skills.rest
jeremybrasher
jeremybrasherCOMMUNITY
Explore all skills by this author →
GitHub

create-verification-skill

Generates a project-local verification skill that drives an app like a user and captures behavioral evidence.

Updated Aug 28, 2026
Search Tags:#automation#verification#playwright#end-to-end testing#feature map#evidence capture#skill generator
One-click install
npx skills add https://github.com/jeremybrasher/grokbot-skills --skill create-verification-skill-jeremybrasher
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: create-verification-skill
Source: https://github.com/jeremybrasher/grokbot-skills/tree/main/collections/pstack/skills/create-verification-skill
Command: npx skills add https://github.com/jeremybrasher/grokbot-skills --skill create-verification-skill-jeremybrasher

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Projects often lack a scripted way to prove that the real app behaves correctly, leaving agents and developers to rely on manual clicking or unverified assumptions. This Skill interviews the repository and generates a tailored verification skill that launches the app, drives it the way a user would, and captures evidence. ## Core Features & Use Cases - Repo Interview: Detects the app's surface (web UI, CLI/TUI, API, desktop), run commands, drive harnesses (Playwright, CDP, tmux/PTY, HTTP), and observable evidence sources directly from the codebase. - Skill Generation: Writes .cursor/skills/verify-<app>/SKILL.md with launch, doctor, drive, evidence, cleanup, and helper sections grounded in real selectors and commands from the repo. - Feature Map Seeding: Creates a features directory with one file per user-facing feature describing how to reach it, drive it, and prove it works. - Self-Proof: Runs the generated skill end to end once before handover, confirming evidence survives cleanup. - Use Case: An agent working in a repo with no test harness invokes this Skill to produce a reusable verification skill that launches the dev server, drives a feature via Playwright, and saves screenshots as proof. ## Quick Start Ask the agent to create a verification skill for this repository so the app can be launched, driven like a user, and proven with captured evidence.

Frequently Asked Questions about create-verification-skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a verification skill for my repository?▼

Invoke the skill with a request like "make a control skill for this repo". It interviews the codebase for surfaces, run commands, and drive harnesses, then writes `.cursor/skills/verify-<app>/SKILL.md` plus a feature map, and proves it by running the generated instructions once.

What tools can drive an app for automated verification?▼

The skill prefers existing harnesses first, such as Playwright or Cypress specs, expect scripts, PTY helpers, and curl-able endpoints. Otherwise it picks a generic recipe: browser/CDP for web and Electron, tmux or PTY for CLI/TUI, and plain HTTP for services.

Does this work for CLI and TUI applications, not just web apps?▼

Yes, it supports any surface including CLI, TUI, desktop, API, mobile, and libraries. For short-lived CLI or TUI apps, launch means building the binary once and starting each drive in its own isolated PTY or tmux session.

What evidence should a verification run capture?▼

Capture the action and the resulting state, not just the final screen: screenshots, terminal transcripts, response bodies, logs, exit codes, and side effects like files written or rows inserted. Evidence must survive cleanup at a location the generated skill names.

When should I not use this skill?▼

Do not use it when required inputs are unavailable and cannot be obtained, when the trigger description is not met, or when a narrower existing skill fits better. In those cases it returns a HOLD naming the gap instead of guessing.

Related Skills

Explore More Software Engineering Skills→
daithang59daithang59
1

Development Setup

Sets up the To-Do List WebApp development environment with Docker Compose and dependency installation.

Community
Intermediate
cursorcursor
6.6k

create-verification-skill

Generates a project-local verification skill that drives an app like a user and captures evidence.

Official
Advanced
mckissingermckissinger
1

debug

Reproduce failures, isolate root causes, and create verified regression fixes.

Community
Advanced
MazenMradMazenMrad
1

bmad-qa-generate-e2e-tests

Generate end-to-end API and UI tests for implemented features.

Community
Advanced