU）的崩溃。自动从 GitHub Releases 下载对应版本 PDB 符号，使用 minidump-stackwalk 解析堆栈轨迹并定位崩溃根因。当 issue 日志包或附件中发现 .dmp 文件，或用户要求分析 DMP/崩溃转储时使用。

Set up Basic Memory for a Pi workspace. Use when Basic Memory is not configured, /bm-status shows no project, recall returns setup guidance, or the user asks to enable durable memory, choose CLI vs MCP, or configure automatic continuity.

Use when addressing Basic Memory pull request feedback, failed checks, or Codex review blockers, then re-running the latest-head review gate.

Prepare and troubleshoot packaging, signing, and notarization workflows for macOS distribution. Use when asked to archive a Mac app, validate bundle structure, reason about notarization readiness, or explain distribution-only failures.

Implement, refactor, or review modern macOS SwiftUI UI for the new design system and Liquid Glass. Use when adopting Liquid Glass, updating NavigationSplitView, toolbars, search, sheets, and controls, removing custom backgrounds that fight system materials, or building custom glass surfaces with glassEffect, GlassEffectContainer, and glassEffectID.

Build, run, and debug local macOS apps and desktop executables using shell-first Xcode and Swift workflows. Use when asked to build a Mac app, launch it, diagnose compiler or linker failures, inspect startup problems, or debug desktop-only runtime issues.

星火燎原：从零起步、资源极少时，先评估客观条件，选定一个能站稳、能复用、能扩展的"根据地"（最小切入点），扎根后再逐步扩张，拒绝四处出击的流寇主义。当启动新项目、做 MVP / pilot、面对宏大目标不知从何下手、或做了很多零散事却没有积累时触发；项目已有稳固基础、只是修改现有系统时不触发。 English: Spark a prairie fire. When starting from almost nothing, assess the conditions, choose one base area (a minimal foothold that can hold, be reused, and expand), dig in, then grow step by step instead of scattering effort. Trigger for new projects, MVPs, pilots, daunting goals with no obvious first step, or busy work that accumulates nothing; skip when a solid base already exists or the task modifies an existing system.

集中兵力：多件事同时争抢时间、注意力或预算时，列出全部待办，选定唯一主攻目标并公开锁定，彻底解决、验证后再转向下一个。当待办过多、推进分散、"每件都做了一点但都没做完"、需要决定先做什么时触发；只有一个任务、任务彼此独立可并行、用户明确要求同时推进时不触发。 English: Concentrate forces. When several tasks compete for time, attention, or budget, enumerate them, lock onto a single main target, finish and verify it completely, then move on. Trigger when priorities sprawl, effort is scattered, or you must decide what to do first; skip when there is one task, tasks are independent and parallel, or the user explicitly wants them advanced together.

Sync cookies from local Chrome to a Browserbase persistent context so the browse CLI can access authenticated sites. Use when the user wants to browse as themselves, sync cookies, or log into sites via Browserbase.

Migrate browser-use (Python) browser-automation scripts to Stagehand v3 (TypeScript) on Browserbase. Use when the user wants to convert, port, rewrite, or migrate a browser-use Agent script to Stagehand, map browser-use features/APIs to Stagehand primitives (act/extract/observe/agent), or move agentic browser automation onto Browserbase with more determinism. Triggers on "browser-use", "browser_use", or "Agent(task=...)".

Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page summaries back into an agent loop so its next iteration learns from the last one.

Use when adding or following the red/yellow/green final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md instructions.

Use when asked to compare, cross-review, merge, judge, choose, or arbitrate competing plans from multiple agents such as Codex and Claude Code; when given two or more proposed plans, session IDs, transcripts, plan documents, PR descriptions, or pasted strategies; or when the user wants one recommended execution plan after agents review each other's proposals.

Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.

Answer code/product questions as visual Plan artifacts using repo, bridge, or GitHub context; use for API specs, UI look, schema models, and architecture.

Tiers, checkpoints, and off-limits paths for an agent editing the app's own source. Use when designing UI for agent editability, deciding whether a file is safe for the agent to change, or when tempted to patch config, `.env`, or an `@agent-native/*` package. Do not load it for ordinary source edits.

Generate or edit images with GPT Image 2 or 2.5 through the packaged CLI and Reference Gallery. Use for image requests including imprecise 'GPT 2.5' model names, posters, typography, reference edits, and inpainting; resolve the model choice before generation.

Use before browser-use, Playwright MCP, web browsing, browser automation, or when browser-use fails with a missing browser, missing executable, "Executable doesn't exist", or Chrome/Chromium install error in PilotDeck Desktop.

Create, edit, review, and finalize standalone XLSX, XLS, CSV, and TSV spreadsheet files. Use for spreadsheet generation, formatting, formulas, charts, data consolidation, source-based calculations, numeric reconciliation, legacy conversion, and visual QA. Do not use for live Microsoft Excel control or macro-enabled workbook editing.

Create, edit, review, and finalize editable Microsoft PowerPoint .pptx presentations. Use for new decks, source- or template-based presentations, targeted slide edits, charts, tables, images, speaker notes, visual QA, and legacy .ppt conversion. Do not use for HTML/browser presentations, Google Slides, or live Microsoft PowerPoint control.