Acceptance Criteria Design
Design executable acceptance criteria for approved requirements by converting goals/specs into binary pass/fail checks with observable outcomes. Use when implementation handoff, QA validation, or release decisions need testable criteria for stable `REQ-*`/`NFR-*` baselines; do not use for requirement discovery, prioritization, or sprint slicing.
Install
$ agentstack add skill-kentoshimizu-sw-agent-skills-acceptance-criteria-design ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Acceptance Criteria Design
Overview
Use this skill to translate approved requirements into acceptance criteria that engineering and QA can execute without interpretation drift.
Scope Boundaries
- Use this skill when the task matches the trigger condition described in
description. - Do not use this skill when the primary task falls outside this skill's domain.
Inputs To Gather
- Approved requirements (
REQ-*) and relevant non-functional requirements (NFR-*). - Business intent, out-of-scope boundaries, and policy constraints.
- User-visible behaviors, system side effects, and error paths.
- Test environment capabilities and observability limits.
Deliverables
- Acceptance criteria set with binary pass/fail expectations.
- Scenario matrix covering happy path, boundary, negative, and failure cases.
- Traceability map: requirement -> criterion -> verification method.
- Open ambiguity list that blocks objective verification.
Quality Standard
- Each criterion is independently testable and yields one clear result.
- Each criterion states preconditions, action, expected observable outcome, and evidence source.
- Boundary values, invalid inputs, authorization errors, and integration failure behavior are covered when applicable.
- Criteria describe required behavior, not implementation detail.
- Overlap and contradiction across criteria are removed.
Workflow
- Normalize requirement intent and explicit assumptions.
- Split requirements into observable behavior units.
- Draft pass/fail criteria for normal, boundary, negative, and failure scenarios.
- Define evidence sources (API response, UI state, logs, metrics, events) for each criterion.
- Run ambiguity and overlap review; publish unresolved blockers.
Failure Conditions
- Stop when requirement intent is unstable or contradictory.
- Stop when a criterion cannot be verified with available test/observability capabilities.
- Escalate when missing instrumentation prevents objective pass/fail judgment.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: KentoShimizu
- Source: KentoShimizu/sw-agent-skills
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.