Extend Smoke Coverage
mastra-ai/mastra-smoke/.agents/skills/extend-smoke-coverage
ai-mlOfficial
Official Provider SkillView repo
Add smoke-test coverage for a new Mastra feature, API route, or Studio UI surface. Use when the user asks to "add coverage for X", "write a smoke test for the new Y endpoint", "test the new Z page", when a Mastra release notes mention features not currently exercised, when investigating a regression that wasn't caught because there was no test for that path, or any time you are about to write or modify a `.test.ts` / `.spec.ts` file under `tests/` or `tests-ui/`. This skill explains where tests
Files1 files
SKILL.md675 lines
Loading editor…
Install
RecommendedOne command — your agent picks it up automatically.
Select an AI agent above to see the install command.
or
Manual Install
More stepsDownload the file and paste it into your agent's system prompt.
Skill details
Versionv1.0.0
AuthorMastra AI
Categoryai-ml
Skill IDmastra-ai/mastra-smoke/.agents/skills/extend-smoke-coverage
Related skills
Debug Mastra FrameworkDebug bugs inside the @mastra/* packages from the smoke suite. Use when a smoke test fails with a stack trace pointing at node_modules/@mastra/* or .mastra/output/*, when you see framework-specific error strings (keyValidator._parse, SQLITE_ERROR mastra_*, "Background task started" instead of a tool result, "Tool not found" 500s, ZodObject._parse crashes), or when the user asks to investigate a regression in the published alpha. This skill teaches you how to map a published version back to upstrDiagnose Smoke FailureDiagnose a failing Mastra smoke-test run when tagged on the failure thread in Slack (the channel running `mastra-ai/mastra-smoke`). Use this when you see a Slack message containing the literal token `SMOKE_FAILURE_CONTEXT` in a thread you've been mentioned in, when the user asks you to "debug this smoke run" / "look at the failure" / "diagnose this red build", or when a smoke-channel message links to a `github.com/mastra-ai/mastra-smoke/actions/runs/<id>` URL and asks for help. This skill teacheAgent Prompt Quality BarUniversal quality bar and final audit rubric for any agent system prompt. Activate this whenever you are unsure which archetype skill applies, or as a final review pass before writing the system prompt. It defines the required run contract, completion criteria, fallback paths, response format, and anti-patterns every produced agent prompt must satisfy.Builder Smoke TestSmoke test the Agent Builder feature branch end-to-end against a hermetic project scaffolded by the skill (linked to the current worktree). Covers workspace reconciliation, stored agents/skills CRUD, ownership, visibility, stars, registry/library Copy flow, picker allowlists, model policy, RBAC role gating, role impersonation UI, builder defaults, infrastructure diagnostics, channels, and Studio + Agent Builder UI. Trigger when validating the agent-builder feature branch, PRs that touch packagesDebugging Difficult BugsUse early when debugging a medium or hard bug, especially when tests alone may not reveal the real runtime failure. Trigger this before extended TDD iteration when a bug involves runtime state, ordering, persistence, streaming, concurrency, UI/manual reproduction, external services, or when a red or newly passing test may not model the real issue. Skip only when the root cause is already directly proven by a stack trace or deterministic test that exercises the real runtime path.Docs DiagramsConvert existing docs diagram images to Mermaid, and author new Mermaid diagrams for Mastra docs. Use when replacing an Excalidraw or PNG/JPG/SVG diagram with Mermaid, when a docs page needs a new diagram, when a diagram renders wrong in light or dark mode, or when auditing which docs images should become Mermaid. Triggers on: convert diagram, Excalidraw, mermaid, flowchart, diagram image, diagram styling, diagram looks wrong.