菜单
Compact the current conversation into a handoff document for another agent to pick up.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use this skill when the user wants to prototype an idea, sanity-check a data model or state machine, mock up a UI, explore design options, or try several approaches before committing — even if they just say "let me play with it" or "try a few designs". Creates a runnable throwable that lets the user interact with the design before implementation.
Use this skill when building, fixing, reviewing, or debugging web UI, UX, or frontend behavior and you need to exercise the app in a real browser with agent-browser. Use it to reproduce user-reported browser bugs, inspect accessibility snapshots, interact with forms and controls, capture screenshots for visual verification, check console/network failures, or compare UI before and after changes.
Convention-first frontend engineering for RunWield agents. Use this skill when implementing, fixing, debugging, or reviewing frontend UI/UX work in JavaScript, HTML, or CSS across frameworks such as React, Vue, Svelte, Next.js, Vite, Astro, or TanStack; especially when source-first code exploration, current framework docs, and real-browser verification should guide the change. Don't use for TUI work.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one the user picks. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make the codebase more testable and AI-navigable.
Use this skill when the user reports a bug, says something is broken, throwing errors, or failing — even if they don't say "diagnose" or "debug". Also use for performance regressions, when the user says something is slow, degraded, or slower than before. Follows a feedback-loop → reproduce + minimise → hypothesise → instrument → fix → regression-test loop.
| name | handoff |
| description | Compact the current conversation into a handoff document for another agent to pick up. |
| argument-hint | What will the next session be used for? |
| disable-model-invocation | true |
Write a handoff document summarising the current conversation so a fresh agent can continue the work. Save to the temporary directory of the user's OS - not the current workspace.
Include a "suggested skills" section in the document, which suggests skills that the agent should invoke.
Do not duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.
Redact any sensitive information, such as API keys, passwords, or personally identifiable information.
If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.
