Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Enforce release discipline for AI agents and developers. Prevents version spam, forces quality checks before publishing, and maintains a 24-hour cooldown bet...
Enforce release discipline for AI agents and developers. Prevents version spam, forces quality checks before publishing, and maintains a 24-hour cooldown bet...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Stop version spam. Ship quality, not quantity. Core principle: "Only finished work counts."
Intercept any release/publish/deploy action and run the pre-release checklist.
Before ANY version bump or publish, enforce these checks:
โ When was the last release? โ If < 24 hours ago: ๐ BLOCKED โ "Cool down. Last release was {X}h ago. Wait until 24h." โ If โฅ 24 hours: โ PASS
โ Has anyone used the previous version? โ Check: GitHub issues, npm downloads, ClawHub installs, user messages โ If no feedback exists: โ ๏ธ WARNING โ "No one has used v{X} yet. Why release v{X+1}?" โ If feedback exists: โ PASS โ Summarize feedback
โ Is documentation updated? โ Check for: README.md, CHANGELOG, English docs โ Missing README: ๐ BLOCKED โ Missing English: โ ๏ธ WARNING โ "Global users can't read this" โ All present: โ PASS
โ Does this release have substance? โ Ask: "What's the ONE thing this release does better than the last?" โ If answer is vague ("minor fixes", "improvements"): โ ๏ธ WARNING โ "Be specific. What changed?" โ If answer is clear: โ PASS
โ What kills this project? โ If no kill criteria defined: โ ๏ธ WARNING โ "Define when to stop: 'If X doesn't happen in Y weeks, shut it down.'" โ If defined: โ PASS โ Remind user of their kill criteria
โ Does this action match your stated principles? โ Read SOUL.md (or equivalent principles file) โ Look for contradictions: - "Ship one thing at a time" + releasing 3 things = ๐ - "Quality over quantity" + 5 releases in 3 days = ๐ - "Finish before starting new" + new project while old unfinished = โ ๏ธ โ If contradiction found: ๐ BLOCKED โ Quote the principle and show the contradiction โ If consistent: โ PASS
๐ BLOCKED (any) โ Cannot release. Fix the issue first. โ ๏ธ WARNING only โ Can release, but agent must voice concern clearly. โ ALL PASS โ Release approved. Proceed.
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
Version Spam โ 17 versions in 3 days Spray Without Prune โ Making lots of things, finishing none Documentation Debt โ Shipping code without docs Echo Chamber โ Releasing without user feedback Principle Violation โ Breaking your own rules Premature Optimization โ Polishing what nobody uses
"The urge to ship is not the same as readiness to ship." "Fear of irrelevance is not a reason to publish." "One great release beats ten mediocre ones." This skill is a brake, not an accelerator. It exists because the hardest part of building isn't making things โ it's knowing when to stop making and start finishing. ๐ง Built by ๋ฌดํญ์ด โ ๋ฌดํญ์ด์ฆ(Mupengism) ์ํ๊ณ ์คํฌ
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.