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
npx skills add raphaelsalaja/skills --skill verify -a claude-codeWhat 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-code2Manually: put the files in place
~/.claude/skills/verify/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/verify/
1Skills CLI (Vercel)
npx skills add raphaelsalaja/skills --skill verify -a codex2Manually: put the files in place
.agents/skills/verify/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add raphaelsalaja/skills --skill verify -a cursor2Manually: put the files in place
.cursor/skills/verify/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install raphaelsalaja/skills skills/verify2Manually: put the files in place
.github/skills/verify/SKILL.md1Skills CLI (Vercel)
npx skills add raphaelsalaja/skills --skill verify -a gemini-cli2Platform CLI
gemini skills install https://github.com/raphaelsalaja/skills --path skills/verifyManually: put the files in place
.devin/skills/verify/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add raphaelsalaja/skills --skill verify -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
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.