test-runner
SolidUse this skill when orchestrating agentic end-to-end tests. Resolves target + profile, dispatches the right driver(s) (playwright for web today, peekaboo for macOS (issue #381)), invokes the ux-evaluator agent (opus, read-only) against driver artifacts, reconciles findings with the open issue tracker via scripts/lib/test-runner/issue-reconcile.mjs, and writes report.md + JSONL roll-up. Wraps upstream tools (no forks). Hard-gates Playwright MCP for browser drive (4× token cost vs CLI per Microsoft's own benchmark).
Install
Quality Score: 82/100
Skill Content
Details
- Author
- Kanevry
- Repository
- Kanevry/session-orchestrator
- Created
- 5 months ago
- Last Updated
- today
- Language
- JavaScript
- License
- MIT
Integrates with
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
playwright-driver
Use this skill when executing web tests via the canonical `playwright` npm package (Microsoft, Apache-2.0). Dispatched by `skills/test-runner/` to execute web tests against a target, captures token-frugal AX-tree snapshots + screenshots + console output under `.orchestrator/metrics/test-runs/<run-id>/`, and exits with deterministic JSON output the orchestrator can parse.
test-runner
Discover, run, and report change validation without modifying the workspace. Use for tests, lint, formatting, type checks, builds, or independent verification while another agent owns fixes. Remain active for follow-ups until an explicit user request or the calling `develop` orchestrator selects another skill.
playwright-tester
Author persistent Playwright .spec.ts tests, run them natively with `npx playwright test` (zero AI tokens per run), and fix failures in a diagnose-first loop. Use whenever the user wants to test a web app, check whether a frontend works, run or re-run UI tests, verify a form or login flow, do end-to-end testing, reproduce a UI bug, smoke test a site, catch a visual regression, check for broken links, test across browsers, add regression coverage, audit every component, sweep a codebase for UI bugs, or confirm recent changes did not break anything. Also triggers on "run my e2e tests", "my playwright tests are failing", "check the app in a browser", "does this page still work after my change", "test the happy path", "write e2e tests", "set up playwright", "find UI bugs", or "test the whole app and tell me what is broken". Prefer this over driving a browser live or screenshot-based checking for anything that should be verifiable more than once.