Skip to content

anbeime/skill / skills/awesome-jev/awesome-jev

awesome-jev

Verified

Find and compare JEV-related GitHub projects for a user's task, language or agent workflow using the curated Awesome JEV catalogue and scenario references. Use for project discovery and implementation research, not for executing JEV API calls.

FileKindSize
.github/workflows/validate.ymlconfig292 B
.readme-refiner/report.jsonconfig2.3 KB
AGENTS.mdmarkdown564 B
CONTRIBUTING.mdmarkdown2.0 KB
LICENSEother1.0 KB
NOTICE.mdmarkdown784 B
README.ja.mdmarkdown81.6 KB
README.mdmarkdown75.5 KB
README.zh-CN.mdmarkdown75.3 KB
SKILL.mdskill md3.5 KB
assets/readme/cover.pngbinary1.8 MB
assets/readme/cover.webpbinary98.2 KB
data/projects.jsonconfig321.3 KB
data/scenarios.jsonconfig11.4 KB
docs/agent-search.en.mdmarkdown1.6 KB
docs/agent-search.ja.mdmarkdown1.9 KB
docs/agent-search.zh.mdmarkdown1.5 KB
package.jsonmanifest425 B
scenarios/filter-content.en.mdmarkdown1.8 KB
scenarios/filter-content.ja.mdmarkdown2.1 KB
scenarios/filter-content.zh.mdmarkdown1.8 KB
scenarios/operate-interfaces.en.mdmarkdown1.8 KB
scenarios/operate-interfaces.ja.mdmarkdown2.1 KB
scenarios/operate-interfaces.zh.mdmarkdown1.7 KB
scenarios/retrieve-context.en.mdmarkdown1.7 KB
scenarios/retrieve-context.ja.mdmarkdown2.0 KB
scenarios/retrieve-context.zh.mdmarkdown1.8 KB
scenarios/review-work.en.mdmarkdown1.7 KB
scenarios/review-work.ja.mdmarkdown2.0 KB
scenarios/review-work.zh.mdmarkdown1.7 KB
scenarios/route-agents.en.mdmarkdown1.7 KB
scenarios/route-agents.ja.mdmarkdown1.9 KB
scenarios/route-agents.zh.mdmarkdown1.7 KB
scenarios/trim-context.en.mdmarkdown1.7 KB
scenarios/trim-context.ja.mdmarkdown1.8 KB
scenarios/trim-context.zh.mdmarkdown1.7 KB
scripts/AGENTS.mdmarkdown371 B
scripts/add-star100-batch.mjsscript24.0 KB
scripts/curate-star50-expansion-2026-09-21.mjsscript22.1 KB
scripts/curate-star50-expansion-2026-09-22.mjsscript22.7 KB
scripts/curate-star50-expansion-2026-09-23.mjsscript14.2 KB
scripts/discovery.test.mjsscript2.7 KB
scripts/export-website-data.mjsscript4.4 KB
scripts/import-competitor-supplement.mjsscript12.2 KB
scripts/refresh-curated-projects.mjsscript28.8 KB
scripts/refresh-stars.mjsscript3.2 KB
scripts/sync-readmes.mjsscript14.1 KB
scripts/validate.test.mjsscript4.5 KB

scenarios/operate-interfaces.zh.md

View on GitHub
<!-- Generated from data/scenarios.json + data/projects.json. -->
[← 返回检索入口](../README.zh-CN.md#discovery)

# 自动操作网页与桌面

根据当前界面选择下一步动作,由程序实际执行。

**JEV 在哪一步**

观察界面与合法候选动作 → JEV 选择目标和动作 → 执行器操作

## 可以参考的项目

### [Jev Ultrafast](https://github.com/browser-use/jev-ultrafast)

用 JEV 一次选出浏览器动作与对应 DOM 元素,只在需要输入文本时再调用文本模型。

**值得参考什么:** 参考动作与 DOM 目标一起选择,以及与文本生成的分工。

[源码证据](https://github.com/browser-use/jev-ultrafast/blob/1231850a0bf1a0c0341fe408ef1668dbbfdfac46/jev_ultrafast/model.py)

### [Cua · JEV Use](https://github.com/trycua/cua)

把 Cua Driver 的观察与执行能力和 JEV 的有限动作选择结合起来。

**值得参考什么:** 参考界面观察如何转成有限动作 ID 的选择。

[源码证据](https://github.com/trycua/cua/blob/83f142c4290a0f7d9ed545ae8532858c6e4f8145/libs/cua-driver/examples/jev-use/python/jev_adapter.py#L11)

### [Agent Desktop · JEV Skill](https://github.com/lahfir/agent-desktop)

根据系统无障碍数据选择原生桌面控件与动作的可选 JEV Skill。

**值得参考什么:** 参考通过无障碍数据选择原生桌面控件。

[源码证据](https://github.com/lahfir/agent-desktop/blob/7a8e4a10281c7319733aa200fd79501f34529716/scripts/jev/act.mjs)

这些项目分别展示该模式的一部分,并非一套开箱即用的完整应用。源码核对不代表运行、性能或 BeatAPI 接入兼容性已经验证。

[试用免费 JEV API](https://docs.beatapi.io/decisions#free-calls) · [用 Agent 搜索](../docs/agent-search.zh.md)
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall