Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Thalarch Browser Qa

ASecurity

Verifies web UI behavior in a real browser using the strongest browser/DevTools/Playwright capability actually available on the current host. Use after frontend changes or for browser-only bugs. Checks interaction, console, network, responsive behavior, screenshots, recordings, accessibility signals, and performance evidence rather than treating a successful build as proof.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsrustfrontendperformance

Works with

claude codemcp

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add LUC4N3X/antigravity-thalarch --skill thalarch-browser-qa --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Thalarch Browser Qa?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Thalarch Browser Qa
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/luc4n3x-thalarch-browser-qa/badge)](https://www.skillsdirectory.com/skills/luc4n3x-thalarch-browser-qa)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: thalarch-browser-qa
description: >
  Verifies web UI behavior in a real browser using the strongest browser/DevTools/Playwright
  capability actually available on the current host. Use after frontend changes or for
  browser-only bugs. Checks interaction, console, network, responsive behavior, screenshots,
  recordings, accessibility signals, and performance evidence rather than treating a successful
  build as proof.
---

# Thalarch Browser QA

Use a **real browser/runtime capability that actually exists in the current host/session**.
Antigravity may expose a Browser Subagent/Chrome integration; Codex or Claude Code may expose
browser/MCP/Playwright/Chrome tooling differently; some environments may expose none.

Never invent browser evidence, screenshots, console state, network traces, or a browser agent/tool
name because another host supports it.

Do not install a competing automation stack merely for ritual QA when an existing trusted browser
path can prove the requirement. Do not silently install browser dependencies without authorization.

If no usable browser capability is available, perform source/build checks that are still meaningful
and keep browser/visual/interaction claims `UNVERIFIED`.

## QA path

When browser tooling is available:

1. Start or locate the application using repository-native instructions.
2. Use the browser on the real running page, not a generated mockup.
3. Navigate the primary user flow.
4. Verify visible acceptance criteria.
5. Inspect console errors/warnings relevant to the change.
6. Inspect relevant network requests and failures.
7. Capture at least:
   - a compact/mobile viewport;
   - a normal desktop viewport;
   - any specific breakpoint named by the requirement.
8. Capture screenshots for load-bearing visual claims.
9. Exercise changed interactions, not only the initial screen.
10. When useful and supported, preserve a recording/trace artifact showing the flow.
11. For performance work, collect concrete metrics/traces rather than subjective speed.

Use the host tool's actual current schema/capabilities. Do not assume Chrome DevTools, Playwright,
screenshot, recording, network inspection, or device emulation features exist until confirmed.

## Visual stress cases

Select only relevant stress cases:

- long text;
- narrow viewport;
- wide viewport;
- empty/loading/error state;
- open menu/dialog/sheet;
- keyboard focus;
- reduced motion;
- slow image/network load;
- zoom/high text scale where practical.

## Image integration checks

For generated or edited imagery used by a site, inspect the real integration when possible:

- crop and focal point at responsive widths;
- loading behavior;
- contrast behind text;
- resolution/sharpness;
- aspect-ratio stability;
- layout shift;
- fallback/alt behavior;
- asset weight where relevant.

An image can pass standalone QA and still fail inside the page.

## Evidence handoff

Use `thalarch-visual-qa` and an independent design/visual review role when such review capability
exists. Otherwise perform a staged cold visual check in the strongest available context.

A successful frontend build is not equivalent to the user flow passing.
A generated mockup is not equivalent to the implemented page passing.
A browser capability that was not actually invoked is not evidence.

Attribution

LUC4N3XLUC4N3X
View sourceSee grades on GitHubMore from LUC4N3X →
SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1087401 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

697551 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →