Ac Validation — Development skill for Claude Code
Review Acceptance Criteria for one or more user stories against completeness and quality standards.
How to install Ac Validation
Installs to ~/.claude/skills/kuzniarr-ai-native-ba-framework-ac-validation/SKILL.md
mkdir -p ~/.claude/skills/kuzniarr-ai-native-ba-framework-ac-validation && curl -fsSL https://raw.githubusercontent.com/kuzniarr/ai-native-ba-framework/HEAD/skills/ac-validation.md -o ~/.claude/skills/kuzniarr-ai-native-ba-framework-ac-validation/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Ac Validation does
name: ac-validation description: "Review Acceptance Criteria for one or more user stories against completeness and quality standards. Checks happy path, alternative flows, edge cases, error states, and criterion quality, and returns findings only — never rewrites the AC. Use before refinement, or on AC inherited from someone else."
ac-validation
What it does
Reviews the Acceptance Criteria of a story, or a set of stories, against completeness and quality standards. Returns a stru
Alternatives in Development
- Happy — Mobile and Web client for Claude Code, with realtime voice, encryption and fully featured 16.3k ★
- Open Agent SDK TypeScript — Agent-SDK without CLI dependencies, as an alternative to claude-agent-sdk, completely open source 2.6k ★
- 04 Gedcom Completeness — GEDCOM Completeness 1.1k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Hybrid Status
Show execution status of all stories in the PRD. Displays batch progress, individual story states, completion
HERO Anti OverDefense
HERO = Hashing · Edge cases · Rubrics · Overbuild — the four shapes coding agents over-defend in. A paste-in c
Cluster Triage
Ensemble-curator step 6 — for a detected cluster, pick winner(s) by file-path, extract edge cases from losers,
Wp Dev Learn
Extract learnings from the current session and update wp-dev-skills skill files — captures corrections, new ru
Unity Interview
Socratic interview flow — explores requirements, identifies edge cases, clarifies scope, and outputs a structu
Definition Of Done Rules
Always-on Definition of Done. Applied to every behavior change. Five hard criteria plus two opt-in -- review,
Related Agents
Critic Logic
Review code for logic bugs, unhandled edge cases, happy-path assumptions, input-validation gaps, and error-han
Scenario Griller
Brainstorms API test scenarios for a repo interactively (category by category, happy path first, then top edge
Agent Eval Engineer
Use to design and run regression evaluations for an agent, skill, tool, or prompt — happy-path, edge-case, adv