01-acceptance-qa — Claude Code skill: what it does, how to install
01-acceptance-qa is a Claude Code skill that checks browser-visible behavior against acceptance criteria and records evidence videos. It verifies changes that have already been reviewed.
MIT ★ 571 updated 2026-10-29
/plugin marketplace add ai-driven-dev/framework
/plugin install aidd-qa@aidd-frameworkWhat 01-acceptance-qa does
The skill checks an application's observable behavior against its acceptance criteria. It selects at most one primary path, then covers edge cases named by those criteria. Scenarios must trace to acceptance criteria, not to a diff or source code.
The workflow checks scope and prerequisites, prepares a run, then executes scenarios. It records and verifies video, resets state, and writes qa.md. Browser-runner and media dependencies are checked before execution, so those prerequisites need to be available.
It works on a reviewed change and does not patch the application. State-changing browser actions run sequentially, and the skill does not spawn agents. It is not for diff review or unit and integration tests.
What it helps with
- check a browser journey against acceptance criteria
- cover edge cases named in the criteria
- record scenario videos as reviewer evidence
- write the QA result to
qa.md
Example prompts for the agent
- Check this reviewed change against these acceptance criteria, run the browser journey, and record a video.
- Verify the candidate's browser behavior against the criteria, including their named edge cases, then write
qa.md. - Check whether the browser runner and media dependencies are ready for these acceptance scenarios.
How to install 01-acceptance-qa
1Plugin marketplace
/plugin marketplace add ai-driven-dev/framework/plugin install aidd-qa@aidd-frameworkThis installs the whole aidd-qa plugin with all its skills
2Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 01-acceptance-qa -a claude-code3Manually: put the files in place
~/.claude/skills/01-acceptance-qa/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/01-acceptance-qa/
1Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 01-acceptance-qa -a codex2Manually: put the files in place
.agents/skills/01-acceptance-qa/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 01-acceptance-qa -a cursor2Manually: put the files in place
.cursor/skills/01-acceptance-qa/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install ai-driven-dev/framework plugins/aidd-qa/skills/01-acceptance-qa2Manually: put the files in place
.github/skills/01-acceptance-qa/SKILL.md1Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 01-acceptance-qa -a gemini-cli2Platform CLI
gemini skills install https://github.com/ai-driven-dev/framework --path plugins/aidd-qa/skills/01-acceptance-qaManually: put the files in place
.devin/skills/01-acceptance-qa/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 01-acceptance-qa -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 01-acceptance-qa
How do I install 01-acceptance-qa in Claude Code?
Add the marketplace with /plugin marketplace add ai-driven-dev/framework, then install the skill with /plugin install aidd-qa@aidd-framework.
What does 01-acceptance-qa do?
It checks a reviewed change's browser-visible behavior against acceptance criteria, records scenario videos, and writes qa.md.
Can I use this skill to review a diff or fix the application?
No. It validates observable behavior against acceptance criteria; it does not review diffs or modify the application.
Source text
SKILL.md · MIT
--- name: 01-acceptance-qa description: Validate a reviewed candidate's observable behavior against its acceptance criteria and record short named videos as reviewer evidence. Use when acceptance criteria exist and a browser-observable journey needs proof it holds. Do NOT use for diff review, unit or integration tests, or application fixes. argument-hint: acceptance criteria | reviewed candidate --- # Acceptance QA ```mermaid flowchart LR scope["load-scope"] --> prerequisites["prerequisites"] --> prepare["prepare-run"] --> run["run-scenarios"] --> report["qa.md"] scope -- skipped --> report ``` ## Actions Read only the next action's file before running it. | # | Action | Does | | --- | --------------- | ---------------------------------------------------------- | | 01 | `load-scope` | Lock at most one happy path and the edge cases its acceptance criteria name | | 02 | `prerequisites` | Verify the browser runner and media dependencies | | 03 | `prepare-run` | Resolve the shortest deterministic path to executable runs | | 04 | `run-scenarios` | Record, normalize, verify, reset, and report every scenario | ## Transversal rules - Run against a reviewed change and never patch the application. - Never delete data not proven test-only. - Never derive a scenario from the diff or the source code; every scenario traces to an acceptance criterion. - Never spawn agents. Batch independent reads and tool checks, but keep state-changing browser work sequential. - Do not narrate action transitions, searches, fixtures, selectors, or successful checks. Report only a blocker, a required decision, or the final verdict and paths.
© AI-Driven Dev · MIT · ai-driven-dev/framework