Agent skill

Claw Browser Anchor

by breakstageaxe61 in breakstageaxe61/genspark-claw

Make browser automation reliable — anchor every click, type, and scroll to stable DOM selectors and semantic roles instead of screen coordinates, so actions survive layout shifts, A/B tests, and…

MITAuto-check passedProductivity & Automation

Install Claw Browser Anchor

skills CLI
$ npx skills add breakstageaxe61/genspark-claw --skill claw-browser-anchor -a claude-code

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

GitHub CLI
$ gh skill install breakstageaxe61/genspark-claw claw-browser-anchor --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/breakstageaxe61/genspark-claw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/claw-browser-anchor .claude/skills/claw-browser-anchor && 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
claw-browser-anchor
GitHub stars
169
Token cost
~1k tokens
SKILL.md length
479 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Make browser automation reliable — anchor every click, type, and scroll to stable DOM selectors and semantic roles instead of screen coordinates, so actions survive layout shifts, A/B tests, and…

  • Works in 7 steps: Snapshot before acting. Capture the DOM… → Choose anchors in priority order → Score every anchor. Before using a… → …
  • Tasks that involve Browser automation
  • SKILL.md covers Context, Instructions, Error Handling and Rules, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Claw Browser Anchor is an agent skill from breakstageaxe61/genspark-claw. Make browser automation reliable — anchor every click, type, and scroll to stable DOM selectors and semantic roles instead of screen coordinates, so actions survive layout shifts, A/B tests, and viewport changes.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: ["genspark-claw","openclaw","hermes","claude-code","cursor"]

It sits in Productivity & Automation, covering Browser automation and A/B testing. It works with Model Context Protocol. The repository describes itself as: 🦀⚡ Community skill pack & CLI for Genspark Claw, OpenClaw & Hermes agents — 5 production-ready SKILL.md skills (deep research, reports, slides, browser automation, AI call…. The licence is MIT.

When your agent uses it

  • Tasks that involve Browser automation
  • Tasks that involve A/B testing

Example prompts

  • “/claw-browser-anchor”

Requirements

  • Compatibility (from SKILL.md): ["genspark-claw","openclaw","hermes","claude-code","cursor"]

Workflow steps

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

  1. Snapshot before acting. Capture the DOM or accessibility tree of the
  2. Choose anchors in priority order
  3. Score every anchor. Before using a selector, verify it matches exactly
  4. Act, then verify. After each click/type/navigation, assert the expected
  5. Handle drift. If an anchor that worked before now fails, re-snapshot
  6. Wait on state, not time. Poll for the element or network idle with a
  7. Log the trace. Keep a step list: action, anchor used, verification

What it can do on your machine

Read from SKILL.md and the folder at commit 2ef198c. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

  • Compatibility

    ["genspark-claw","openclaw","hermes","claude-code","cursor"]

    From compatibility in the SKILL.md frontmatter.

Context cost

Claw Browser Anchor loads about 1k tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 479 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~58
When it runs · the whole SKILL.md, loaded when a task matches
~1k

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 passed

The automated check found no risky patterns in SKILL.md.

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 breakstageaxe61/genspark-claw at commit 2ef198c, republished under its MIT licence (© breakstageaxe61). 479 words, ~1,024 tokens.

Download SKILL.mdSave it as .claude/skills/claw-browser-anchor/SKILL.md (or your agent's skills folder).
name
claw-browser-anchor
description
Make browser automation reliable — anchor every click, type, and scroll to stable DOM selectors and semantic roles instead of screen coordinates, so actions survive layout shifts, A/B tests, and viewport changes.
compatibility
["genspark-claw","openclaw","hermes","claude-code","cursor"]
version
1.0.0
license
MIT
triggers
browse, click, fill out the form, automate the website, log in and, scrape this page
metadata.category
browser-automation
metadata.author
breakstageaxe61

Claw Browser Anchor

You are a browser-automation engineer. Coordinate-based clicking ("click at x=412, y=305") is fragile: it breaks on scroll, reflow, responsive layouts, A/B tests, and font changes. Your job is to anchor every action to the page's structure so the workflow still works tomorrow.

Context

You control a browser through an automation tool (Playwright-style selectors, a computer-use driver, or the agent's built-in browser). Before acting, you can inspect the DOM or accessibility tree. Reliability matters more than elegance: a boring selector that survives a redesign beats a clever one that does not.

Instructions

  1. Snapshot before acting. Capture the DOM or accessibility tree of the current page. Never act from a screenshot alone when structure is available.
  2. Choose anchors in priority order:
    1. data-testid / data-test / data-cy attributes (built for automation)
    2. ARIA role + accessible name (role=button[name="Sign in"])
    3. Stable IDs that are not auto-generated (reject IDs with long random suffixes like ember4271 or :r3k:)
    4. Semantic structure (form[name="login"] input[type="password"])
    5. Text content, only for short unique strings, scoped to a container
    6. XPath/CSS positional chains — last resort; add a comment flagging them
  3. Score every anchor. Before using a selector, verify it matches exactly one element. If it matches zero, re-snapshot; if it matches many, add scope (nearest stable ancestor) until it is unique.
  4. Act, then verify. After each click/type/navigation, assert the expected effect (URL change, element appears, value present) before continuing. Treat "no error" as different from "worked".
  5. Handle drift. If an anchor that worked before now fails, re-snapshot and re-derive the anchor using the same priority order. Record the old and new anchor in your notes so the workflow can be updated.
  6. Wait on state, not time. Poll for the element or network idle with a timeout. Fixed sleep(3) calls are a bug.
  7. Log the trace. Keep a step list: action, anchor used, verification result. When a run fails, the trace is the bug report.
Show full SKILL.md (156 more words)Show less

Error Handling

  • Element not found after re-snapshot: scroll it into view, check iframes and shadow DOM roots, then check for a login wall or consent modal blocking it.
  • Consent/cookie modal: dismiss it once via its own stable anchor, then retry the original action.
  • Navigation race: after any submit/click that navigates, wait for the new page's ready state before snapshotting.
  • Three failed attempts on the same step: stop, report the trace, and ask the user — do not keep clicking blindly.

Rules

  • Never use raw screen coordinates when a structural anchor exists.
  • Never submit credentials, payments, or irreversible actions without explicit user confirmation in the current session.
  • Respect robots.txt, site terms, and rate limits; identify automation honestly when a site asks.
  • Do not bypass CAPTCHAs or access controls — hand off to the user instead.
  • Keep each workflow resumable: store progress so a crashed run can restart from the last verified step.

Output Format

For each automation run, report:

## Run: <goal>
1. <action> — anchor: <selector strategy used> — ✔ verified / ✖ failed
2. …

### Result
<what was accomplished / where it stopped and why>

### Fragile anchors to watch
<selectors that needed positional fallbacks>

© breakstageaxe61, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/claw-browser-anchor of breakstageaxe61/genspark-claw.

Open the folder on GitHubat commit 2ef198c

Compare with similar skills

Claw Browser Anchor 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.

Claw Browser Anchor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Claw Browser Anchor this skillbreakstageaxe61/genspark-claw169—~1kAutomated safety check: PassMIT
Webctlcosinusalpha/webctl419—~1.7kAutomated safety check: PassNone
Browser Automationmozilla/firefox-devtools-mcp478—~807Automated safety check: PassCustom licence
Claude Bowserdisler/bowser265—~327Automated safety check: WarnNone
BrowserUndertone0809/rudder292—~2.6kAutomated safety check: PassApache-2.0
Next Dev Loopvercel/next.js143k9 repos~2.3kAutomated safety check: PassMIT

Similar skills

  • Webctl

    cosinusalpha/webctl

    Browser automation via CLI. An agent skill from cosinusalpha/webctl.

    419 GitHub stars~1.7k tokensUpdated 4 mo ago
    Productivity & AutomationAuto-check passed
  • Browser Automation

    mozilla/firefox-devtools-mcp

    This skill should be used when the user asks about browser automation, testing web pages, extracting content, filling forms, taking screenshots, or monitoring console/network activity.

    478 GitHub stars~807 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Claude Bowser

    disler/bowser

    Observable browser automation using Chrome MCP tools. An agent skill from disler/bowser.

    265 GitHub stars~327 tokensUpdated 7 mo ago
    Productivity & AutomationAuto-check: warnings
  • Browser

    Undertone0809/rudder

    Control Rudder's built-in Browser through the separate run-scoped rudder-browser MCP, but invoke this skill only when the user explicitly mentions or selects Rudder's built-in Browser, Rudder…

    292 GitHub stars~2.6k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Next Dev Loop

    vercel/next.js

    Official

    Verify Next.js runtime behavior after editing app code. An agent skill from vercel/next.js.

    143k GitHub starsUsed in 9 repos~2.3k tokens
    Productivity & AutomationAuto-check passed
  • Skyvern Browser Automation

    Skyvern-AI/skyvern

    Automates websites with Skyvern's AI browser agent to fill forms, extract data, download files, log in and run multi-step workflows through SDKs, REST, MCP or a CLI.

    23k GitHub stars~1.9k tokensUpdated today
    Productivity & AutomationAuto-check passed

More from breakstageaxe61/genspark-claw

  • Call Prep

    breakstageaxe61/genspark-claw

    Prepare an AI phone call end-to-end — research the callee, set a concrete objective and fallback, draft a natural call script with branching, and produce a post-call summary template.

    169 GitHub stars~986 tokensUpdated 13 days ago
    Auto-check passed
  • Spark Report

    breakstageaxe61/genspark-claw

    Turn raw research, notes, links, or a conversation into a polished, shareable Sparkpage-style report page with an executive summary, structured sections, tables, and citations.

    169 GitHub stars~738 tokensUpdated 13 days ago
    Auto-check passed
  • Spark Slides

    breakstageaxe61/genspark-claw

    Turn research, a document, or a rough idea into a presentation-ready slide deck outline — narrative arc, slide-by-slide content, speaker notes, and visual direction — ready for AI Slides or manual…

    169 GitHub stars~813 tokensUpdated 13 days ago
    Auto-check passed
  • Super Research

    breakstageaxe61/genspark-claw

    Run a mixture-of-agents style deep research workflow — decompose a question, fan out parallel searches, cross-verify claims across independent sources, and deliver a fully cited report.

    169 GitHub stars~892 tokensUpdated 13 days ago
    Auto-check passed

Questions about Claw Browser Anchor

What does Claw Browser Anchor do?

Make browser automation reliable — anchor every click, type, and scroll to stable DOM selectors and semantic roles instead of screen coordinates, so actions survive layout shifts, A/B tests, and…. Claw Browser Anchor is an agent skill from breakstageaxe61/genspark-claw. Make browser automation reliable — anchor every click, type, and scroll to stable DOM selectors and semantic roles instead of screen coordinates, so actions survive layout shifts, A/B tests, and viewport changes.

When should I use Claw Browser Anchor?

Claw Browser Anchor fits situations like: tasks that involve Browser automation; tasks that involve A/B testing.

How do I install Claw Browser Anchor in Claude Code?

Run `npx skills add breakstageaxe61/genspark-claw --skill claw-browser-anchor -a claude-code`. Or copy the skill folder (skills/claw-browser-anchor in breakstageaxe61/genspark-claw) into .claude/skills/claw-browser-anchor in your project. Claude Code loads it when a task matches its description.

How do I install Claw Browser Anchor in Codex?

Run `npx skills add breakstageaxe61/genspark-claw --skill claw-browser-anchor -a codex`. Or copy the skill folder (skills/claw-browser-anchor in breakstageaxe61/genspark-claw) into .agents/skills/claw-browser-anchor in your project. Codex loads it when a task matches its description.

Can I use Claw Browser Anchor 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 breakstageaxe61/genspark-claw --skill claw-browser-anchor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/claw-browser-anchor, .gemini/skills/claw-browser-anchor, .github/skills/claw-browser-anchor and .opencode/skills/claw-browser-anchor in your project.

What does Claw Browser Anchor need to run?

SKILL.md names no scripts, command-line tools or credentials: Claw Browser Anchor is instructions for the agent only. Compatibility (from SKILL.md): ["genspark-claw","openclaw","hermes","claude-code","cursor"].

Does Claw Browser Anchor access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Claw Browser Anchor safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Claw Browser Anchor use?

Claw Browser Anchor is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Claw Browser Anchor use?

About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Claw Browser Anchor?

Skills that share tags, products or a category with Claw Browser Anchor: Webctl (cosinusalpha/webctl, 419 stars), Browser Automation (mozilla/firefox-devtools-mcp, 478 stars), Claude Bowser (disler/bowser, 265 stars) and Browser (Undertone0809/rudder, 292 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Claw Browser Anchor?

breakstageaxe61 (a GitHub user) maintains it in breakstageaxe61/genspark-claw, which has 169 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 26, 2026.

Source: breakstageaxe61/genspark-claw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.