heliohq/ship / skills/auto
auto
VerifiedRun Ship's full production workflow from raw requirement to PR: design, dev, E2E, review, QA, refactor, and handoff. Use only for explicit /ship:auto, auto pipeline requests, or end-to-end delivery.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.2 KB |
| prompts/design.md.tmpl | other | 1005 B |
| prompts/dev-fix.md.tmpl | other | 507 B |
| prompts/dev.md.tmpl | other | 657 B |
| prompts/e2e-recheck.md.tmpl | other | 755 B |
| prompts/e2e.md.tmpl | other | 1.5 KB |
| prompts/handoff.md.tmpl | other | 1.3 KB |
| prompts/qa-recheck.md.tmpl | other | 585 B |
| prompts/qa.md.tmpl | other | 1.4 KB |
| prompts/refactor.md.tmpl | other | 586 B |
| prompts/review.md.tmpl | other | 908 B |
prompts/qa.md.tmpl
View on GitHubYou must use Skill('ship:qa'). Skip preamble and auth gate.
Exploratory verification of the running application. Find what the codified
suite couldn't see: UX problems, edge cases, visual regressions, perf issues.
IMPORTANT: You MUST start the application and test it interactively.
- If the diff touches frontend/UI → use browser testing (references/browser.md)
- If the project is an Electron app → use Electron automation (references/electron.md)
Use agent-browser via CDP — do NOT use computer-use/request_access (Electron apps
register as "Electron Helper (Renderer)", not as a named macOS app).
Read the reference BEFORE attempting anything to avoid wasted retries.
- If the diff touches API endpoints → use API testing (references/api.md)
- If the diff touches CLI → use CLI testing (references/cli.md)
"E2E tests passed" is the baseline you're building on, not a substitute —
you're exploring beyond the codified cases. Every acceptance criterion still
needs direct evidence (screenshot, curl output, command output) from your own
interactive session.
Context:
- Review is also clean — correctness concerns already addressed statically.
spec: {{TASK_DIR}}/plan/spec.md
e2e_report: {{TASK_DIR}}/e2e/report.md (may exist — lists what was codified)
input_requirement: {{TASK_DIR}}/input/requirement.md
task_dir: {{TASK_DIR}}
Write reports to: {{TASK_DIR}}/qa/
Mode: /ship:auto staged workflow — no user questions.
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 |