qa
Skill0 starsChanged 59 days agoMITView on GitHub
Runs a runtime smoke test of a change's golden path, beyond what unit tests cover. Use only for user/tool-facing changes — most changes don't need this.
In this repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- code-reviewSkill
- developerSkill
- orchestratorSkill
- plannerSkill
The file
Files
This skill spawns the qa subagent (.claude/agents/qa.md) to build the project and exercise the changed behavior at runtime.
To run it: invoke the Agent tool with subagent_type: "qa", naming the specific tool/feature that changed and what its golden path is. Most changes (refactors, internal-only logic, doc/config edits) don't need this — unit tests already cover them; reserve it for new or changed MCP tool behavior or CLI-visible output.
Calling other skills
- Calls: none — it tests and reports only.
- Called by:
orchestrator(step 4, conditionally, after review passes), or directly by the user via/qafor an ad hoc smoke test.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.