New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Codexqa Jev Browser

by openqa-cn in openqa-cn/codexqa

Jev browser automation with indexed actions. An agent skill from openqa-cn/codexqa.

MITAuto-check: notesTesting & QA

Install Codexqa Jev Browser

skills CLI
$ npx skills add openqa-cn/codexqa --skill codexqa-jev-browser -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install openqa-cn/codexqa codexqa-jev-browser --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/openqa-cn/codexqa.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/codexqa-jev-browser .claude/skills/codexqa-jev-browser && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
codexqa-jev-browser
GitHub stars
152
Token cost
~1.4k tokens
SKILL.md length
674 words
Files
92 (incl. references)
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Jev browser automation with indexed actions. An agent skill from openqa-cn/codexqa.

  • Works in 3 steps: Existing YAML, Markdown, or API cases →… → Only a natural-language goal → auto or… → Unknown site / coverage → explore
  • The user mentions Jev
  • SKILL.md covers Choose a mode, Commands, Model setup and After every run, plus 3 more sections
  • Runs JavaScript scripts from its folder; calls npx and npm; reaches api.typesafe.ai and api.openai.com; needs TYPESAFE_API_KEY and OPENAI_API_KEY

What it does

Codexqa Jev Browser is an agent skill from openqa-cn/codexqa. Jev browser automation with indexed actions. Replay YAML/Markdown/API cases, run goal-driven flows, generate cases, and explore sites in a real browser. Use when the user mentions Jev, browser automation, UI automation, E2E replay, test case generation, exploratory crawl, or YAML/MD/API test cases. Not a fork of browser-use/jev-ultrafast.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 95 other files, including reference files (for example `HOW_IT_WORKS.md`, `HOW_IT_WORKS.zh-CN.md` and `KNOWN_LIMITATIONS.md`).

It sits in Testing & QA, covering Browser automation, Test generation and API testing. It works with OpenAI. The repository describes itself as: codexqa: 11 local-first Agent Skills for Cursor, Claude Code, Codex & OpenClaw — change impact analysis, AI code review, defect scan, testcase generation, browser replay & RCA. The licence is MIT.

When your agent uses it

  • The user mentions Jev
  • Browser automation
  • Test case generation
  • Exploratory crawl

Example prompts

  • “/codexqa-jev-browser”

Requirements

  • Node.js
  • A credential in TYPESAFE_API_KEY
  • A credential in OPENAI_API_KEY

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Existing YAML, Markdown, or API cases → run
  2. Only a natural-language goal → auto or generate
  3. Unknown site / coverage → explore

What it can do on your machine

Read from SKILL.md and the folder at commit 7839542. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (JavaScript, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • npx
    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.typesafe.ai
    • api.openai.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • TYPESAFE_API_KEY
    • OPENAI_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Codexqa Jev Browser loads about 1.4k tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 90 tokens; SKILL.md has 674 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~90
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:42
    Keys live in a `.env` file, not in the chat. The CLI loads the `.env` next to this `SKILL.md` first, then a repo-root `.
  • NoteMentions a .env fileSKILL.md:44
    1. Read that `.env` (or `.env.example` if `.env` is missing). If `TYPESAFE_API_KEY` or `OPENAI_API_KEY` is already set,
  • NoteMentions a .env fileSKILL.md:45
    ther key is set, copy `.env.example` to `.env` in the skill directory and tell the user to fill that file. Do not ask th
  • NoteMentions a .env fileSKILL.md:60
    product. Set `HTTPS_PROXY` in the same `.env` only when that gateway needs a proxy.
  • NoteMentions a .env fileSKILL.md:62
    rite a key into case YAML. Never commit `.env`.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from openqa-cn/codexqa at commit 7839542, republished under its MIT licence (© openqa-cn). 674 words, ~1,449 tokens.

Download SKILL.mdSave it as .claude/skills/codexqa-jev-browser/SKILL.md (or your agent's skills folder). This skill also uses 91 other files; get the full folder from GitHub.
name
codexqa-jev-browser
description
Jev browser automation with indexed actions. Replay YAML/Markdown/API cases, run goal-driven flows, generate cases, and explore sites in a real browser. Use when the user mentions Jev, browser automation, UI automation, E2E replay, test case generation, exploratory crawl, or YAML/MD/API test cases. Not a fork of browser-use/jev-ultrafast.

CodexQA Jev Browser

Drive a real browser through the codexqa-jev-browser CLI (TypeScript). Do not invent CSS/XPath/coordinates or replace the engine with a host browser tool.

Choose a mode

  1. Existing YAML, Markdown, or API cases → run
  2. Only a natural-language goal → auto or generate
  3. Unknown site / coverage → explore

Install once, from this skill directory (the directory that contains package.json and SKILL.md):

bash
npm install

Playwright Chromium is the browser. Do not read another application's browser profile.

Commands

bash
npx codexqa-jev-browser observe <url-or-local-html>
npx codexqa-jev-browser run cases/examples/search-docs.yaml
npx codexqa-jev-browser run cases/examples/search-docs.md
npx codexqa-jev-browser run --from-api https://qa.example.com/cases?suite=smoke
npx codexqa-jev-browser auto --url <url> --goal '<goal>'
npx codexqa-jev-browser generate --url <url> --goal '<goal>' --out generated/case.yaml --md --verify
npx codexqa-jev-browser explore --url <url> --out generated/explore

The browser window is shown by default. Set browser.headless: true to hide it. --headed forces a visible window. --no-screenshots skips images.

Model setup

Do this before live auto / generate --goal. The CLI calls Jev or an OpenAI-compatible API itself. The host Cursor/Codex session model is not the decision model. observe, run, explore, and --decisions do not need a key. Do not stop those commands to ask for one.

Keys live in a .env file, not in the chat. The CLI loads the .env next to this SKILL.md first, then a repo-root .env, and does not override variables already set in the shell.

  1. Read that .env (or .env.example if .env is missing). If TYPESAFE_API_KEY or OPENAI_API_KEY is already set, run the command. Do not ask again.
  2. If neither key is set, copy .env.example to .env in the skill directory and tell the user to fill that file. Do not ask them to paste a key into the chat. Show this shape:
bash
# Each step: which control, which goal phrase to type, whether the step worked, whether the task is done.
TYPESAFE_API_KEY=
TYPESAFE_MODEL=jev-latest
TYPESAFE_BASE_URL=https://api.typesafe.ai/v1

# Task plan before the browser opens. Also the decision and the done check when TYPESAFE_API_KEY is empty.
OPENAI_API_KEY=
OPENAI_BASE_URL=https://api.openai.com/v1
OPENAI_MODEL=gpt-4o-mini
TEXT_MODEL=gpt-4o-mini
  1. Prefer Jev when TYPESAFE_API_KEY is set. OPENAI_MODEL is only the planner unless Jev is unset. A third-party gateway is OPENAI_BASE_URL or TYPESAFE_BASE_URL, not a separate product. Set HTTPS_PROXY in the same .env only when that gateway needs a proxy.
  2. generate writes the YAML after every successful step. Do not hand-author the case step by step while the run is walking the site.
  3. Never write a key into case YAML. Never commit .env.

Optional CLI overrides (never --api-key): --model, --base-url, --config. Model name and gateway may also live in codexqa-jev-browser.config.yaml as ${OPENAI_API_KEY}-style placeholders.

After every run

Open or summarize reports/<run-id>/report.html before concluding. It contains suite totals, every step, and screenshots. Exit code is non-zero on failure. report.json is the machine-readable copy; report.md is the short summary.

Show full SKILL.md (309 more words)Show less

Hard rules

  • Model output may only choose an operation plus an observed index. Never execute model-written selectors, JS, or shell.
  • DONE is not success. Assertions or visible evidence decide the result.
  • READ records a control Jev already sees. The control name is the fact, such as a product and its price. Jev chooses that index. It does not click, type, or ask another model to write the price. A price that is not the name of a visible control is not recorded. When the goal asks to read, list, or report those facts, READ has to record them before DONE. Text drawn only as an image is not copied.
  • Secrets stay in environment variables (${PASSWORD}), never in case files.
  • Confirm before explore/auto on logout, delete, pay, or other destructive controls.
  • Prefer semantic targets: {role, name, nth, within}.

Business knowledge

Per-app notes live in knowledge/<app>/*.md. On live auto / generate --goal, the CLI matches the start URL and the goal against each note's hosts and keywords, then appends the hits to the planner, the decision goal, and the field-text prompt. A note with general: true is included on every run.

Notes are reference for what to type and which visible control to prefer. They do not add operations. Do not copy them into case YAML. Add a new app by adding a note. Do not put that app's fill rules back into src/policy.ts.

A failed auto or generate writes reports/<run-id>/knowledge-draft.md when the failed step names a control. The draft is not active until a person runs npx codexqa-jev-browser knowledge-accept <draft>. That copies it into knowledge/<app>/. Do not accept a draft that names a secret or invents a selector.

Case sources

  • YAML is the source of truth. Markdown uses numbered Click/Type/Select/Scroll/Wait/Assert/HTTP lines.
  • --from-api pulls cases; steps may also use op: http for setup or backend checks.

Schema and verbs: references/schema.md. Examples: references/examples.md.

© openqa-cn, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 91 other files (references) in skills/codexqa-jev-browser of openqa-cn/codexqa.

  • SKILL.md
  • .env.example
  • .gitignore
  • HOW_IT_WORKS.md
  • HOW_IT_WORKS.zh-CN.md
  • KNOWN_LIMITATIONS.md
  • KNOWN_LIMITATIONS.zh-CN.md
  • LICENSE
  • README.md
  • README.zh-CN.md
  • agents/openai.yaml
  • bin/codexqa-jev-browser.mjs
  • cases/examples/api-suite.json
  • cases/examples/login.yaml
  • cases/examples/search-docs.md
  • cases/examples/search-docs.yaml
  • cases/scripts
  • … and 75 more

Open the folder on GitHubat commit 7839542

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in openqa-cn/codexqa, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Codexqa Jev Browser next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Codexqa Jev Browser compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codexqa Jev Browser this skillopenqa-cn/codexqa152—~1.4kAutomated safety check: NotesMIT
Kane CLI Browser TestingLambdaTest/kane-cli247—~8.4kAutomated safety check: PassApache-2.0
BiSheng E2E Test Generatordataelement/bisheng12k—~1.4kAutomated safety check: PassApache-2.0
Playwright Testingaehrc/pathling137—~1.5kAutomated safety check: PassApache-2.0
PR TestElite588/AUTOGPT103—~9.4kAutomated safety check: NotesCustom licence
Uat Testingooiyeefei/ccc494—~2.7kAutomated safety check: NotesMIT

Similar skills

  • Kane CLI Browser Testing

    LambdaTest/kane-cli

    Drives a real browser through the kane-cli tool and designs requirement-linked test suites from a PRD or a plain description, with mobile and cloud-grid runs.

    247 GitHub stars~8.4k tokensUpdated 2 days ago
    Testing & QAAuto-check passed

  • BiSheng E2E Test Generator

    dataelement/bisheng

    Generates and runs end-to-end tests for BiSheng, pairing pytest API tests with a manual checklist for UI behavior, from a feature spec or a free description.

    12k GitHub stars~1.4k tokensUpdated 7 days ago
    Testing & QAAuto-check passed

  • Playwright Testing

    aehrc/pathling

    Expert guidance for writing end-to-end tests with Playwright Test framework.

    137 GitHub stars~1.5k tokensUpdated today
    Testing & QAAuto-check passed

  • PR Test

    Elite588/AUTOGPT

    E2E manual testing of PRs/branches using docker compose, agent-browser, and API calls.

    103 GitHub stars~9.4k tokensUpdated 5 mo ago
    Testing & QAAuto-check: notes

  • Uat Testing

    ooiyeefei/ccc

    End-to-end User Acceptance Testing for web applications. An agent skill from ooiyeefei/ccc.

    494 GitHub stars~2.7k tokensUpdated 2 mo ago
    Testing & QAAuto-check: notes

  • Playwright

    magnus919/agent-skills

    Operate Playwright for browser automation end to end: author and debug E2E test suites (robust locators, network interception and mocking, parallel workers, accessibility snapshot checks), wire them…

    111 GitHub stars~3.4k tokensUpdated yesterday
    Testing & QAAuto-check: notes

More from openqa-cn/codexqa

All 14 skills in this repo

  • Codexqa Code Wiki

    openqa-cn/codexqa

    Builds a local architecture wiki for a repository from the CodexQA symbol graph (no model needed): modules, who calls whom and how often, reading paths, and one self-contained HTML page.

    152 GitHub stars~1.3k tokensUpdated 5 days ago
    Auto-check passed

  • Codexqa Rootcause Analyzer

    openqa-cn/codexqa

    Diagnoses exception root causes from stack traces, logs, call-chain dumps, and debug output using the CodexQA CLI for structured repo analysis.

    152 GitHub stars~2.6k tokensUpdated 5 days ago
    Auto-check passed

  • Codexqa Testdata Generator

    openqa-cn/codexqa

    Constructs test data against real backends and writes it back into test cases as executable preconditions.

    152 GitHub stars~4.8k tokensUpdated 5 days ago
    Auto-check passed

  • Codexqa Skill Router

    openqa-cn/codexqa

    Auto-routes a user request to the matching codexqa skill, then ensures that skill is on disk and follows its SKILL.md.

    152 GitHub stars~2k tokensUpdated 5 days ago
    Auto-check passed

  • Codexqa Testcase Generator

    openqa-cn/codexqa

    Generates test plans and test cases from local requirements for APP, Web, and server.

    152 GitHub stars~3.6k tokensUpdated 5 days ago
    Auto-check passed

  • Catalog

    openqa-cn/codexqa

    Constructs catalog products (standard or limited), catalog orders, and account-credit enrollment, including product-then-credit scenes.

    152 GitHub stars~514 tokensUpdated 5 days ago
    Auto-check passed

Works with

Categories

Questions about Codexqa Jev Browser

What does Codexqa Jev Browser do?

Jev browser automation with indexed actions. An agent skill from openqa-cn/codexqa. Codexqa Jev Browser is an agent skill from openqa-cn/codexqa. Jev browser automation with indexed actions.

When should I use Codexqa Jev Browser?

Codexqa Jev Browser fits situations like: the user mentions Jev; browser automation; test case generation; exploratory crawl.

How do I install Codexqa Jev Browser in Claude Code?

Run `npx skills add openqa-cn/codexqa --skill codexqa-jev-browser -a claude-code`. Or copy the skill folder (skills/codexqa-jev-browser in openqa-cn/codexqa) into .claude/skills/codexqa-jev-browser in your project. Claude Code loads it when a task matches its description.

How do I install Codexqa Jev Browser in Codex?

Run `npx skills add openqa-cn/codexqa --skill codexqa-jev-browser -a codex`. Or copy the skill folder (skills/codexqa-jev-browser in openqa-cn/codexqa) into .agents/skills/codexqa-jev-browser in your project. Codex loads it when a task matches its description.

Can I use Codexqa Jev Browser in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openqa-cn/codexqa --skill codexqa-jev-browser -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codexqa-jev-browser, .gemini/skills/codexqa-jev-browser, .github/skills/codexqa-jev-browser and .opencode/skills/codexqa-jev-browser in your project.

What does Codexqa Jev Browser need to run?

Going by SKILL.md and its folder, Codexqa Jev Browser needs JavaScript for the scripts in its folder, the command-line tools its instructions call (npx and npm) and credentials named TYPESAFE_API_KEY and OPENAI_API_KEY. Our summary lists: Node.js; A credential in TYPESAFE_API_KEY; A credential in OPENAI_API_KEY.

Does Codexqa Jev Browser access the network?

SKILL.md names 2 domains. In commands or code: api.typesafe.ai and api.openai.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Codexqa Jev Browser safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Codexqa Jev Browser use?

Codexqa Jev Browser is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Codexqa Jev Browser use?

About 1.4k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 835 tokens, read only when the agent opens those files.

What are the alternatives to Codexqa Jev Browser?

Skills that share tags, products or a category with Codexqa Jev Browser: Kane CLI Browser Testing (LambdaTest/kane-cli, 247 stars), BiSheng E2E Test Generator (dataelement/bisheng, 12k stars), Playwright Testing (aehrc/pathling, 137 stars) and PR Test (Elite588/AUTOGPT, 103 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codexqa Jev Browser?

openqa-cn (a GitHub organization) maintains it in openqa-cn/codexqa, which has 152 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 3, 2026.

Source: openqa-cn/codexqa on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.