agentleFS
thoughtfulllcthoughtfulllc/gridland/.claude/skills/release-check/SKILL.md

release-check

Skill363 starsChanged 7 months agoMITView on GitHub

Pre-release checklist. Runs all 4 agents plus snapshot regression test, TypeScript check, and semver confirmation. Run before publishing a new package version.

14 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If context files are out of date, warn and suggest running /sync-context.

    line 51

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Pre-release checklist before publishing a new package version.

Step 1 — Gather scope of changes

git diff --name-only $(git describe --tags --abbrev=0 2>/dev/null || echo "HEAD~10") HEAD

Get current versions:

grep '"version"' packages/ui/package.json packages/utils/package.json

Step 2 — Run all 4 review agents

Spawn simultaneously as background agents:

  • contract-guardian — API changes and semver recommendation
  • framework-compliance — patterns, anti-patterns, vendor boundary
  • docs-mirror — documentation accuracy
  • dependency-auditor — external library usage

Step 3 — TypeScript check

bun run --cwd packages/ui build 2>&1 | tail -30
bun run --cwd packages/utils build 2>&1 | tail -20

Flag any TypeScript errors as release blockers.

Step 4 — Snapshot regression

bun run --cwd packages/ui test 2>&1 | tail -40
bun run --cwd packages/web test 2>&1 | tail -40

Report which snapshots changed. Ask for explicit confirmation before updating.

Step 5 — Context files check

git diff HEAD -- CLAUDE.md packages/ui/CLAUDE.md packages/docs/CLAUDE.md .claude/rules/

If context files are out of date, warn and suggest running /sync-context.

Step 6 — Aggregate and present

## Release Check Report

### Release Blockers
- [list of critical issues from all agents]
- [TypeScript errors]
- [Unexpected snapshot changes]

### Warnings
- [non-critical issues]

### TypeScript Status
- packages/ui: PASS/FAIL
- packages/utils: PASS/FAIL

### Snapshot Status
- Changed: [list] — need explicit confirmation
- Unchanged: [count]

### Semver Recommendation
**[MAJOR | MINOR | PATCH]** — based on contract-guardian findings
Current: X.X.X → Suggested: X.X.X

### Agent Summary
- contract-guardian: [pass/fail]
- framework-compliance: [pass/fail]
- docs-mirror: [pass/fail]
- dependency-auditor: [pass/fail]

Do not publish or update versions without explicit user confirmation.

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.