ship
Ship — Pre-Launch Checklist v3.0
Orchestrate all quality checks before shipping.
Checklist
SHIP CHECKLIST
==============
[ ] 1. /gates — All 4 stages pass (correctness, quality, security, consistency)
[ ] 2. /security — No critical/high vulnerabilities
[ ] 3. /browser-test — No console errors, Lighthouse > 90 (if frontend)
[ ] 4. /perf audit — Core Web Vitals in target range (if frontend)
[ ] 5. Git status — No uncommitted changes
[ ] 6. Tests — All tests pass
[ ] 7. ADR — Major decisions documented (if complexity >= 7)
[ ] 8. Spec — Exit criteria met (if spec exists)
Usage
/ship # Run full checklist
/ship --skip-browser # Skip browser tests (backend-only)
Behavior
- Run each check sequentially
- BLOCKING checks (1-2): must pass to ship
- ADVISORY checks (3-8): reported but don't block
- Output: summary with PASS/FAIL per check
Anti-Rationalization
| Excuse | Rebuttal |
|---|---|
| "It's just a small change" | Small changes cause big outages. Run the checklist. |
| "I already tested manually" | Manual testing misses what automated checks catch. |
| "The deadline is tight" | Shipping broken code costs more time than the checklist. |
More from alfredolopez80/multi-agent-ralph-loop
stop-slop
A skill for removing AI-generated writing patterns ('slop') from prose. Eliminates telltale signs of AI writing like filler phrases, excessive hedging, overly formal language, and mechanical sentence structures. Use when: writing content that should sound human and natural, editing AI-generated drafts, cleaning up prose for publication, or any content that needs to sound authentic rather than AI-generated. Triggers: 'stop-slop', 'remove AI tells', 'clean up prose', 'make it sound human', 'edit AI writing'.
10iterate
Ralph Loop pattern with swarm mode: iterative execution until VERIFIED_DONE with multi-agent coordination. Use when: (1) iterative refinement needed, (2) quality gates must pass, (3) automated validation required. Triggers: /iterate, 'iterate until done', 'keep trying', 'fix until passing', 'loop until done'.
2gemini-cli
|
2minimax
Custom skill for minimax
1clarify
Intensive requirement clarification using structured AskUserQuestion workflow. Gathers MUST_HAVE (blocking) and NICE_TO_HAVE (optional) information before implementation. Use when: (1) starting new feature implementation, (2) requirements are ambiguous, (3) multiple approaches possible, (4) before writing any code. Triggers: /clarify, 'clarify requirements', 'ask questions', 'gather requirements'.
1security
Security audit with Codex + MiniMax second opinion. Integrates ralph-security agent (6 quality pillars, OWASP A01-A10). Uses LSP for code navigation during analysis. Use when: (1) /security is invoked, (2) task relates to security functionality.
1