agent-browser-verify
Interactively verify an approved LuckyStack flow against an authorized running app.
Skill by ItsLucky23
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/itslucky23-agent-browser-verify
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-browser-verify
What's inside
- Skill name
agent-browser-verify- Description
- Interactively verify an approved LuckyStack flow against an authorized running app.
- License
- MIT
- Instructions
- 11 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Interactive browser verification 1. Propose the assertion and smallest adequate browser tool; wait for approval. Escalate only for a missing required capability under `docs/AI_BROWSER_TESTING.md` (consumer copy under `docs/luckystack/`). 2. Reuse/start the runtime under applicable local authority. Report the actual URL and use a dedicated test account; never read `.env.local` for credentials. 3. Inspect current tool configuration/help for domain/action restrictions. Preserve supported `.claude/settings.json` permissions; do not assume changing instructions to `AGENTS.md` changes a settings parser. 4. Verify the requested flow, including console/network evidence and denial/failure cases. For auth, test the actual configured token/cookie mode, CSRF policy, account switching and applicable provider flows; source/types are authoritative for transport details. 5. Report pass/fail/skipped cases separately. Offer a deterministic test after the flow is verified, not as proof that exploration already passed. Do not broaden authority, print token values or create a second copied login-flow specification in this skill.
From ItsLucky23/LuckyStack-v2, MIT.
More from ItsLucky23/LuckyStack-v2
- 0.576score
source-command-log-progress
ItsLucky23
Capture meaningful session work in the current branch log and maintain its index.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
source-command-review-branch
ItsLucky23
Review a branch against Git evidence, captured intent and verification gaps.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
source-command-review-memory
ItsLucky23
Review an explicitly identified private memory store with user-selected changes.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
a11y-audit
ItsLucky23
Review accessibility with authorized browser tooling and source-backed findings.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
ideas
ItsLucky23
Offer evidence-backed improvement options without changing code or inventing a backlog.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
agent-browser
ItsLucky23
Turn approved interactive browser evidence into deterministic end-to-end tests.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
lighthouse
ItsLucky23
Measure approved frontend performance and propose source-backed improvements.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
perf-budget
ItsLucky23
Define and verify a deliberate performance budget without silently accepting regressions.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
security-audit
ItsLucky23
Review dependencies, secret exposure and application trust boundaries with verified findings.
SkillAFreshness: A★ 1Claude Code +9 - 0.315score
audit-api-rate-limits
ItsLucky23
No description from the publisher yet.
SkillAFreshness: A★ 1Claude Code +9 - 0.315score
add-new-api
ItsLucky23
No description from the publisher yet.
SkillAFreshness: A★ 1Claude Code +9 - 0.315score
add-new-component
ItsLucky23
No description from the publisher yet.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 13, 2026 (15 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ItsLucky23/LuckyStack-v2
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ItsLucky23
- 0.576score
source-command-log-progress
ItsLucky23
Capture meaningful session work in the current branch log and maintain its index.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
source-command-review-branch
ItsLucky23
Review a branch against Git evidence, captured intent and verification gaps.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
source-command-review-memory
ItsLucky23
Review an explicitly identified private memory store with user-selected changes.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
a11y-audit
ItsLucky23
Review accessibility with authorized browser tooling and source-backed findings.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
ideas
ItsLucky23
Offer evidence-backed improvement options without changing code or inventing a backlog.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
agent-browser
ItsLucky23
Turn approved interactive browser evidence into deterministic end-to-end tests.
SkillAFreshness: A★ 1Claude Code +9
Cite this page
agent-browser-verify skill. Agent Mart. https://agentmart.dev/skills/itslucky23-agent-browser-verify (last updated 2026-10-24)