Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/test-runner
Use 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 Microsof
Passed 12 of 19 test cases with the skill, and 3 of 19 without it.
and 14 more in the full report
11 fixed3 passed either way7 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
During issue triage, a finding title is evaluated against open tracker issues. If no exact fingerprint match exists, but an issue exists with a title Levenshtein distance of 1, what triage action is produced?
| Checked | Without skill | With skill |
|---|---|---|
| Selects update as the decision action from triageDecision when title Levenshtein distance is <= 2. | Missed | Passed |
| Calls updateFinding to append a comment to the existing issue. | Missed | Passed |
The instructions your model reads when the skill loads.
Project-instruction file resolution:
CLAUDE.mdandAGENTS.md(Codex CLI) are transparent aliases — see skills/_shared/instruction-file-resolution.md. Wherever this skill mentionsCLAUDE.md, the alias rule applies.
Before anything else, read and internalize soul.md in this skill directory. It defines WHO you are — your role as an orchestrator, your delegation boundaries, and your non-negotiable constraints.
Read skills/_shared/bootstrap-gate.md and execute the gate check. If GATE_CLOSED, invoke skills/bootstrap/SKILL.md and wait for completion. If GATE_OPEN, continue to Phase 1.
Read and parse Session Config per skills/_shared/config-reading.md. Store result as $CONFIG.
Test-runner specific fields (parse these specifically):
test-runner.default-profile (default: smoke)test-runner.retention-days (default: 30)test-command, typecheck-command, lint-command (used for context only — not driven here)Resolution order (first match wins):
--target <name> --profile <name> (explicit, highest priority).orchestrator/policy/test-profiles.json by target name (if present)playwright.config.{ts,js} present → target type web, dispatch playwright-driverPackage.swift present → target type mac, dispatch peekaboo-driver (see skills/peekaboo-driver/SKILL.md)Error: Cannot resolve target — provide --target or add .orchestrator/policy/test-profiles.json
test cases passed, vs 3 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.