---
name: using-ship-guard-skills
description: >
  Route ship/delivery guard work after AI coding. Use when checking if an agent diff
  is safe to merge, redacting secrets, flaky tests, repro packs, feature flags, env
  drift, or Chinese "能不能合", "上线检查", "脱敏", "flaky", "最小复现", "特性开关",
  "环境变量对不上". Do NOT use for multi-model routing or request splitting to cheap models.
---

# Using Ship Guard Skills

## Overview

Pick the smallest delivery-guard skill. This pack is **after AI writes code**, not model routing.

## Routing

| Intent | Primary |
|--------|---------|
| Paste logs/secrets into chat | `secret-redact-before-ai` |
| Agent PR / uncommitted AI diff | `agent-diff-ship-check` |
| CI red intermittent | `flake-vs-bug-triage` |
| Need minimal repro | `minimal-repro-pack` |
| Bug ticket → test first | `customer-bug-to-failing-test` |
| Add/remove feature flag | `feature-flag-lifecycle` |
| .env vs docs mismatch | `env-drift-check` |
| Delete unused code safely | `dead-code-safe-delete` |
| Pre-merge full gate | Ship-check below |

## Ship-check sequence

1. `secret-redact-before-ai` if sensitive material in session  
2. `agent-diff-ship-check` on the diff  
3. `env-drift-check` if config touched  
4. `feature-flag-lifecycle` if flags touched  
5. Tests failing → `flake-vs-bug-triage`

## Steps

1. Restate goal.  
2. Pick skill.  
3. Announce.  
4. Execute to exit criteria.  

## Exit criteria

- [ ] Primary skill chosen  
- [ ] User informed  
- [ ] Specialized criteria met  

## Anti-patterns

- Multi-model dispatch “optimization” (wrong pack)  
- Approving merge without ship-check when pack was invoked  

## Output template

```markdown
## Ship-guard routing
- Goal: ...
- Primary: `...`
```