Skills Hub is a cross-platform desktop application for installing, organizing, updating, and syncing Agent Skills across AI coding tools. Developers use it to maintain one central skill library and distribute selected skills to tools such as Claude Code, Codex, Cursor, OpenCode, and Antigravity. Its catalogue instructions describe how to work with the managed skills.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add qufei1993/skills-hub --skill dsh-record-browser-gifgit clone --depth 1 https://github.com/qufei1993/skills-hubWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/qufei1993/skills-hub/dsh-record-browser-gif)<a href="https://agentmods.dev/skills/qufei1993/skills-hub/dsh-record-browser-gif"><img src="https://agentmods.dev/badge/skills/qufei1993/skills-hub/dsh-record-browser-gif/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/qufei1993/skills-hub/dsh-record-browser-gif"><img src="https://agentmods.dev/badge/skills/qufei1993/skills-hub/dsh-record-browser-gif.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.00561 |
| Opus 5.5 | $0.00015 | $0.00224 |
| Sonnet 5.5 | $0.00007 | $0.00112 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
dsh-record-browser-gif scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
录制并核验真实应用演示
用户要求浏览器演示 GIF 时使用。阅读项目上下文和验证证据。默认在本地采集；上传、发布或发送须属于用户明确要求的范围。不得伪造应用画面或成功状态。
- 设计简短的用户操作过程，通常包含 3–6 个有意义的状态。检查项目启动和构建命令，确认实际运行的产物与版本。全程使用相同的应用源地址、进程或运行实例、视口和会话。录制前先处理旧服务，不能录完再解释。
- 使用可用浏览器工具真实操作并截图或录屏。优先用环境已有工具，项目声明的浏览器测试库可作备用。缺少浏览器或凭据意味着受阻，不允许合成画面代替。
- 等待可观察状态，不靠固定休眠。逐一查看采集状态，不隐藏相关失败，避免暴露凭据和私有用户数据。将原始采集文件及状态说明保存在本地证据目录。
- 确认已安装
ffmpeg和ffprobe，运行自带编码器：python3 <skill-dir>/scripts/encode_gif.py <frames-dir> <output.gif> --durations 1,2,2。 视频裁剪、速度和末帧停留参数见--help。至少需要两帧，且尺寸一致。默认限制为 5 MiB、宽度 1200、10 fps，可按目标用途调整。没有覆盖原文件的意图时，不使用--force。 - 读取编码器实际退出状态，以及 JSON 中的尺寸、帧数、时长和大小。编码失败仍可能留下输出文件，文件存在不等于成功。必须从 GIF 本身解码检查帧顺序、调色板、时间和可读性；仅查看源截图无法验证编码结果。
- 返回本地 GIF，附简短说明和当前应用运行证据。文件过大或不可读时，保留操作过程，调整时长或缩放后重新核验。查看最终文件后，只发布到用户明确指定的目标。
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 18 lines · 37 tokens per session scan A 52f1021e25ba
dsh-record-browser-gif is a skill published in the GitHub repository qufei1993/skills-hub (1,848 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 561 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-31.
Other skills, from other repositories
web-extract
Open selected webpages and extract relevant正文, structured facts, tables, and source URLs. Use when an agent has one or more URLs and needs faithful page content, dynamic-page rendering, table extraction, or citation-ready evidence without yet synthesizing a full research conclusion.
browser-playwright-check
Use when an agent needs to operate or verify a web page with Playwright, including screenshots, viewport checks, navigation, forms, clicks, canvas visibility, responsive layout, or local Panel/browser behavior.
browser-use
Control approved enterprise Web applications as a digital employee through CodeFlowMu-managed Google Chrome or Microsoft Edge. Use when a Cursor Agent must open an approved Web target, inspect visible DOM controls, click, fill forms, select options, securely fill saved credentials, upload user-authorized local files…
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
ha-browser
Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…
web-app-qa
Test a web app the way a real user would: click through the main flows, try odd inputs, watch for errors, and keep screenshots as proof. You get a bug report ranked by how serious each problem is.