maestro-lifecycle-test
SolidValidate a built maestro binary end to end (install/init completeness + the feature->task->QA lifecycle + standalone tasks + real-use edge cases + agent-UX) in an isolated throwaway repo, emitting a machine-aggregatable NDJSON report. Run as one sub-agent of a swarm fix-loop, or standalone to smoke-test a change.
Install
Quality Score: 91/100
Skill Content
Details
- Author
- ReinaMacCredy
- Repository
- ReinaMacCredy/maestro
- Created
- 5 months ago
- Last Updated
- today
- Language
- Rust
- License
- MIT
Similar Skills
Semantically similar based on skill content — not just same category
test-as-self
Deploy the current instar dist into a throwaway agent home and verify the deploy is healthy — clean evidence instead of post-hoc log forensics. Use BEFORE shipping a change that touches the deploy/lifeline/server path; AFTER landing such a change; or to reproduce a crash observed in the wild.
qa
Run test suite, browser checks, and verify acceptance criteria. Bootstrap test framework if missing.
long-run
Set up a long-running multi-agent orchestrator that builds a project end-to-end across many /loop cycles. Use when the user wants to "kick off an overnight build", "start a weekend run", "set up the orchestrator harness", "run a long autonomous build", or any task framed as "let Claude build this while I sleep". Hard-requires a detailed milestone roadmap before kickoff — if the user lacks one, this skill stops and routes them to write one (it does NOT auto-generate the roadmap). Uses Git as the source of truth; expects the app, docs, marketing site, tests, and screenshots to live in the same repo so the prototype's assets evolve together. Do NOT apply to short one-shot tasks, single PRs, or anything that can finish in one Claude turn.