browser
Skill1 starsChanged 32 days agoMITView on GitHub
Navigate and interact with a website through an owned, bounded ArkSpace browser session. Use when a task requires dynamic page state, clicks, form filling, scrolling, pagination, or an accessibility snapshot rather than ordinary public-web retrieval.
68 other projects use a version of this.
Adopted by
Most recently taken up by
- wubinKKK/private-ai-workbenchtheir own version, first seen Nov 8, 2026
- EthanLLL/loomtheir own version, first seen Nov 8, 2026
- matthewwong525/WongStacktheir own version, first seen Nov 8, 2026
- letsloose501/sqs-agent-memorytheir own version, first seen Nov 3, 2026
- Y91R/chromectltheir own version, first seen Nov 2, 2026
- derwells/learn-skilltheir own version, first seen Nov 1, 2026
Used with
Projects with it also use V3 Core Implementation, V3 DDD Architecture and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
ruvnetSkillV3 Core Implementation
Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing.
Also in 15 projects that use this
ruvnetSkillV3 DDD Architecture
Domain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern.
Also in 15 projects that use this
- +10 more from ruvnet
Other versions68 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 68
- ruvnet/wifi-densepose★ 103ksame name
- ruvnet/RuView★ 103ksame name
- ruvnet/claude-flow★ 80ksame name
- ruvnet/ruflo★ 79ksame name
- ruvnet/ruvector★ 4.7ksame name
- ruvnet/RuVector★ 4.7ksame name
- browserbase/agent-browse★ 3.7ksame name
- VibiumDev/vibium★ 3ksame name
- cexll/myclaude★ 2.8ksame name
- proffesor-for-testing/agentic-qe★ 524same name
58 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 1 is distinctive, and 5 are very specific to this project.
0
Common
Most of the 58 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Use the installed arks CLI or ArkSpace MCP tools.
- Very specific: line 13
Run arks --version. If unavailable, explain that ArkSpace CLI is required and ask before changing the user's environment.
- Very specific: line 14
Run arks doctor --json when Firecrawl readiness is unknown.
- Distinctive: line 15
Ask before changing configuration or the user's environment.
- Very specific: line 34
Keep the returned data.sessionId.
- Very specific: line 36
Use browser.snapshot before acting.
“Common” is measured: kept by at least 6 in 10 of the 58 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Browser
Use the installed arks CLI or ArkSpace MCP tools. Prefer the web Skill when Search or Fetch can produce the evidence without browser state.
Readiness
- Run
arks --version. If unavailable, explain that ArkSpace CLI is required and ask before changing the user's environment. - Run
arks doctor --jsonwhen Firecrawl readiness is unknown. If credentials are missing, direct the human to runarks setupin a trusted local terminal. Never ask for an API key in conversation or place one in a command argument. - Ask before changing configuration or the user's environment. Explain that an open Firecrawl browser session accrues credits until it is closed or expires.
Session lifecycle
Open only the exact initial HTTP(S) URL needed:
{
"protocolVersion": 1,
"capability": "browser.open",
"input": {
"url": "https://example.com",
"ttlSeconds": 600,
"activityTtlSeconds": 300,
"timeoutMs": 30000
}
}Keep the returned data.sessionId. It is an opaque handle bound to the API key that created the session. Never substitute another account or Provider. ArkSpace intentionally does not return CDP or live-view authority URLs.
Use browser.snapshot before acting. Prefer interactiveOnly: true. The snapshot returns bounded @eN references for the current page state.
Actions and confirmation
browser.interact performs exactly one structured action:
navigatewith an exact HTTP(S) URL;clickwith a current@eNreference;fillwith a current@eNreference and text;presswith an allowed key;scrollwith direction and bounded pixels;scrapeto read current page content.
Before each action, state the target and intended effect. Obtain explicit user approval before setting "confirmed": true. A click or key press can submit a form, purchase an item, publish content, change account state, or trigger another irreversible effect. Do not infer approval from an earlier request when the concrete target or effect has changed.
Refresh the snapshot after navigation or any action that materially changes the page. References are not stable across page states. Never send arbitrary JavaScript, Python, or shell code through Protocol v1.
For sensitive form values, disclose that the value will be sent to the remote browser Provider. Use a restrictive temporary request file, do not print its contents, remove it immediately, and proceed only with explicit approval.
Cleanup and failure
Close the session as soon as the task completes:
{
"protocolVersion": 1,
"capability": "browser.close",
"input": { "sessionId": "<session-id>", "timeoutMs": 30000 }
}TTL is a backstop, not normal cleanup. If an action fails with safeToRetry: false, report that its external effect is uncertain and do not repeat it automatically. If open reports failed cleanup, preserve and report the session ID because it may remain active and billable. Treat local timeout or process exit as neither proof of failure nor proof of closure.
Report the actions performed, the verified final page state, the close outcome, and any unresolved or uncertain side effect. Summarize snapshots instead of pasting the complete raw snapshot unless the user requests it.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

