- Home
- Skills
- Agents & Orchestration
- Acceptance Criteria Verification
Works with the AI Agents you already use
Acceptance Criteria Verification
Checks every acceptance criterion individually against real evidence — never counts "most of them look fine" as done.
$4.99
Acceptance Criteria Verification
Example session with this skill installed
Check the acceptance criteria for the E2E testing ticket — the verification report just came back.
- Read your context and instructions
- Compiled the acceptance criteria verification
Summary
6 of 8 criteria look fine — but the ticket isn't done. One ambiguous locator matches two different "Add item" buttons, so the core happy-path test doesn't actually pass yet.
| Criterion | Status |
|---|---|
| Playwright configured, runs in CI | Satisfied |
| Critical happy-path flow passes | Not satisfied — locator matches 2 elements |
| Stable selectors | Not satisfied — same locator issue |
| Failure artifacts captured | Satisfied |
| Blocks promotion on failure | Not verifiable — no promotion pipeline exists yet |
| ...3 more | Satisfied |
{
"criteria": [
{ "text": "Critical happy-path flows are covered first.", "status": "not-satisfied", "evidence": "critical-flow.spec.ts exists but fails: strict-mode violation on an ambiguous locator.", "gap": "Locator needs scoping to its section before this flow genuinely passes." }
],
"overallStatus": "incomplete",
"ambiguousCriteria": []
}
Next steps
- Scope the ambiguous locator to its containing section
- Re-run implementation verification, then re-check acceptance criteria — don't call this done at "6 of 8"
Connects securely to your tools. The creator never sees your data.
About this skill
A ticket isn't done because most of its acceptance criteria look satisfied — it's done when every single one is. This skill takes a ticket's literal list of acceptance criteria and checks each one against concrete evidence from an implementation-verification step: a specific test, an observed behavior, a config change — never "the code looks like it should do this."
It handles the nuanced cases correctly: a criterion with its own documented escape valve gets marked not-applicable (with the reasoning), not falsely satisfied or falsely failed. A criterion about documentation quality gets marked not-verifiable with a pointer to what a human should actually read — never rubber-stamped satisfied just because a file with the right name exists.
The overall ticket is only "complete" when every criterion is satisfied or legitimately not-applicable — one real gap, however small, keeps it honestly incomplete.
Part of the Ticket-to-Shipped workflow: 10 skills covering the full requirement-to-shipped-code lifecycle. Works standalone too.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Only as good as the verification report it's given — if a check never ran, a criterion depending on it can't be marked satisfied, by design. Doesn't resolve genuinely ambiguous or contradictory criteria itself — flags them for a human instead of guessing. Assumes acceptance criteria are stated explicitly somewhere in the ticket; can't evaluate against criteria that were never written down.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 18 days ago