Explore

Proactive layered recall and generic domain-aware routing.

自动归档 + 知识图谱同步 + 记忆生命周期管理

Vue 2/3 代码规范检查。包括组件命名、Props 校验、Composition API 规范等。

国际化完整性检查。检查翻译 key 是否缺失、硬编码文本、locale 文件一致性。

Code review with LSP-powered code intelligence. Uses MCP tools (diagnostics, hover, references, definition, symbols) for semantic code understanding, not just text grep.

大规模扫描硬编码凭证，忽略占位符

Rust 服务审查：panic、SQL 注入、密钥、错误吞没、遗留标记

Python 遗留代码审查：bare except、SQL 注入、反序列化、密钥、调试输出

Operate web pages in Emperor's built-in browser with the browser_* tools, and macOS app windows with the desktop_* tools — open or bind a target, read it, fill, click or type, and verify the result. Use when a task needs a real web page or app window (a form, a dashboard, a site or app without an API or CLI). Requires Settings › 电脑操作 to be switched on.

Use after task analysis when a non-trivial Formax repository task needs a structured `docs/todolist.md` with [x]/[ ] items, definitions-before-UI ordering, explicit non-goals, tests, and loop-ready execution slices.

Use after receiving WebGPT or another LLM review on a Formax todo and before sending the todo back for another pass. Produce a concise handoff response that says what we adopted, what we reject or question, and what the reviewer should specifically re-evaluate in `docs/todolist.md`.

Use for all frontend and web UI tasks by default to apply a business-agnostic desktop web visual style system with medium-strength guardrails; if an existing design system is present, follow it first and use this skill only as a style harmonizer.

Use when changing web CSS/UI styling so requirements, state ownership, and acceptance checks are locked before edits to prevent rework churn.

Implement or refactor Formax tool transcript UI using the Tool UI Blocks (C-lite) pattern (ToolUiBlocks renderer + blocks presenters) to avoid touching many tool presenter files; use when adjusting ⏺/⎿ spacing, indent rules, or migrating additional tools to blocks presenters with targeted Ink/Vitest tests and Codex review before commit.

Use when adding or fixing Formax tests (especially Ink UI tests) and you need deterministic synchronization in test interactions.

Use when designing, refactoring, or debugging Formax system prompt assembly, system-reminder injection, or skills/deferred-tool prompt exposure semantics; mandatory for any change involving FORMAX_DEFERRED_TOOL_EXPOSURE and request-payload parity checks.

Use when changing REPL clear/reset/resume/surface behavior (onClearTerminal, transcriptSeq remount, Ink Static paths, Ctrl+O/Ctrl+E transitions). Enforces single-owner reset transaction and prevents black-screen/flicker/duplicate-row regressions.

Use when adding/modifying Formax slash commands (/permissions /agents /hooks /todos etc), especially output rendering (command sublines), overlay dismiss messages, and whether outputs are injected into the next LLM turn.

Run a read-only verification pass after implementation to check whether completion claims are real, validation actually ran, and obvious edge cases or regressions were missed.

Coordinate multiple agents by splitting work into research, synthesis, implementation, and verification, assigning ownership, and keeping the coordinator focused on integration rather than raw exploration.

Compress a long agent conversation into a nine-part continuation summary that preserves request, files, errors, user messages, current work, and the next aligned step.

Extract durable memories from recent conversation turns into user, feedback, project, and reference categories while avoiding stale code-state facts.

Build a lightweight proactive mode with scheduled checks, sleep intervals, concise user briefs, and expiry safeguards so an agent can work in the background without becoming an uncontrolled daemon.

Consolidate recent logs, sessions, and existing memory files into durable topic memories, normalize dates, prune stale entries, and keep MEMORY.md short enough for prompt use.

Generate beautiful, high-resolution mindmaps from Markdown unordered lists. Outputs interactive HTML, HD PNG, and PDF with colorful branch themes.

Render Mermaid diagrams as SVG or ASCII art using beautiful-mermaid. Use when users need to create flowcharts, sequence diagrams, state diagrams, class diagrams, or ER diagrams. Supports both graphical SVG output and terminal-friendly ASCII/Unicode output.

Control desktop apps on Windows through Computer Use just like OpenAI Codex and ChatGPT Desktop. Use to interact with Windows applications, click UI elements or coordinates, drag, scroll, type text, press keyboard shortcuts, assign element values, capture appshots (screenshots and Windows UIAutomation trees), and list running apps.

Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit. Use when asked to record an e2e run, demo a fix on a PR, attach a GIF or screen recording to a pull request, show a test passing visually, or produce a terminal recording of pi-go. Encodes the sandbox trap that makes VHS segfault on the first attempt.

Brief — the owner's day in review: tasks, calendar, mail, Telegram, every Connection and plugin, goals from CORE, weather. Load in a scheduled Brief turn (08:30 and 14:00 by default), on /digest, and when the owner asks for a day plan, a review of the day or their open tasks.

Use for complex multi-step tasks. Create a structured plan before writing code. Use when the user asks for a plan, spec, or when the task is too large to implement in one step.

Use when implementing any feature or bugfix, before writing implementation code. Enforces red-green-refactor cycle with strict rules.

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

Use when development work is complete and you need to prepare for merge. Guides through cleanup, testing, documentation, and creating a well-structured pull request.

Use when reviewing code for bugs, security issues, performance problems, or adherence to best practices. Provides structured code review with severity levels and actionable feedback.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Use when you have a spec or requirements for a multi-step task, before touching code

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

Use when implementing any feature or bugfix, before writing implementation code

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when executing implementation plans with independent tasks in the current session

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Pull skills from a remote GitHub repository into the local skills directory. Use when the user wants to install shared skills.

Create a new skill with guided setup. Use when the user wants to create a custom skill for pi-go.

Enforce "no evidence = no completion"; run Gate Function verification before declaring done.

Use Git worktrees to create parallel working directories safely; avoid branch-switch contamination.

Drive changes with Red→Green→Refactor; ensure behavior is verifiable and regression-safe.

Use when investigating a bug, test failure, flaky test, unexpected behavior, or a hotfix, or an unexplained or failed fix; find the root cause first.

Decompose tasks via subagent collaboration; define interface contracts and integration checkpoints.

Check official docs when framework APIs or configuration may be version-sensitive.

Evaluate when to dispatch parallel agents; use a 4-step pattern to split, coordinate, and integrate results.

Design schemas and migrations when persistent data structures change.

Secure authentication and authorization when credentials, sessions, roles, or permissions change.

Design or review REST/GraphQL APIs when endpoints or contracts change.