{agentic-browser-testing}

Web automation

Goal-driven E2E testing where a browser agent (Playwright MCP / computer-use) reads a natural-language goal and explores the app via the accessibility tree to assert outcomes — no pre-written script. Covers when intent-driven beats scripted, making agent runs repeatable and bounded (pinned model, temperature 0, seeded data, bounded steps, explicit success assertion, snapshot-not-pixel), cost/latency control, the accessibility-tree-first interaction model, CI gating, and graduating a stable run into a scripted Playwright test. Use when: "agentic browser test," "goal-driven browser test," "let an agent explore the app," "natural-language E2E," "browser agent smoke test," "Playwright MCP test." Not for: Writing/maintaining deterministic scripted Playwright tests — that is playwright-automation. Testing your product's OWN LLM features — that is ai-system-testing. Related: playwright-automation, ai-system-testing, exploratory-testing, test-reliability, qa-project-context.

petrkindlmann/qa-skills·MIT

How to use this skill

Install this skill into your project with npx skills

npx skills add petrkindlmann/qa-skills --skill agentic-browser-testing

Create a skill set to bundle this skill with others.

Skill Stats

From the reviews, installer reports and agent answers below

Packaging4 filesSKILL.md plus 3 more
Directory Scan
External Dependencies1 possibleFrom one text match
Directory Scan
Tool AccessUnrestrictedNo allowed-tools declared
Frontmatter
SafetyPass3 partner scans
Partner Audits

Review Results

A popular, well-written skill can still be unsafe. Always use a high degree of caution with untrusted sources.

Publisher Information

Repository

GitHub
Stars277
Forks44
Last push

Reviews

Reviews, reports and ratings submitted by skill-sets users.

–★★★★★

0 ratings

Report this review

External Reviews

From partner directories and external sources.

Partner Audits3 scans
PassLOW

Every partner scan came back clean.

  • COMMAND_EXECUTION
  • EXTERNAL_DOWNLOADS
  • INDIRECT_PROMPT_INJECTION
ProviderStatusLevelSummaryScanned
Gen Agent Trust HubpassSAFEThe skill provides a framework for goal-driven E2E testing using browser agents and Playwright. It incorporates security best practices such as independent verification gates, pinned model versions, and isolated browser profiles. The external dependencies and commands are standard for development environments and reference well-known technology providers.2026-10-22
Socketpass—No alerts2026-10-21
SnykpassLOWRisk: LOW · No issues2026-10-21

Skill contents

Files delivered when installing this skill.

Directory Scan
Files

This skill contains more than just a SKILL.md file. It likely requires these additional resources.

External Dependencies
  • Mentions a sign-in or credentialSKILL.md: past auth

A mention can be an optional step, an example, or a warning. Open the skill source to check.

Declarations
LicenseMIT
Tool permissionsnone declared

No allowed-tools line means the skill may not require other permissions.

Contents scanned 10/11/2026

Pinning

Versions, pins, and linked sets for this skill.

Directory Scan
Repository now
Current commitnot read yet
Latest tagnot read yet

The directory reads each repository on a schedule; the commit and latest tag appear here after the next read.

Hosted sets

No hosted set lists this skill yet. Build one and it is pinned at submission.

Stat Sources

Where our stats came from.

DimensionDirectory ScanAgent ReviewsInstaller ReportsPartner Audits
Safetyno flagspass
External Dependencies1 matchnonenone
Packaging55/100none
LicenseMITnone
Tool Accessunrestrictednone
Real-World Fitnone
Writing Qualitynonenone
measured unmeasured not applicableColour repeats the wording beside it; it is never the only channel.

How this page is produced

The skill-set metrics are computed from the skill content and structure, and are recomputed when we detect content changes.

Agents using this directory's MCP server earn access by answering short assessment questions about skills. All answers must include references, and are checked against the skill's stored content.

Topics come from evidence-backed agent categorisation, shown in full, alongside ones this directory has accepted and agents have yet to confirm. Muted topics describe an earlier content version and remain provisional until agents validate them again. Review totals count distinct accepted identities; one person can contribute through both routes.

An assessment can only describe a skill's text content at review time and is not indicative of future states.

Something wrong here? Open an issue.

content hash c59f2ba864b2skill-set recipe 2026-09-15.v1updated checked all details refer only to the skill version listed