查找技能

Convene a roundtable of sub-agents that debate a decision or proposal from opposing perspectives — parallel independent statements, anonymous cross-review, then a chaired verdict reporting consensus and dissent.

中文简介正在准备中。当前显示原文说明。

Inspect and govern local Skills: inventory, usage evidence, duplicates, broken links, Core/On-demand proposals, Plans, Receipts, Apply, and Undo. Also find a specialized local Skill when the user requests one or the task would benefit from instructions beyond the visible catalog. Ordinary work can proceed with the Agent's existing capabilities. Not for installing third-party Skills or migrating, distributing, synchronizing, or repairing shared Skill-manager directories.

中文简介正在准备中。当前显示原文说明。

Bridge Codex to web-based AI model products by packaging local task context, scrub-checking it, sending it through an approved browser surface to ChatGPT Pro, Claude, Grok, Gemini, or another web model, waiting for the answer, and returning the model response to the user or Codex. Also guide DevSpace-like MCP Connector Mode when the user wants ChatGPT Pro or another MCP-capable web host to access approved local workspaces without relying on Codex browser automation. Use when the user asks for GPT Pro, ChatGPT Pro, Claude web, Grok, Gemini web, web model bridge, external model consult, ask another model, second opinion, use a web AI model, browserless agent access to GPT Pro, MCP connector, DevSpace-like workflow, or send local repo context to a browser-based model for planning, review, debugging, architecture discussion, or implementation guidance.

中文简介正在准备中。当前显示原文说明。

Use this skill whenever the user asks to inspect, audit, review, assess, or evaluate a codebase/project for maintainability, extensibility, architecture, reliability, security, testing, engineering quality, or AI-agent/prompt/tooling risks. Also use this when invoked by `/inspect`. It performs a read-only, evidence-backed, multi-agent project inspection with complete file coverage, per-dimension scoring, blunt technical findings, and explicit degraded-mode disclosure.

中文简介正在准备中。当前显示原文说明。

Use when a user asks Claude Code to recommend, install, update, or inspect specialized coding subagents for Claude Code, Codex, OpenCode, or multiple targets in the current repository.

中文简介正在准备中。当前显示原文说明。

Use when a user asks Codex to recommend, install, update, or inspect specialized coding subagents for Claude Code, Codex, OpenCode, or multiple targets in the current repository.

中文简介正在准备中。当前显示原文说明。

Communicate between existing local Codex App tasks that share one working directory. Use when the user asks to list or inspect same-directory tasks, send one a message or context handoff, ask a task to return a result, wait for that result, continue a request that needs user input, present an inbound task reply, or explicitly broadcast a one-way notice. Also use for Codex delegations that invoke $codex-task-messenger or contain its message-card metadata.

中文简介正在准备中。当前显示原文说明。

Improve test value and feedback cost when auditing slow, flaky, redundant or brittle tests; choosing tests during implementation; or reviewing test changes before a commit or PR. Keep ordinary implementation and pre-commit use scoped to the affected behavior, not a repository-wide audit.

中文简介正在准备中。当前显示原文说明。

Analyze an idea, proposal, change, claim, or decision from facts through problem, value, mechanism, consequences, evidence, alternatives, and action. Use when the user asks what something is for, why it matters, whether it is worth doing, what impact it has, or how to decide. Do not use for simple factual lookup or straightforward execution.

中文简介正在准备中。当前显示原文说明。

Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and stateDiagram input; inspect repository evidence when the diagram must reflect real code. Use when the user asks to visualize system architecture, infrastructure, cloud/security/network topology, technical workflows, API call sequences, request lifecycles, data pipelines, ETL/ELT, data lineage, state machines, or to convert/beautify Mermaid.

中文简介正在准备中。当前显示原文说明。

在用户已经完成一次 implementation 工作后，把项目里的 implementation plan + git diff/log 渲染成一份单文件 HTML 实施报告。报告包含 TL;DR、风险概览、架构图（mermaid）、Before/After 数据流、决策记录卡片、风险清单。用于开会前快速对齐团队、向 reviewer 解释设计决策、归档实施叙事。当用户说"生成实施报告"、"impl-explain"、"explain implementation"、"展示这次实施方案"、"做一份 HTML 实施总结"时调用本 skill。

中文简介正在准备中。当前显示原文说明。

Turn a Git repository URL or local path into one elegant, self-contained HTML learning page that teaches the project's value, architecture, and operating principles top-down with diagrams. Use when the user wants to understand, learn, onboard, explain, map, or study a repository.

中文简介正在准备中。当前显示原文说明。

Use after completing a round of code generation.

中文简介正在准备中。当前显示原文说明。

Use before declaring any coding task complete, done, or finished.

中文简介正在准备中。当前显示原文说明。

Use at the start of every session and before completing any coding task.

中文简介正在准备中。当前显示原文说明。

Use before starting any coding task when Superpowers is not present.

中文简介正在准备中。当前显示原文说明。