Skip to content

lootlog/monorepo / .agents/skills/create-verification-skill

create-verification-skill

Verified

Create a project-local verification skill for one app that drives an existing running application or service through real user paths and captures durable evidence. Use when an app lacks a repeatable browser, HTTP, CLI, or integration verification workflow.

FileKindSize
SKILL.mdskill md1.9 KB
agents/openai.yamlconfig222 B
---
name: create-verification-skill
description: Create a project-local verification skill for one app that drives an existing running application or service through real user paths and captures durable evidence. Use when an app lacks a repeatable browser, HTTP, CLI, or integration verification workflow.
---

# Create a verification skill

Create `.agents/skills/verify-<app>/` for one application at a time.

## Interview the repository

Determine from code and configuration:

- the user-facing surface;
- the existing development command and expected URL, port, or socket;
- stable ways to drive it, preferring current browser, HTTP, CLI, or test harnesses;
- observable evidence and side effects;
- authentication, seed-data, environment, and isolation constraints.

Do not start the application. This repository assumes it already runs. Ask only for information that code, configuration, process state, and the visible application cannot provide.

## Generate

Use the client's available skill-creation mechanism. When none exists, create `SKILL.md` directly, mirroring the layout of the existing skills in `.agents/skills`. The generated skill must contain:

- Doctor: a read-only check that confirms the expected instance and version are reachable.
- Drive: exact selectors, routes, commands, or requests from this repository.
- Evidence: the action, resulting UI or response, and relevant side effects.
- Cleanup: only resources created by the verification run. Never kill processes by name.
- Feature map: the top three to five user-facing flows, each with entry path and observable success.

Store temporary evidence in an ignored location. Do not commit screenshots, credentials, tokens, or personal data.

## Prove the skill

Validate the skill folder, run Doctor, drive one mapped feature against the existing instance, capture evidence, and execute cleanup. A generated skill that has not completed this loop is a draft.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall