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

Replay Vision Scanner Broken Experiences

ASecurity

The breakage monitor brief for Replay vision

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

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 9/19/2026

$npx -y skills add Aymenjdily/biblion-testing-agentic-ai-skills --skill replay-vision-scanner-broken-experiences --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Replay Vision Scanner Broken Experiences?

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

Security grade badge for Replay Vision Scanner Broken Experiences
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aymenjdily-replay-vision-scanner-broken-experiences/badge)](https://www.skillsdirectory.com/skills/aymenjdily-replay-vision-scanner-broken-experiences)

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: replay-vision-scanner-broken-experiences
description: The breakage monitor brief for Replay vision
metadata:
  author: PostHog
  version: 1.51.0
---

# Breakage scanner (monitor)

The product visibly breaking, on the flow where breaking costs the most —
written for **this** product, not a generic template. Create with
`vision-scanners-create`. You fill four blanks; the scaffold around them is
locked.

```jsonc
{
  // AGENT FILLS `name`, per the core naming rule - "Broken checkout",
  // "Booking failures".
  "name": "<name>",
  "scanner_type": "monitor",
  "scanner_config": {
    "prompt": "Watch this session for moments where the product visibly broke for the user: an error message or toast, a blank/white screen, content that failed to load, obviously broken layout, a spinner that never resolves, or a button/form/action that clearly did nothing or failed. In this product that especially means: {{WATCH_FOR}}. Only flag issues that are unambiguous on screen and would actually matter to the user – ignore cosmetic nits and anything you're unsure about. For each: what the user was trying to do, what broke, and the URL.\n\n{{PRODUCT_CONTEXT}}"
  },
  "query": {
    // AGENT FILLS: this product's key completion flow + its immediate
    // predecessors, read out of the repo.
    "kind": "RecordingsQuery",
    "properties": [
      { "key": "$current_url", "value": "/checkout", "operator": "icontains", "type": "event" }
    ]
  },
  "sampling_rate": 0.5,
  "model": "gemini-3-flash-preview"
}
```

**`{{WATCH_FOR}}`** is what makes this scanner belong to this product: three
to six concrete failure modes read out of the repo, each observable on screen,
in the product's own vocabulary — "the slot picker showing no available
courts", "the payment step rejecting a valid card", "a booking confirmation
that never appears". Facts about what failure looks
like *here*, under the same content rules as `{{PRODUCT_CONTEXT}}`.

This monitor owns the *where* axis of the disjointness rule in
`replay-vision-scanners-core` — a URL-scoped query, never an event gate. In
particular never gate it on `$exception`: that blinds it to silent breakage,
the thing vision is uniquely good at.

Re-run match phrase: `moments where the product visibly broke for the user`.

Attribution

AymenjdilyAymenjdily
View sourceSee grades on GitHubMore from Aymenjdily →
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 →