DangQuangSE/team-development-skills / .cursor/skills/ck-test
ck-test
VerifiedStandalone testing skill — owns writing and running tests, verifying behavior, and two-pass TDD orchestration. Default mode analyzes changed scope and runs the relevant tests; `--unit`/`--integration`/`--e2e`/`--all` scope by test type; `--verify` reruns exactly the prior failures; `--all-phases <plan>` sweeps every completed phase for regression. `--tdd --prepare`/`--tdd --verify` bracket `ck:cook` for red-green TDD. Never edits production code, and blocks until a phase's `ck:quality` gate is APPROVED (except `--tdd --prepare`, which runs before any implementation exists).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.8 KB |
| agents/openai.yaml | config | 227 B |
| references/tdd-ready-schema.json | config | 971 B |
| references/test-report-schema.json | config | 1.8 KB |
references/test-report-schema.json
View on GitHub{
"_comment": "Example ck:test report. One report is written per invocation (except --tdd --prepare, which writes tdd-ready-schema.json instead). Not a JSON-Schema document — an annotated canonical instance, matching this pack's plan-schema.json / ck-quality report-schema.json convention.",
"phase": "phase-02-receipt-gate",
"_phase": "Phase file stem (no extension). For --all-phases, one report per phase, or an aggregate — see mode.",
"mode": "verify",
"_mode_values": ["default", "unit", "integration", "e2e", "all", "verify", "all-phases", "tdd-verify"],
"verdict": "FAILED",
"_verdict_values": ["PASSED", "FAILED", "BLOCKED"],
"_verdict_rule": "BLOCKED means the phase's quality gate was not APPROVED and no test was written or run. FAILED means tests ran and at least one failed, or a tdd-verify run detected a weakened/deleted/modified prepared test.",
"reviewed_at": "2026-07-11T02:00:00Z",
"summary": {
"passed": 12,
"failed": 2,
"skipped": 0
},
"failures": [
{
"id": "TEST-004",
"severity": "HIGH",
"_severity_values": ["HIGH", "MEDIUM", "LOW"],
"type": "BEHAVIOR",
"_type_values": ["BEHAVIOR", "REGRESSION", "WEAKENED_TEST"],
"_type_weakened_test": "Only for tdd-verify: a prepared test's assertions were loosened, deleted, or narrowed without a corresponding acceptance-criteria change.",
"expected": "Duplicate request returns the existing result",
"actual": "A duplicate record was created",
"likely_owner": "production_code",
"_likely_owner_values": ["production_code", "test_code"],
"related_files": ["src/orders/create-order.ts"]
}
],
"report_path": "plans/{slug}/tests/{phase}-test-report.json",
"_report_path": "Set once the report is written to disk; ck:test always writes one, unlike ck:quality's audit modes."
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |