agent-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"
供给资产档案
编程与开发 Agent
代码审查、仓库分析、测试、CI、GitHub、DevOps 与开发工作流 Skill。
场景
编程 Agent
我需要一个能理解仓库、修改代码并审查 Pull Request 的编程 Agent。
适配 Agent
Claude Code + CLI + Codex
适用于 Codex、Claude Code、Cursor、CLI 或自定义 Agent。
安装
就绪
npx skills add Devin-AXIS/iPolloWork --skill agent-first-screenshots
维护状态
新鲜
今天有推送
风险
可安全尝试
Repository license is NOASSERTION; no explicit license for the skill code or documentation.
GitHub 质量
4.5K
83/100 质量 · 78/100 信任
覆盖标签
审查说明
Repository license is NOASSERTION; no explicit license for the skill code or documentation. · Scripts depend on 'sharp' but no package.json or installation instructions are provided; setup may be non-trivial.
Agent 采用评分卡
一眼查看信任、审计与安装准备度
这些分数综合公开仓库元数据、OpenAgentSkill 审查信号、维护新鲜度与安装准备度。它用于候选筛选,不替代人工审查。
质量
强可靠的选择,值得加入生产工作流候选列表。
信任
仅限沙盒有用但信任信号不足或混杂的候选项。在结果闭环证明任务匹配前,请保持在隔离工作区内使用。
审计
可安全尝试对安装准备度、安全元数据、维护情况与采用风险的机器可读审查。
OpenAgentSkill 信任评分 v5
安装前需人工审查
仅在沙盒中运行,并在用于真实工作前比较接近的替代方案。
Stars
4.5K 个 GitHub Stars
仓库活跃度
4.5K 个 Star,878 个 Fork
维护状态
今天有推送
许可证
NOASSERTION
安装
npx skills add Devin-AXIS/iPolloWork --skill agent-first-screenshots
安装安全性
标准软件包或运行时安装路径
权限范围
公开元数据中未发现高风险权限范围
Agent 结果
暂未有 Agent 结果数据
文档
Usable metadata, review docs
风险摘要
生产前审查
- Repository license is NOASSERTION; no explicit license for the skill code or documentation.
- Quality score needs review
安装准备度
安装路径可用
- 安装路径可用
- 仓库证据可用
- 已声明许可证
- 暂无 Agent 验证结果证据
Agent 可读元数据
这个 Skill 的机器可读决策数据。
使用此区块或内嵌 JSON 判断 Agent 是否应安装该 Skill、选择替代方案,或先请求人工审查。
适用任务
- 编程 Agent 工作流
- Claude Code 团队
- 重视 GitHub 采用信号的团队
- Inspect source files
适用 Agent
安装决策
- 命令
- npx skills add Devin-AXIS/iPolloWork --skill agent-first-screenshots
- 策略
- 审查
- 人工审查
- 是
信任与风险
- 信任
- 70/100
- 审计
- 85/100
- 风险级别
- 可安全尝试
结果闭环
- 端点
- /api/agent/outcome
- 事件 ID
- resolve
- 结果
- 5
不适用场景
- 需要厂商支持 SLA 的团队
- production agents without a repository review
- Repository license is NOASSERTION; no explicit license for the skill code or documentation.
- 暂未有 OpenAgentSkill 使用反馈数据
- Scripts depend on 'sharp' but no package.json or installation instructions are provided; setup may be non-trivial.
替代 Skill
Code Review
168.6K Stars
npx skills add mattpocock/skills --skill code-review
替代 Skill
Grill With Docs
164.7K Stars
npx skills add mattpocock/skills --skill grill-with-docs
替代 Skill
To Spec
164.7K Stars
npx skills add mattpocock/skills --skill to-spec
替代 Skill
To Tickets
176.7K Stars
npx skills add mattpocock/skills --skill to-tickets
Agent 安全 v2
73/100 · 安装前审查
审计与安全信号良好,公开元数据中没有高风险权限提示。
先查看审计页面,再在沙盒工作流中允许 Agent 安装。
中
网络访问
Skill 可能访问远程页面、API、仓库或外部服务。
- Repository license is NOASSERTION; no explicit license for the skill code or documentation.
安装目标
在你的 Agent 工作流中安装此 Skill
通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。
OpenAgentSkill CLI
Resolve policy, run the source installer safely, and report a verified install receipt.
$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install devin-axis-agent-first-screenshotsAgent 解析计划
让 Agent 在安装前验证匹配度。
Resolve API 返回首选 Skill、替代方案、安全策略、审计说明、安装目标和可直接执行的提示词,无需抓取此页面。
打开 JSON
/api/agent/resolve?task=Use%20agent-first-screenshots%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve 文本
/api/agent/resolve?task=Use%20agent-first-screenshots%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
安装交接
/api/skills/devin-axis-agent-first-screenshots/install
Agent 应检查
- 从 Resolve API 检查任务匹配与替代方案。
- 检查审计评分、信任评分和安全策略警告。
- 检查 Codex、Claude Code、Cursor 或 CLI 的安装目标兼容性。
复制提示词
Task: Use agent-first-screenshots in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20agent-first-screenshots%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/devin-axis-agent-first-screenshots/install
Install command: npx skills add Devin-AXIS/iPolloWork --skill agent-first-screenshots
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent 交接
把安装路径交给 Agent,而不是再给一个目录页。
通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。
安装交接
/api/skills/devin-axis-agent-first-screenshots/install
LLM 文本格式
/api/skills/devin-axis-agent-first-screenshots/install?format=text
寻找替代方案
/api/skills/search?q=agent-first-screenshots&limit=3
Agent 提示词
Use agent-first-screenshots for this task. Review https://www.openagentskill.com/api/skills/devin-axis-agent-first-screenshots/install, then install with: npx skills add Devin-AXIS/iPolloWork --skill agent-first-screenshotsRegistry 元数据
用于自动选择 Skill 的 Agent 可读档案。
本页通过 Registry API 提供相同的决策、信任、审计、场景和安装信号,让 Agent 无需抓取界面即可排序。
Agent 决策面板
适合 编程 Agent 的首选
将其作为优先候选,再在你的 Agent 环境中验证 README 与安装路径。
栈中角色
首选
主要匹配
编程 Agent
信任标签
可用于生产
安装路径
命令已就绪
适用场景
- 编程 Agent 工作流
- Claude Code 团队
- 重视 GitHub 采用信号的团队
证据
- 4,479 个 GitHub Stars
- 仓库近期活跃
- 已提供安装命令或 GitHub 仓库
- 83/100 质量档案
先审查
- Repository license is NOASSERTION; no explicit license for the skill code or documentation.
- 暂未有 OpenAgentSkill 使用反馈数据
实施路径
- 1在沙盒 Agent 中安装它,并端到端完成一次编程 Agent任务。
- 2Compare output quality, latency, and failure behavior against at least one alternative.
- 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.
信任档案
仅限沙盒
有用但信任信号不足或混杂的候选项。在结果闭环证明任务匹配前,请保持在隔离工作区内使用。
GitHub 采用度
通过4.5K 个 GitHub Stars
Star/Fork 活跃度
通过4.5K 个 Star,878 个 Fork; 当前元数据中没有议题活跃度信息
近期维护
通过今天有推送
许可证清晰度
通过NOASSERTION
积极信号
- AI 审查已通过
- 安装路径可用
- 仓库证据可用
- 近期维护的仓库
- 有意义的 GitHub 采用信号
- 安装命令未发现明显高风险模式
- 结果闭环已就绪,但需要首次真实 Agent 运行
安装前审查
- Repository license is NOASSERTION; no explicit license for the skill code or documentation.
- Quality score needs review
- 暂未有真实 Agent 结果报告
- 无人值守安装前需要人工审查
建议操作
仅在沙盒中运行,并在用于真实工作前比较接近的替代方案。
质量档案
强 适用于 Agent 工作流的候选
可靠的选择,值得加入生产工作流候选列表。
工作流匹配
在这些场景使用此 Skill
Build and ship code
Coding agents
I need a coding agent that can understand a repository, edit code, and review pull requests.
Publish consistently
Content automation
I need my agent to turn research and product updates into useful content drafts.
Process rich media
Multimodal media
I need my agent to process images, video, or audio and extract useful information.
工作流匹配
加入完整工作流
Inspect, patch, and verify code
Coding review agent
A workflow for software agents that inspect repositories, review pull requests, generate tests, and turn findings into shippable patches.
Operate and verify web apps
Browser QA agent
A workflow for agents that navigate products, fill forms, take screenshots, and verify real user flows across web applications.
Find, compare, and synthesize
Research report agent
A workflow for agents that gather sources, compare claims, summarize long material, and draft useful research briefs.
替代方案短名单
安装前对比
可能适合该任务的相近 Skill。
Code Review
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
Grill With Docs
A relentless interview that pressure-tests a plan against the codebase, sharpens domain language, and updates CONTEXT.md and ADRs when decisions become durable.
To Spec
Turn the current conversation and codebase context into a structured implementation spec, then publish it to the configured project issue tracker.
To Tickets
Break a plan, spec, or conversation into independently actionable tracer-bullet tickets with explicit blocking relationships.
概览
--- name: agent-first-screenshots description: 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. ---
# 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
1. **Only remove, never add.** Hiding a leaf distraction (notification badge, "Sign in" footer link, status text) via `display:none` is 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). 2. **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. 3. **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. 4. **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. 5. **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:
1. **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. 2. **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. 3. **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_defect` is 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").
技术详情
- 版本
- 1.0.0
- 许可证
- NOASSERTION
- 最近更新
- 2026年8月22日
- 发布时间
- 2026年8月22日
决策摘要
首选
4,479 个 GitHub Stars
Agent 验证证据
Agent 验证证据
来自解析、审查、安装和一次小范围运行后的结果报告。
- 成功率
- —
- 近期失败
- —
- 结果
- 0
- 输出质量
- —
- 失败
- 0
- 不相关
- 0
- 安装次数
- 0
- 风险拦截
- 0
- 需要配置
- 0
- 生产环境
- 0
暂时没有 Agent 结果数据。首次 Agent 执行可以通过 /api/agent/outcome 报告成功、需要设置、风险拦截、失败或不相关。
增长闭环
分享工具包
为 agent-first-screenshots 准备的场景化草稿,可手动发布到 X。
A practical pick for the next deck: agent-first-screenshots: Agent-first screenshots — an agent drives the real app via CDP and produces clean, defect-free product screenshots (newslet... 4.5K stars https://www.openagentskill.com/skills/devin-axis-agent-first-screenshots?ref=x
可选:带安装命令的回复
Listing + install path for agent-first-screenshots: https://www.openagentskill.com/skills/devin-axis-agent-first-screenshots?ref=x Install: npx skills add Devin-AXIS/iPolloWork --skill agent-first-screenshots
收录来源
Registry 收录
此列表来自公开来源,维护者认领获批前不会标记为官方。
- 创作者
- Devin-AXIS
- 收录方
- OpenAgentSkill 社区索引
归属链接指向公开仓库或创作者主页。创作者可认领列表以更新所有权信号。
认领此 Skill所有者认领
认领此 Skill 页面
这条 Registry 收录 列表归属于 Devin-AXIS,但尚未标记为官方。认领后可增加已验证所有者信号,使后续发布、安装和审计更新更值得信赖。
创作者外链工具包
将证据徽章加入你的 README
在开发者评估仓库的位置展示规范页面、当前信任与审计信号,以及真实的 Agent 验证证据。
[](https://www.openagentskill.com/skills/devin-axis-agent-first-screenshots)
[](https://www.openagentskill.com/skills/devin-axis-agent-first-screenshots)
[](https://www.openagentskill.com/skills/devin-axis-agent-first-screenshots/audit)
[](https://www.openagentskill.com/skills/devin-axis-agent-first-screenshots)作者
Devin-AXIS
@devin-axis
平台适配
健康信号
- GitHub Stars
- 4.5K
- 质量评分
- 48/100
- 最近 GitHub 推送
- 2026年8月22日
- 框架提示
- 未知
- OpenAgentSkill 浏览量
- 0
- 复制安装命令
- 0
- 跳转点击
- 0
社区信号
告诉我们这个 Skill 是否对你的 Agent 工作流有帮助。汇总反馈会持续改善排序。
信任与安全
仅限沙盒
- GitHub 采用度4.5K 个 GitHub Stars通过
- Star/Fork 活跃度4.5K 个 Star,878 个 Fork; 当前元数据中没有议题活跃度信息通过
- 近期维护今天有推送通过
- 许可证清晰度NOASSERTION通过
- README/SKILL.md 完整度公开元数据需要更完整的 README/SKILL.md 上下文信息
- 依赖与运行时风险公开元数据中未发现主要依赖风险提示通过
相关 Skill
Code Review
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
168.6K StarsGrill With Docs
A relentless interview that pressure-tests a plan against the codebase, sharpens domain language, and updates CONTEXT.md and ADRs when decisions become durable.
164.7K StarsTo Spec
Turn the current conversation and codebase context into a structured implementation spec, then publish it to the configured project issue tracker.
164.7K StarsTo Tickets
Break a plan, spec, or conversation into independently actionable tracer-bullet tickets with explicit blocking relationships.
176.7K Stars