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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Vesely/skills --skill cursor-agent命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Upload an image, GIF or video into a GitHub PR or issue body and get back a github.com/user-attachments URL. `gh` has no native command for this — this is the same endpoint the web UI's drag-and-drop uses, so the asset inherits the repo's visibility instead of sitting on a public host. Use when embedding a screenshot, before/after collage, screencast or UI proof into a PR description, an issue, or a review comment. Triggers on "put this screenshot in the PR", "attach this to the issue", "embed this video in the PR description", "upload proof to GitHub", "nahraj to do PR".
Generates annotated browser screenshots of every UI change as the primary PR deliverable — plus an optional GIF screencast for multi-step or animated flows — then writes a concise PR title and description ready to paste into GitHub, and optional data-model documentation notes. Reviews the current branch diff against the default branch, captures every affected user-facing surface with the agent-browser CLI, marks the changed elements in red, stitches the shots into a collage with ImageMagick, hosts it through a configured uploader (or leaves it local for drag-and-drop), and embeds it in the PR body with per-panel captions. Use whenever the user wants to write a PR description, document branch changes for a reviewer, create a PR writeup, prepare a handoff, or says things like "write PR description", "prep the PR", "PR handoff", "document my changes", "screenshot my PR", or "generate PR notes". Also trigger when the user just says "PR" in the context of finishing or shipping work.
Turn an agent-browser session into a polished product-demo video — fully local, free, no cloud upload. Records the browser to WebM while logging every action, then composites an MP4 with automatic zoom-to-click, a smooth animated cursor with trail, click ripples, a keystroke overlay (keycast), idle trimming, chapters (burned-in lower-thirds plus embedded MP4 chapters), and a gradient background with a rounded, shadowed browser card. Use this whenever the user wants to record or generate a demo video, screencast, walkthrough, "how it works" clip, or animated screen recording of a web flow — especially one that looks like Screen Studio (auto-zoom, keystrokes, chapters) but produced by the agent itself. Trigger on "record a demo", "make a screencast", "generate a walkthrough video", "demo video with zooms and chapters", "record the signup/onboarding flow". Built on the agent-browser CLI; requires ffmpeg and Node. Not for live screen capture of the whole desktop — it records a browser flow the agent drives.
基于 SOC 职业分类
正在显示 SKILL.md
| name | cursor-agent |
| description | Delegate a task to Cursor's CLI agent (code review, Q&A, planning) for a second opinion from a non-Claude model |
| allowed-tools | ["Bash(cursor-agent:*)","Bash(git diff:*)","Bash(git log:*)","Bash(git status:*)"] |
| when_to_use | Use when the user wants to run cursor-agent (Cursor's CLI). Triggers: 'cursor review', 'ask cursor', 'use cursor', 'review with cursor', 'second opinion from cursor', 'cursor-agent', 'use cursor-agent'. Also use for verifying code/plans/texts/UI with a different model than Claude. |
| argument-hint | [task for cursor-agent, e.g. 'review this branch'] |
| arguments | ["task"] |
Delegate a task to Cursor's headless CLI agent (cursor-agent). Use this to get a second opinion from a non-Claude model on code reviews, plan critiques, text/copy review, or general Q&A.
$task: The task to hand to cursor-agent. Usually a review or question prompt. If the user adds a model hint (e.g. "with Opus", "using GPT", "pomocí Sonnetu"), extract it and pass via --model.Run cursor-agent headless, surface its output to the user, and add a brief Claude TL;DR so the user doesn't have to re-read a wall of text.
Extract from $task and the surrounding conversation:
--model claude-opus-4-7-medium--model claude-4.6-sonnet-medium--model gpt-5.3-codex--model gemini-3.1-pro--model auto--model (cursor uses its default: composer-2-fast)--mode plan--mode (cursor can write)--mode ask (read-only, default)Success criteria: Flags decided, prompt ready.
If the task is a code review:
main (git diff origin/main...HEAD), or uncommitted changes (git diff HEAD)."Review the branch
<name>against main. Usegit diff origin/main...HEADto see the actual changes. Focus on real issues (correctness, edge cases, security); skip nitpicks. Report under ~400 words withfile:linereferences."
For non-review tasks (ask/plan/text/UI), pass the task as-is.
Success criteria: Final prompt string ready for the CLI.
Invoke headless via Bash:
cursor-agent -p --output-format text [--mode <mode>] [--model <model>] "<prompt>"
-p (print/headless).--output-format text unless the task needs structured output.--workspace unless the user explicitly asked for a different dir.--mode ask or --mode plan), no extra permission flags are needed. For headless write mode, do not silently add --force or --yolo; ask the user first.tail -n 200 if you suspect a very long response and want to cap context use. By default, take the full output.Success criteria: cursor-agent returns (exit 0) with a response. If it errors (auth, model not available), surface the error to the user instead of hiding it.
Present to the user in this order:
Keep the summary tight — the goal is to save the user from re-reading, not to replace cursor's output.
Success criteria: User sees both cursor's raw output and a Claude-curated action list.
cursor-agent --list-models shows every available model ID. If the user asks for something exotic (e.g. "thinking tier", "max tier"), check the list first.cursor-agent reads/writes inside the current workspace like any CLI tool — it is not sandboxed by default. Treat its output the same way you'd treat a teammate's PR comment: trust but verify.cursor-agent interactively themselves (no -p).