Skip to main content
skill CX Codex

verify · raphaelsalaja — Claude Code skill: checks changes in the app

The verify Claude Code skill checks UI and behaviour changes in the running app. The agent opens the affected screen, tests new controls and reports where the result can be seen.

MIT 171 installs ★ 69 updated 2026-11-14

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add raphaelsalaja/skills --skill verify -a claude-code
Open on GitHub

What verify does

verify requires evidence from the running app rather than treating a successful build as proof. The agent first reproduces the issue, then reloads the screen or confirms hot reload, inspects the full affected area and tries each new control.

When the same issue returns, the skill directs the agent to investigate its cause, for instance by comparing with the last working commit. The report says what was checked and where, and names anything left unchecked and why. If the running result cannot be reached, the agent must state what blocks access; a change is not verified until it has been opened.

What it helps with

  • check a UI fix in the running app
  • catch a new control that has no effect
  • trace a recurring issue instead of changing the same value again
  • tell where a verified change can be seen

Example prompts for the agent

  • Check the fix on the settings page and tell me where to see the result.
  • Test the new button in the running app.
  • The issue came back: compare with the last working commit and find the cause.

How to install verify

1Skills CLI (Vercel)

npx skills add raphaelsalaja/skills --skill verify -a claude-code

2Manually: put the files in place

~/.claude/skills/verify/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/verify/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about verify

How do I install verify in Claude Code?

Run npx skills add raphaelsalaja/skills --skill verify -a claude-code. The skill file is at ~/.claude/skills/verify/SKILL.md.

What does verify do?

It sets out a process for checking changes against the running app. The agent reproduces the issue, inspects the affected screen and reports what it could verify.

Why doesn't a passing build count as verification in verify?

A build or typecheck cannot show whether a UI or behaviour change works in the app. The agent has to open the result and inspect it there.

Source text

SKILL.md · MIT
---
name: verify
description: Checks a change in the running app before calling it done, then says where to see it.
---

# Verify

This skill decides when a change may be called done. It asks for evidence from the running result, not from a passing build.

## A build is not evidence

A typecheck, a lint pass or a green build does not show that a visual or behavioural change works. Saying "fixed" without opening the result is a finding. Opening it and reporting an imperfect result is not.

Run it after any change to UI or behaviour, before replying "done". Run it at once when the user says "still", "nothing changed" or "test it yourself". What to change belongs to `scope`. Matching an outside app belongs to `match`.

## 1. See the problem first

Open the app, the page or the output and find the symptom before editing. Use the browser, a screenshot or computer use. Editing from the description alone is `verify-reproduce-first`. When you cannot reach the running result, say what blocks you.

## 2. Look where the user will look

Reload, or confirm hot reload applied, then look at the same place. A build pass offered as proof is `verify-build-is-not-proof`. Click every control you added once. A control with no effect is `verify-click-new-controls`.

Look at the whole surface, not only the line you edited. Scroll to both ends and open each state the change touches. Checking only the edited element is `verify-whole-surface`.

## 3. Find the cause on a repeat report

When the user reports the same problem again, stop adjusting the same value. Diff against the last commit where it worked, read the computed style or search for the cause. A third guess at one property is `verify-root-cause-on-repeat`.

## 4. Report what you saw

Say what you checked, how and where the user can see it: the route, the window, the menu path or the folder. "It should work now" is `verify-say-where`. Open the result for the user when you can. A bare output path is `verify-open-the-result`.

Name anything you could not check and why. "Done" with an unchecked item is `verify-name-the-gap`.

## The pair

Every check is a pair. The broken line sits beside the line that replaces it.

| Rule | Broken | Replacement |
| --- | --- | --- |
| `verify-reproduce-first` | Editing from the bug report alone | Open the screen, see the bug, then edit |
| `verify-build-is-not-proof` | "Typecheck passes, so it is fixed" | "Reloaded Settings and the toggle now persists" |
| `verify-click-new-controls` | A new "Add Condition" button with no handler | Click it once and see a row appear |
| `verify-whole-surface` | Checking the edited row only | The whole panel, scrolled to both ends |
| `verify-root-cause-on-repeat` | A third tweak to the same `padding` | Diff against the last working commit, then fix |
| `verify-say-where` | "It should work now" | "Open Library, right-click a save, choose Hide" |
| `verify-open-the-result` | `~/Downloads/clips` printed in the reply | The folder opened for the user |
| `verify-name-the-gap` | "Done" while export was never run | "Not verified: export, it needs a signed build" |

## Reporting

**Severity.** `HIGH` is "done" with no look at the running result, or a new control that does nothing. `MEDIUM` is a repeat report met with another guess, or a reply with no place to see the change. `LOW` is a checked change whose reply omits how it was checked.

**Format.** One finding per root cause, citing the request when no file applies:

```
file:line - [rule-id] what is wrong
request 2 - [rule-id] what is wrong
```

Then a `Rule | Count | Severity` summary. `Block` when any `HIGH` remains, `Approve` otherwise. Never `Approve` a change you did not open. Mark every check you could not run as `Not verified`.

© raphaelsalaja · MIT · raphaelsalaja/skills

Similar skills

SKILL.md skills catalog →

verify by other authors comes first.

verify react verify validates code changes against React repository requirements before committing. Runs Prettier, linter, Flow type checks, and tests. CX Codex +1 1,200installs verify Yeachan-Heo verify turns "it should work" into evidence you can read: which check ran, what passed, and what stayed unverified. CX Codex +1 721installs verify official anthropics verify — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode that tests harness changes end-to-end without Docker. CX Codex +1 257installs verify codewithmukesh verify — a skill for Claude Code, Codex, Cursor, and other agents that runs a seven-phase verification pipeline on .NET projects: build, analyzers, antipattern detection, tests, security, formatting, and diff review. CX Codex +1 4,000installs verify plastic-labs The verify Claude Code skill tests Honcho changes against a running local app. It exercises the HTTP API, deriver queue, and SQL query plans. CX Codex +1 172installs playwright-stealth-verify liarjsdev playwright-stealth-verify — a skill for Claude Code, Codex, Cursor and more that runs liarjs against a Page you already have and scores its fingerprint across eight checks. CX Codex +1 132,900installs verify-and-stop JuliusBrussee verify-and-stop proves existing work meets acceptance criteria without expanding scope. Useful for validation tasks and last-mile checks. CX Codex +1 129,000installs convex-verify convex convex-verify is a Claude Code skill that tests Convex features with multiple user identities. It runs when asked to verify a specific query, mutation, or action. CX Codex +1 43,800installs block-no-verify-hook cskwork block-no-verify-hook is a skill for Claude Code, Codex, and Cursor that adds a PreToolUse hook to intercept Bash calls with --no-verify or --no-gpg-sign before execution. CX Codex +1 6,500installs openspec-verify-change openspec openspec-verify-change is a Claude Code skill that checks code against OpenSpec specs, tasks, and design before archiving a change. CX Codex +1 4,000installs om-verify-in-repo open-mercato om-verify-in-repo — a skill for Claude Code runs read-only triage on tracker issues before triggering autofix workflows. It verifies defects and halts the pipeline with NO_ACTION_NEEDED if no work is required. CX Codex +1 3,500installs

From the same set25

The whole set →
restraint The restraint Claude Code skill trims changes to the requested scope. It flags extra UI, settings, and code paths during implementation and cleanup. CX Codex +1 175installs defaults defaults — a skill for Claude Code enforces interface baseline rules across surfaces, scrolling, shadows, focus states, and overlays. Audits markup against common UI flaws directly in code. CX Codex +1 174installs lab lab — a skill for Claude Code that builds an isolated preview route displaying all states and variants of actual UI components. Runs during component styling and design tuning in local development. CX Codex +1 173installs copy copy — a Claude Code skill that inspects and edits interface text. Enforces Title Case on buttons and headers, cuts excess phrasing, and bans em dashes. CX Codex +1 172installs keyboard This Claude Code skill tests a running page using only the keyboard. It records focus stops and reports controls that users cannot reach, see, or operate. CX Codex +1 170installs rule This Claude Code skill turns repeated corrections into short project rules and fixes code that breaks them. After the same correction comes up twice, it proposes a rule. CX Codex +1 169installs scope The scope Claude Code skill keeps code edits within the user’s request and tracks each requested item. It applies to focused changes, refactors, and planning tasks. CX Codex +1 169installs prototype prototype is a Claude Code skill that builds several working versions of one idea on a single page. The agent uses it on direct request, then moves the chosen version into the product and removes the rest. CX Codex +1 168installs

Project sponsors

Companies that keep this analytics open