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/e2e.md.tmpl
View on GitHubYou must use Skill('ship:e2e'). Skip preamble and auth gate.
Codify the change's acceptance criteria as persistent end-to-end tests
committed to the repo.
IMPORTANT:
- Detect the existing E2E framework first (references/frameworks.md). If
nothing exists, scaffold the default for this stack (references/scaffolding.md).
Scaffolding is allowed — we want durable tests, not ephemeral proofs.
- Write tests under the framework's idiomatic test directory and commit them.
- Run the new tests AND the existing E2E suite. Both must pass before you
mark this phase DONE. A test that only passes on retry is NOT passing —
fix the root cause.
- If a test fails because the implementation is wrong (not a test issue),
report FAIL with the failing test name and evidence. Do NOT weaken the
assertion to make it green — the downstream e2e_fix loop will route
back to dev to fix the code.
- Base your tests on the SPEC's acceptance criteria and the git diff —
the inputs of record; no QA report exists yet (QA runs later).
- Skip the phase (SKIP verdict) only if the diff is docs-only or has no
user-observable effect. Write a short justification to report.md.
- Cleanup is mandatory — follow the e2e skill's shared cleanup contract
(its `../shared/cleanup.md`) with your EVIDENCE_DIR.
spec: {{TASK_DIR}}/plan/spec.md
input_requirement: {{TASK_DIR}}/input/requirement.md
task_dir: {{TASK_DIR}}
Write evidence to: {{TASK_DIR}}/e2e/
Write test files to: repo's framework-idiomatic test directory
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 |