anthropics/skills180kagent-first-screenshots
Agent-first screenshots — an agent drives the real app via CDP and produces clean, defect-free product screenshots (newsletters, landing pages, social, decks, PR). Dual-channel verification (DOM + pixels + vision) in a capture loop. Use for any "take/redo screenshots of the app" task.
安装
把这段话发给 Claude Code、Codex 或 Cursor。智能体会先检查安全性,你确认后才安装。
读取 https://funcoding.ai/skills/devin-axis/ipollowork/agent-first-screenshots/install.md ,按里面的步骤帮我安装这个 Skill。
SKILL.md
Agent-First Screenshots
An agent-first screenshot is produced by an agent driving the real app via CDP, gated by structural + pixel + vision verification before it ships. It turns screenshots from hand-crafted artifacts into a regenerable pipeline.
Use this for "take/redo screenshots / make marketing images" tasks. It is NOT
e2e evidence — for pass/fail proof use the fraimz skill.
The Zero-Defect Bar
A shippable screenshot has ZERO obvious visual defects — the bar is not "the content is present", it is: would a human glancing at it immediately spot something broken? Overlapping or clipped text, misaligned/collapsed layout, garbled or mid-transition content, blank regions, stray modals/tooltips — any of these disqualifies the frame. Full stop.
The One Method
Operate the app like a power user preparing a demo, not like a developer hacking the DOM. The app already looks great: get it into a real, settled state through the UI and capture it cleanly. Never rebuild or fake it.
Golden Rules
- Only remove, never add. Hiding a leaf distraction (notification badge,
"Sign in" footer link, status text) via
display:noneis safe. Never inject fake HTML, override flex/height/width on structural containers, add fixed-position overlays, or mutate the DOM tree — the layout engine will collapse (scroll areas shrink to 0, content disappears). - If a feature isn't available, don't fake it. Enable it through the settings UI like a real user, or skip the shot and say so.
- Each shot starts from a clean reload.
location.reload(), wait for full render, navigate through the UI, minimal leaf cleanup, verify, capture. Never carry CSS hacks across shots. - Get state naturally. Click the real tabs/buttons/pickers; close panels via their close buttons (not CSS); run real multi-turn tasks so content is impressive — no toy data, no mid-stream captures.
- Match the target aspect ratio via CDP metrics override (e.g. 1440x900
at
deviceScaleFactor: 2), then wait ~1s and re-verify — the override can trigger re-layout.
Verify with three channels, in a loop
innerText existing does not mean visible; a healthy DOM rect does not mean it
rendered. Every frame must pass all three before it ships:
-
DOM pre-check (cheap, before capture): scroll area height > 100px (not collapsed), hero text inside the viewport rect, no unexpected modal/overlay. If it fails: reload and redo — never fix with more CSS.
-
Pixel post-check (truth, after capture): decode the PNG and sample the DOM-derived hero rects. Calibration: for text-on-white UI, background ratio is a bad signal (85–92% background is normal). Variance is the reliable signal: content-filled region variance > ~200 (often 1000+); blank/flat region < 50. Whole-image
bgRatio > 0.97→ blank frame. -
Vision check (mandatory gate): deterministic stats CANNOT catch the defects that matter most — overlap, clipping, misalignment, double-rendering. Hand the PNG to a vision-capable model with a zero-defect rubric returning JSON:
{ any_obvious_defect: bool, // the gate — if true, REJECT overlapping_text_or_elements: bool, clipped_or_cutoff: bool, misaligned_or_broken_layout: bool, blank_or_empty_regions: bool, stray_modal_tooltip_or_panel: bool, legible: bool, polish_score: 1-5, defects: ["..."] }If
any_obvious_defectis true the frame is rejected regardless of layers 1–2. Diagnose, fix the root cause (settle the state, close the picker, reload), recapture.
Reusable scripts in this skill's directory: screenshot-verify.mjs (verify an
existing PNG) and capture-verify.mjs (capture at 2x + verify regions + save
only on pass); both use sharp.
Common failure modes
| Symptom | Fix |
|---|---|
| Overlapping/clipped text (layers 1–2 pass) | Unsettled/edit-mode/wrong-width state — settle, use preview mode, gate on vision |
| Blank screenshot / 32px scroll area | Structural element was CSS-hidden — reload, close panels via UI |
| Overlay (picker/modal) on every shot | It was opened and never closed — Escape before capturing |
| In DOM but not in pixels | Clipped/blank render — trust variance + vision, not innerText |
Anti-patterns
Injecting fake components; overriding flex properties; fixed-position
overlays; carrying state across shots; verifying via innerText only;
proof-frame mindset (the goal is "I want that", not "it didn't crash").
相似的 Skill
anthropics/skills180k
anthropics/skills180kbrand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
AI 与智能体
anthropics/skills180kinternal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
AI 与智能体
anthropics/skills180kmcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
AI 与智能体
anthropics/skills180kalgorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
AI 与智能体
anthropics/skills180kacademy-guide
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.
AI 与智能体