06-test — Claude Code skill: what it does, how to install
06-test finds untested behaviors, iterates tests until they pass, and validates user flows end to end in the browser.
MIT ★ 571 updated 2026-10-29
/plugin marketplace add ai-driven-dev/framework
/plugin install aidd-dev@aidd-frameworkWhat 06-test does
The skill guides coding agents through developer-side testing during feature implementation. It defines two distinct actions: test to detect missing test coverage and write unit tests, and test-journey to walk a user flow end to end directly in the browser. Tests focus strictly on functional behavior without binding to implementation internals.
The agent selects a single action per run and reads the matching file in the actions/ folder. When the goal is unclear, the agent must ask one clarifying question instead of guessing.
This skill is explicitly not intended for independent acceptance QA, reviewer evidence, test suite health audits, or troubleshooting failing test suites.
What it helps with
- find untested application behaviors during development
- write and iterate tests until all checks pass
- validate a multi-step user journey directly in the browser
Example prompts for the agent
- Find what's untested in the payment service and write tests until they pass
- Test the complete checkout user journey in the browser
- Add test coverage for the billing flow scope
How to install 06-test
1Plugin marketplace
/plugin marketplace add ai-driven-dev/framework/plugin install aidd-dev@aidd-frameworkThis installs the whole aidd-dev plugin with all its skills
2Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 06-test -a claude-code3Manually: put the files in place
~/.claude/skills/06-test/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/06-test/
1Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 06-test -a codex2Manually: put the files in place
.agents/skills/06-test/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 06-test -a cursor2Manually: put the files in place
.cursor/skills/06-test/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install ai-driven-dev/framework plugins/aidd-dev/skills/06-test2Manually: put the files in place
.github/skills/06-test/SKILL.md1Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 06-test -a gemini-cli2Platform CLI
gemini skills install https://github.com/ai-driven-dev/framework --path plugins/aidd-dev/skills/06-testManually: put the files in place
.devin/skills/06-test/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 06-test -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 06-test
How to install 06-test in Claude Code?
Run /plugin marketplace add ai-driven-dev/framework, then run /plugin install aidd-dev@aidd-framework.
What does 06-test do?
It guides coding agents to detect untested behavior and iterate developer tests until they pass, or walk full user journeys inside a browser.
When should you not use 06-test?
Do not use it for independent acceptance testing, auditing test health, generating reviewer proof, or debugging broken tests.
Source text
SKILL.md · MIT
--- name: 06-test description: Write and iterate developer-side tests until they pass, or validate a user journey end to end in the browser during implementation. Use when the user wants to add coverage, find what's untested, or walk a flow while building it. Do NOT use for independent acceptance QA or reviewer evidence, auditing test health, or debugging a failure. argument-hint: scope | journey --- # Skill: test Find untested behavior and iterate tests until they pass, or drive a full user journey through the browser and check each step. ## Actions | # | Action | When to use | | --- | -------------- | -------------------------------------------------------------- | | 01 | `test` | Find untested behaviors and write or iterate tests until they pass | | 02 | `test-journey` | Validate a full user journey end-to-end in the browser | Pick the one action matching the intent; never default to `01`. Triggers like "write tests" or "what's untested" route to `01`, "test the user journey" or "end-to-end" to `02`. Ask one question when the intent is ambiguous. Before running an action, read its file in `actions/`, not only the table or assets. ## Transversal rules - One action per run: follow only the matching action file. - Functional behavior only: never couple a test to implementation details. - Never compromise quality for speed.
© AI-Driven Dev · MIT · ai-driven-dev/framework