基于 SOC 职业分类
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/binary16labs/prime-silo --skill screenshots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。
正在显示 SKILL.md
Be the operator's grounded co-pilot inside the Bridge cockpit (#/_prime_silo/bridge). Load this when the user is on the Bridge and asks "what am I looking at", "explain this graph", "what did I work on", "ingest these docs", "re-run the last manifest", or any question about the mesh on screen — memory, documents, code graph, flows, or runs.
Build animejs.com-grade scroll-driven kinetic pages with the vendored anime.js v4 bundle (website/vendor/anime.esm.min.js). Use when working on the prime-silo marketing site (website/) or any scrollytelling/animation surface. Contains the VERIFIED v4 API, the design language to emulate, the Prime-Silo set-piece specs, and the verification protocol.
Operate the Prime-Silo delivery board (delivery/) autonomously — select, claim, execute, verify, and log work contracts without frontier supervision. Use whenever picking up a task from delivery/board/BOARD.md, authoring a gate script, verifying another agent's task, or deciding which model tier should take which contract.
| name | Screenshots |
| description | Capture the current page or a DOM target as a PNG |
Use this skill when the user wants a browser screenshot.
load helper
/mod/_core/skillset/ext/skills/screenshots/screenshots.jshtml2canvas for you/mod/_core/skillset/ext/skills/screenshots/screenshots.js and pass custom html2canvasOptionshelpers
await import("/mod/_core/skillset/ext/skills/screenshots/screenshots.js")takeScreenshot({ target?, filename?, type?, quality?, html2canvasOptions? }) -> { canvas, blob, width, height, type, filename }screenshotBase64(options) -> { base64, width, height, type, filename }screenshotDownload("name.png", options?) -> downloads and returns { downloaded: true, filename, width, height, type }target
target for a full-page document.body screenshottarget may be a CSS selector string or a DOM elementpage-content.pngguidance
screenshotDownload(...) when the user wants an actual image filescreenshotBase64(...) only when JavaScript needs inline image data, because the return value is largeexamples Taking a low-level screenshot result _javascript const screenshots = await import("/mod/_core/skillset/ext/skills/screenshots/screenshots.js") return await screenshots.takeScreenshot()
Downloading a full-page screenshot _javascript const screenshots = await import("/mod/_core/skillset/ext/skills/screenshots/screenshots.js") return await screenshots.screenshotDownload("page-content.png")
Capturing a specific panel _javascript const screenshots = await import("/mod/_core/skillset/ext/skills/screenshots/screenshots.js") return await screenshots.screenshotDownload("panel.png", { target: "[data-panel]" })
Getting base64 image data _javascript const screenshots = await import("/mod/_core/skillset/ext/skills/screenshots/screenshots.js") return await screenshots.screenshotBase64()