Individual skill
verify
Confirm a change works by running the real thing: start the app the way the project starts it, exercise it with real requests, assert the side effect in the data rather than the status code, compare the screen against the design when asked, and stop after three rounds with a named person rather than patching indefinitely. Use when the suite is green and nobody has yet seen the feature work, before handing a ticket to QA, or before a release goes out. Triggers on: "verify", "verify this works", "kiểm chứng", "chạy thử thật", "test thực tế", "đối chiếu thiết kế", "動作確認", "実機確認", "画面確認", "/atk:verify".
plugins/atk/skills/verify/SKILL.md
Source commit 55481d2e4ae3cec8e2050c160303c751bbf20173
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 12
- Repository last updated
- Nov 9, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- ai-skills Repository topic
- claude-code Repository topic
- codex Repository topic
- cursor Repository topic
- plugin Repository topic
- sdlc Repository topic
- team-workflow Repository topic
- design Derived category
- data Derived category
- testing Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 19,732 bytesSKILL.mdcore · 19,732 bytesSKILL.mdcore · 19,732 bytesSKILL.mdcore · 19,732 bytesevals/trigger_evals.jsonasset · 2,915 bytesreferences/report-template.mddoc · 7,253 bytesreferences/runtime-checks.mddoc · 19,943 bytesreferences/ui-checks.mddoc · 4,902 bytes
Read excerpt
# Verify on the Running System (`atk:verify`)
Runs the thing and looks. A green suite proves that the checks somebody wrote still pass; it does
not prove that the record was written, that the job reached the queue, or that the screen renders
what the design says. This skill closes that distance, on the real application, with the commands
the project itself uses.
It has one built-in limit. After three rounds of fix and retry it stops and hands the problem to a
person by name: a failure that survives three fixes is usually a design question in a bug's clothes.
## Scope
Handles: starting the application the way `.atk/profile.md` says to start it, waiting for the
readiness signal, exercising the change with real requests or real interaction, asserting the side