agentleFS
Sign inStart free
WanbinyuWanbinyu/ship-guard-skills/skills/agent-diff-ship-check/SKILL.md

agent-diff-ship-check

Skill1 starsChanged 3 months agoMITView on GitHub

Pre-merge ship check for AI/agent-generated diffs. Use on uncommitted changes or PRs written mostly by agents, or Chinese "Agent 改动能不能合", "AI PR 检查", "上线前检查". Focus on ship risk, not style nits.

The file

Create a free account to mount
Files
SKILL.md

Agent Diff Ship Check

Overview

AI diffs fail differently: missing tests, silent behavior change, secrets, incomplete migrations, debug leftovers. Produce a go / no-go with blockers.

Checklist axes

  1. Intent — what was supposed to change vs what did
  2. Correctness risk — edge cases, nulls, authz
  3. Tests — added/updated? gaps?
  4. Migrations / flags — safe rollout?
  5. Secrets & debug — keys, console.log, TODOs that ship
  6. Scope creep — unrelated files
  7. Rollback — can we revert cleanly?

Steps

  1. Collect diff (git status / git diff / PR).
  2. Summarize intent in one sentence (ask user if unclear).
  3. Walk checklist; record blockers vs warnings.
  4. Required commands to run before merge (test, lint, migrate dry-run).
  5. Verdict: ship | ship-with-followups | block.

Exit criteria

  • Diff scope summarized
  • Checklist completed
  • Blockers explicit
  • Verdict stated

Anti-patterns

  • Style-only review
  • “LGTM” without tests when behavior changed

Output template

## Agent diff ship-check
### Intent
...
### Findings
| severity | item | why |
|----------|------|-----|
### Commands before merge
- [ ] ...
### Verdict
- **block** | **ship-with-followups** | **ship**

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