Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Browser Verify

ASecurity

Use when handed a runtime or browser verification task: prove a change actually works end-to-end in a running app, adversarially. Requires the Playwright MCP server (global mcp_config). Produces a verdict plus evidence other agents can audit.

2 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgoapi

Works with

cliapimcp

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add jckeen/dotfiles --skill browser-verify --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Browser Verify?

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

Security grade badge for Browser Verify
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jckeen-browser-verify/badge)](https://www.skillsdirectory.com/skills/jckeen-browser-verify)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: browser-verify
description: "Use when handed a runtime or browser verification task: prove a change actually works end-to-end in a running app, adversarially. Requires the Playwright MCP server (global mcp_config). Produces a verdict plus evidence other agents can audit."
---

# Browser Verify

This is the runtime/browser verification lane from the multi-agent contract:
the conductor hands over a claim, this skill tries to BREAK it in a real
browser, and the verdict — with evidence — becomes an artifact the whole team
can audit.

## Required payload

A verification handoff must carry (ask for anything missing before starting):

1. **Target** — URL or route, and how to start the app if not running.
2. **Flow** — the exact steps to drive (click X, submit Y, expect Z).
3. **Expected observable** — what SHOULD happen, stated concretely.
4. **Claim to disprove** — the falsifiable statement under test.

## Workflow

1. Confirm the Playwright MCP tools are available (`/mcp` lists servers). If
   absent, stop and report — do not fake a verification with static reading.
2. Start or reach the app; navigate the flow EXACTLY as specified first.
3. Then get adversarial: bad input, rapid repeats, back/forward, refresh
   mid-flow, empty states, small viewport. You are here to refute the claim,
   not confirm it.
4. Capture evidence as you go: screenshots at each decisive step, console
   errors, failed network requests.
5. Copy evidence to the shared path other agents read:
   `~/.claude/handoffs/evidence/YYYY-MM-DD-<short-slug>/`
   (create it; screenshots, console log excerpts, a one-line INDEX.md naming
   each file's moment).
6. Report the verdict:
   - **REFUTED** — the claim broke: exact step, observed vs expected, evidence file.
   - **HELD** — survived the specified flow AND the adversarial pass (list what was tried).
   - **BLOCKED** — could not complete verification: what stopped it.
7. Write or append a handoff note (`~/.claude/handoffs/YYYY-MM-DD-<project>-handoff.md`)
   with the verdict and the evidence path, so the verdict outlives this session.

## Rules

- A verdict without evidence files is not a verdict — capture before reporting.
- Disagreement with the conductor's claim is the valuable outcome; report it
  plainly with the repro, never soften it to "mostly works".
- Never test against production with destructive inputs; use local/dev targets
  unless the handoff explicitly says otherwise.

Attribution

jckeenjckeen
View sourceMore from jckeen →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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 DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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".

1066601 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', ...

686011 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →