WanbinyuWanbinyu/ship-guard-skills/skills/using-ship-guard-skills/SKILL.md

using-ship-guard-skills

Skill1 starsChanged 3 months agoMITView on GitHub

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.

Reads credentials

In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-diff-ship-checkSkill
- customer-bug-to-failing-testSkill
- dead-code-safe-deleteSkill
- env-drift-checkSkill
- feature-flag-lifecycleSkill
- flake-vs-bug-triageSkill
- minimal-repro-packSkill
- secret-redact-before-aiSkill

The file

Create a free account to mount

Files

SKILL.md

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

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

Steps

Restate goal.
Pick skill.
Announce.
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

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

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free