release-discipline
Enforce release discipline for AI agents and developers. Prevents version spam, forces quality checks before publishing, and maintains a 24-hour cooldown between releases. Use when the user wants to publish, release, deploy, or bump versions. Triggers on "release", "publish", "deploy", "version bump", "npm publish", "릴리즈", "배포", "버전".
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/gyeuun97/release-discipline🛑 Release Discipline
Stop version spam. Ship quality, not quantity.
Core principle: "Only finished work counts."
When This Activates
Intercept any release/publish/deploy action and run the pre-release checklist.
Pre-Release Checklist (ALL must pass)
Before ANY version bump or publish, enforce these checks:
Gate 1: Cooldown Check
❓ When was the last release?
→ If < 24 hours ago: 🛑 BLOCKED — "Cool down. Last release was {X}h ago. Wait until 24h."
→ If ≥ 24 hours: ✅ PASS
Gate 2: User Feedback Check
❓ Has anyone used the previous version?
→ Check: GitHub issues, npm downloads, ClawHub installs, user messages
→ If no feedback exists: ⚠️ WARNING — "No one has used v{X} yet. Why release v{X+1}?"
→ If feedback exists: ✅ PASS — Summarize feedback
Gate 3: Documentation Check
❓ Is documentation updated?
→ Check for: README.md, CHANGELOG, English docs
→ Missing README: 🛑 BLOCKED
→ Missing English: ⚠️ WARNING — "Global users can't read this"
→ All present: ✅ PASS
Gate 4: Quality Check
❓ Does this release have substance?
→ Ask: "What's the ONE thing this release does better than the last?"
→ If answer is vague ("minor fixes", "improvements"): ⚠️ WARNING — "Be specific. What changed?"
→ If answer is clear: ✅ PASS
Gate 5: Kill Criteria Check
❓ What kills this project?
→ If no kill criteria defined: ⚠️ WARNING — "Define when to stop: 'If X doesn't happen in Y weeks, shut it down.'"
→ If defined: ✅ PASS — Remind user of their kill criteria
Gate 6: Self-Contradiction Check
❓ Does this action match your stated principles?
→ Read SOUL.md (or equivalent principles file)
→ Look for contradictions:
- "Ship one thing at a time" + releasing 3 things = 🛑
- "Quality over quantity" + 5 releases in 3 days = 🛑
- "Finish before starting new" + new project while old unfinished = ⚠️
→ If contradiction found: 🛑 BLOCKED — Quote the principle and show the contradiction
→ If consistent: ✅ PASS
Scoring
🛑 BLOCKED (any) → Cannot release. Fix the issue first.
⚠️ WARNING only → Can release, but agent must voice concern clearly.
✅ ALL PASS → Release approved. Proceed.
Release Log
After every release (approved or blocked), log to memory/release-log.md:
## {date} — v{version}
- Status: ✅ APPROVED / 🛑 BLOCKED / ⚠️ WARNED
- Gates: [1:✅ 2:⚠️ 3:✅ 4:✅ 5:✅ 6:✅]
- Reason: {why released or why blocked}
- User feedback on previous: {summary or "none"}
- Time since last release: {hours}
Weekly Review
Every 7 days, review the release log:
- Total releases this week
- Block rate (healthy: 20-40% blocked = you're actually checking)
- 0% blocked = checklist is rubber-stamping, tighten criteria
- Pattern analysis: recurring issues
Anti-Patterns This Skill Prevents
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-gyeuun97-release-discipline": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
openclaw-starter-kit
OpenClaw 초보자를 위한 풀패키지 온보딩 스킬. 첫 세팅부터 보안 강화까지 대화형으로 안내한다. "초기 세팅", "처음 설정", "starter kit", "온보딩", "setup guide", "시작하기", "세팅 도와줘" 키워드에 반응.
ai-meeting-room
AI 회의실 — 주제를 던지면 전문가 AI 에이전트들이 다각도로 토론하고 회의록을 생성한다. 사업성 검토, 전략 회의, 브레인스토밍, 의사결정, 리스크 분석 등에 활용. Use when a user wants multiple perspectives on a topic, needs a business review, strategy discussion, brainstorming, devil's advocate analysis, or says "회의", "토론", "검토해줘", "브레인스토밍", "사업성", "meeting", "debate", "discuss", "review this idea".
gandalf-breaker
Solve Gandalf prompt injection CTF challenges (gandalf.lakera.ai). Provides a systematic attack methodology for each difficulty level, covering direct extraction, encoding bypasses, semantic misdirection, output filter evasion, and OSINT techniques. Use when the user wants to play Gandalf, practice prompt injection, learn AI red-teaming, or break LLM guardrails in a CTF/educational context.