explainx.ainewsletter3.4k
Productivity

steel-browser▌

steel-dev/cli · updated Apr 8, 2026

MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.

$npx skills add https://github.com/steel-dev/cli --skill steel-browser
0 commentsdiscussion
summary

Cloud browser automation with fast extraction APIs and explicit session control for web tasks.

  • ›Provides three command families: steel scrape and steel pdf for fast API-based extraction, steel screenshot for page capture, and steel browser for interactive multi-step automation with click, fill, wait, and snapshot operations
  • ›Supports named session management with parallel execution, CAPTCHA/anti-bot handling via stealth mode and proxy configuration, and credential injection through stored
skill.md

Steel

Cloud browser infrastructure for AI agents. Steel gives your agent a real browser that can navigate pages, fill forms, solve CAPTCHAs, and extract content.

If Steel is not installed yet, execute the setup steps below autonomously. Only ask the user to do one thing: click the authentication link.

OBJECTIVE: Install the Steel CLI, authenticate, and verify everything works.

DONE WHEN: steel scrape https://example.com returns page content successfully.

Setup

Step 1: Install Steel CLI

Check if steel is already available:

steel --version

If the command is not found, install it:

curl -sSf https://setup.steel.dev/install.sh | sh
export PATH="$HOME/.steel/bin:$PATH"

Step 2: Authenticate

If STEEL_API_KEY is already set in the environment, skip this step.

Otherwise, run:

steel login

This will print a URL. Ask the user to click the link to complete authentication. Wait for the command to finish — it will print "Authentication successful" when the user has approved.

Step 3: Verify

steel scrape https://example.com

This should return Markdown content. If it does, setup is complete.

Choose the right tool

Task Tool
Extract text/HTML from a page steel scrape <url>
Take a screenshot steel screenshot <url>
Generate a PDF steel pdf <url>
Multi-step interaction, login, forms, JS-heavy pages steel browser session
Anti-bot / CAPTCHA sites steel browser --stealth session

Start with steel scrape when you only need page content. Escalate to steel browser when the page requires interaction or JavaScript rendering.

API tools (one-shot, no session needed)

# Scrape — returns Markdown by default (use --json flag for structured output)
steel scrape https://example.com
steel scrape https://example.com --format html
steel scrape https://example.com --use-proxy

# Screenshot
steel screenshot https://example.com
steel screenshot https://example.com --full-page

# PDF
steel pdf https://example.com

Interactive browser session

Core workflow

  1. Start a named session
  2. Navigate to the target URL
  3. Snapshot to get page state and element refs
  4. Interact using @eN refs from the snapshot
  5. Re-snapshot after every navigation or DOM change (refs expire)
  6. Stop the session when done
steel browser start --session my-task --session-timeout 3600000
steel browser navigate https://example.com --session my-task
steel browser snapshot -i --session my-task
steel browser fill @e3 "search term" --session my-task
steel browser click @e7 --session my-task
steel browser wait --load networkidle --session my-task
steel browser snapshot -i --session my-task
steel browser stop --session my-task

Rules:

  • Always use the same --session <name> on every command.
  • Never use an @eN ref without a fresh snapshot — refs expire after navigation or DOM changes.
  • Prefer element refs from snapshot -i over CSS selectors. Use -c for large DOMs, -d 3 to limit depth.
  • Use batch to combine multiple commands into a single invocation for efficiency.

Batch execution

Run multiple commands in one CLI call. Each quoted string is one command.

# Navigate and snapshot in one call
steel browser batch "navigate https://example.com" "snapshot -i" --session my-task

# Action + re-snapshot (no separate snapshot call needed)
steel browser batch "click @e3" "snapshot -i" --session my-task

# Multiple actions without intermediate snapshots
steel browser batch "fill @e1 Seoul" "fill @e2 Tokyo" "click @e5" --session my-task

# Stop on first error with --bail
steel browser batch "click @e3" "snapshot -i" --session my-task --bail

Use batch when:

  • You need to snapshot after an action (most common case)
  • You are filling multiple form fields in sequence
  • You want to reduce the number of CLI invocations

Use separate commands when you need to read the output of one command before deciding the next.

Session lifecycle

steel browser start --session <name> --session-timeout 3600000
steel browser start --session <name> --stealth
steel browser start --session <name> --proxy <url>
steel browser sessions
steel browser live --session <name>
steel browser stop --session <name>
steel browser stop --all

Navigation and inspection

steel browser navigate <url> --session <name>
steel browser snapshot                         # full accessibility tree
steel browser snapshot -i                      # interactive elements + refs
steel browser snapshot -c                      # compact output
steel browser snapshot -i -c -d 3             # combine flags
steel browser get url --session <name>
steel browser get title --session <name>
steel browser get text @e1 --session <name>
steel browser back --session <name>
steel browser forward --session <name>
steel browser reload --session <name>

Interaction

steel browser click @e1 --session <name>
steel browser dblclick @e1 --session <name>
steel browser fill @e2 "value" --session <name>
steel browser type @e2 "value" --delay 50 --session <name>
steel browser press Enter --session <name>
steel browser press Control+a --session <name>
steel browser hover @e1 --session <name>
steel browser select @e1 "option" --session <name>
steel browser scroll down 500 --session <name>
steel browser scrollintoview @e1 --session <name>
steel browser drag @e1 @e2 --session <name>
steel browser tab new --session <name>
steel browser tab switch 2 --session <name>
steel browser tab list --session <name>
steel browser tab close --session <name>

Synchronization

steel browser wait --load networkidle --session <name>
steel browser wait --selector ".loaded" --state visible --session <name>
steel browser wait -t "Success" --session <name>
steel browser wait -u "/dashboard" --session <name>

Extraction

steel browser get text @e1 --session <name>
steel browser get html @e1 --session <name>
steel browser get value @e1 --session <name>
steel browser get attr @e1 href --session <name>
steel browser get count ".item" --session <name>
steel browser content --session <name>
steel browser eval "document.querySelectorAll('a').length" --session <name>
steel browser find ".item" --session <name>

Screenshots (in-session)

steel browser screenshot -o ./page.png --session <name>
steel browser screenshot --full --session <name>
steel browser screenshot --selector "#chart" --session <name>

Top-level steel screenshot <url> and steel pdf <url> are stateless one-shot API calls — they do not take --session or -o flags. Use steel browser screenshot for in-session captures.

Cookies and storage

steel browser cookies --session <name>
steel browser cookies set <name> <value> --session <name>
steel browser cookies set <name> <value> --domain .example.com
steel browser cookies clear --session <name>
steel browser storage session --session <name>
steel browser storage session set authToken "abc123" --session <name>

Browser settings

steel browser set viewport 1920 1080 --session <name>
steel browser set geo 37.7749 -122.4194 --session <name>
steel browser set offline on --session <name>
steel browser set useragent "Custom UA" --session <name>

CAPTCHA

steel browser start --session <name> --stealth
steel browser captcha status --wait --session <name>
steel browser captcha solve --session <name
how to use steel-browser

How to use steel-browser on Cursor

AI-first code editor with Composer

1

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

  • ›Cursor installed and configured on your development machine
  • ›Node.js version 16.0+ with npm package manager (verify with node --version)
  • ›Active project directory or workspace where you want to add steel-browser
2

Execute installation command

Execute the skills CLI command in your project's root directory to begin installation:

$npx skills add https://github.com/steel-dev/cli --skill steel-browser

The skills CLI fetches steel-browser from GitHub repository steel-dev/cli and configures it for Cursor.

3

Select Cursor when prompted

The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:

◆ Which agents do you want to install to?
│
│ ── Universal (.agents/skills) ── always included ────
│ • Amp
│ • Antigravity
│ • Cline
│ • Codex
│ ●Cursor(selected)
│ • Cursor
│ • Windsurf
4

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/steel-browser

Reload or restart Cursor to activate steel-browser. Access the skill through slash commands (e.g., /steel-browser) or your agent's skill management interface.

⚠

Security & Verification Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.

Additional Resources

›View source code on GitHub›Skills CLI documentation›Learn more about Cursor›What are agent skills?

List & Monetize Your Skill

Submit your Claude Code skill and start earning

GET_STARTED →

Use Cases▌

User Story & Requirements Generation

Create detailed user stories, acceptance criteria, and feature specs

Example

Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios

✓

Reduce spec writing time by 50%, ensure comprehensive coverage

Competitive Analysis

Research competitors, compare features, identify gaps

Example

Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities

✓

Complete competitive research in 2 hours instead of 2 days

Roadmap Prioritization

Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs

Example

Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale

✓

Make data-driven prioritization decisions faster

Stakeholder Communication

Draft PRDs, status updates, and stakeholder presentations

Example

Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement

✓

Save 3-5 hours/week on communication overhead

Implementation Guide▌

Prerequisites

  • ›Claude Desktop or compatible AI client
  • ›Access to product documentation and roadmap tools (Jira, Notion, etc.)
  • ›Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
  • ›Stakeholder contact information and communication channels

Time Estimate

30-60 minutes to see productivity improvements

Installation Steps

  1. 1.Install product management skill
  2. 2.Start with user story generation for known feature
  3. 3.Progress to competitive analysis: research 2-3 competitors
  4. 4.Use for roadmap prioritization: apply RICE/ICE scoring
  5. 5.Draft stakeholder communications and refine based on feedback
  6. 6.Build template library for recurring PM tasks
  7. 7.Share effective prompts with product team

Common Pitfalls

  • ⚠Not validating competitive research—verify facts before sharing
  • ⚠Accepting user stories without involving engineering team
  • ⚠Over-relying on frameworks without qualitative judgment
  • ⚠Not customizing outputs to company culture and communication style
  • ⚠Skipping stakeholder validation of generated requirements

Best Practices▌

✓ Do

  • +Validate research and competitive analysis with real data
  • +Collaborate with engineering when generating technical requirements
  • +Customize frameworks and templates to your company context
  • +Use skill for first drafts, refine with stakeholder input
  • +Document successful prompt patterns for PM tasks
  • +Combine AI efficiency with human judgment and intuition

✗ Don't

  • −Don't publish competitive analysis without fact-checking
  • −Don't finalize user stories without engineering review
  • −Don't make prioritization decisions solely on AI scoring
  • −Don't skip customer validation of generated requirements
  • −Don't ignore company-specific context and culture

💡 Pro Tips

  • ★Provide context: company goals, constraints, customer feedback
  • ★Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
  • ★Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
  • ★Use skill for 70% generation + 30% customization to company needs

When to Use This▌

✓ Use When

Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.

✗ Avoid When

Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.

Learning Path▌

  1. 1Basic: user stories, feature specs, status updates
  2. 2Intermediate: competitive analysis, prioritization frameworks, PRDs
  3. 3Advanced: product strategy, go-to-market planning, OKR setting
  4. 4Expert: product vision, market positioning, business model innovation

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.6★★★★★70 reviews
  • ★★★★★Yuki Shah· Dec 24, 2024

    I recommend steel-browser for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • ★★★★★Dhruvi Jain· Dec 20, 2024

    We added steel-browser from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.

  • ★★★★★Chinedu Iyer· Dec 12, 2024

    steel-browser is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

  • ★★★★★Zara Sanchez· Dec 8, 2024

    Solid pick for teams standardizing on skills: steel-browser is focused, and the summary matches what you get after install.

  • ★★★★★Kabir Tandon· Dec 8, 2024

    Registry listing for steel-browser matched our evaluation — installs cleanly and behaves as described in the markdown.

  • ★★★★★Ishan Gupta· Dec 8, 2024

    Useful defaults in steel-browser — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • ★★★★★Ava Chawla· Dec 4, 2024

    steel-browser has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • ★★★★★Olivia Patel· Nov 27, 2024

    I recommend steel-browser for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • ★★★★★Ava Malhotra· Nov 27, 2024

    steel-browser reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • ★★★★★Noah Bansal· Nov 27, 2024

    We added steel-browser from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.

showing 1-10 of 70

1 / 7