agentjido/jido_run/jido-browser
- community
Checking that the SKILL.md file is still in the repository.
Builder-oriented guidance for the upstream `jido_browser` package. Use when Codex needs to build browser-backed Jido automations, wrap navigation or extraction flows in actions, turn browser docs into runnable examples, or review `jido_browser` boundaries versus `req_llm` and app-specific scraping code.
Install
npx vskill@latest install agentjido/jido_run/jido-browserSKILL.md
Jido Browser
jido_browser is the upstream Hex package name.
Start Here
Use this skill when the workflow needs a browser, page state, or DOM interaction rather than plain HTTP requests.
Good triggers:
- "Build a Jido agent that logs in and gathers data from a website."
- "Wrap a browser step in a
Jido.Action." - "Turn the browser package docs into a runnable demo."
- "Review whether this should use browser automation or a simpler HTTP client."
Read references/builder-notes.md before implementing when selectors, navigation state, or safety limits matter.
Primary Workflows
Build browser-backed actions
- Separate navigation, observation, and mutation steps.
- Keep selectors and site assumptions explicit so the action can fail predictably when a page changes.
- Prefer small page operations over giant "do everything" browser actions.
Decide when browser automation is justified
- Use
jido_browseronly when the target behavior depends on rendering, authentication state, or DOM interaction. - Prefer
req_llm, Req, or API clients for stable JSON or HTML endpoints. - Minimize the amount of browser state that leaks into the rest of the agent runtime.
Turn docs into runnable examples
- Choose one real browsing scenario such as login, extract, click, or form submit.
- Show the browser step inside a broader Jido workflow only after the page-level behavior is clear.
- Add waits, retries, or assertions only when the docs justify them.
Review boundaries
- Keep DOM and navigation logic in
jido_browser. - Keep prompt or reasoning loops in
jidoorjido_ai. - Keep site-specific product logic in the application layer.
Build Checklist
- Confirm that the target site really requires browser automation.
- Define selectors, navigation transitions, and failure conditions up front.
- Capture only the page data the next step needs.
- Add tests or examples that tolerate timing and rendering variability.
Boundaries
- Do not use this skill for generic web scraping when plain HTTP is enough.
- Do not hide brittle selectors inside unrelated business logic.
- Do not promise support for site behaviors the docs do not cover.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingpriv/skills/arrowcircle-jido-skills/skills/jido-browser/SKILL.md
Popularity
- Repository stars
- 44
- Repository forks
- 20
- 7-day trend score
- 19
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 17 May 2026, 5 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/agentjido/jido_run/jido-browser)