← 返回 Skills 市场
mupengi-bot

Release Discipline

作者 mupengi-bot · GitHub ↗ · v1.0.0
cross-platform ✓ 安全检测通过
515
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install mupeng-release-discipline
功能描述
Enforce release discipline for AI agents and developers. Prevents version spam, forces quality checks before publishing, and maintains a 24-hour cooldown bet...
使用说明 (SKILL.md)

🛑 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 \x3C 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

  1. Version Spam — 17 versions in 3 days
  2. Spray Without Prune — Making lots of things, finishing none
  3. Documentation Debt — Shipping code without docs
  4. Echo Chamber — Releasing without user feedback
  5. Principle Violation — Breaking your own rules
  6. Premature Optimization — Polishing what nobody uses

Philosophy

"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 — it's knowing when to stop making and start finishing.


🐧 Built by 무펭이무펭이즘(Mupengism) 생태계 스킬

安全使用建议
This instruction-only skill is coherent with its stated goal of gating releases and logging outcomes. Before installing or enabling autonomous enforcement, check: 1) how the agent will access external signals (GitHub issues, npm download counts, 'ClawHub installs', and user messages) — do you need to provide tokens or grant platform permissions? 2) where memory/release-log.md is stored and who can read it (sensitive info could end up in logs); and 3) whether you want the agent to 'intercept' release actions automatically or only run the checklist when explicitly invoked. If you want stricter assurances, request the author to document required API scopes, exact triggers, and the storage location/retention policy for the release log.
功能分析
Type: OpenClaw Skill Name: mupeng-release-discipline Version: 1.0.0 The skill 'release-discipline' is designed to enforce quality checks and cooldowns before publishing new versions. All instructions within SKILL.md, including reading project documentation (README.md, CHANGELOG, SOUL.md), checking external platforms (GitHub, npm, ClawHub), and logging release events to `memory/release-log.md`, are directly aligned with its stated purpose. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts designed to subvert the agent for harmful purposes. The file and network access capabilities are functional requirements for the skill's legitimate operation.
能力评估
Purpose & Capability
Name and description match the instructions: the SKILL enforces pre-release gates (cooldown, feedback, docs, quality, kill criteria, principle checks) and logs outcomes. The requested actions (reading README/CHANGELOG/SOUL.md, summarizing feedback, writing a release-log) are appropriate for a release-discipline tool. One minor mismatch: the checklist asks the agent to check external signals (GitHub issues, npm downloads, ClawHub installs, user messages) but the skill declares no credentials or APIs—this may be because it expects the platform/agent to already provide access.
Instruction Scope
The SKILL.md stays within release-related scope (project files, user feedback, logging). However the instructions are high-level and leave implementation details to the agent (e.g., how to 'check GitHub issues' or 'summarize user messages'), which grants broad discretion. It also instructs 'Intercept any release/publish/deploy action'—as an instruction for the agent this is fine, but there is no concrete trigger mechanism described.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest-risk installation surface (nothing written to disk by an installer).
Credentials
The skill declares no required environment variables or credentials, which is consistent with being instruction-only. That said, it expects access to external signals (GitHub, npm, ClawHub, user messages) that in practice may require tokens or platform permissions; the skill does not request or document these, so you should confirm how the agent will obtain that access before enabling automatic enforcement.
Persistence & Privilege
always:false (no forced inclusion). The skill asks to write to memory/release-log.md — writing its own log is reasonable and scoped to the skill. It does not request changes to other skills or system-wide config.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install mupeng-release-discipline
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /mupeng-release-discipline 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Enforce release quality: version spam prevention, 24h cooldown, quality gates
元数据
Slug mupeng-release-discipline
版本 1.0.0
许可证
累计安装 1
当前安装数 1
历史版本数 1
常见问题

Release Discipline 是什么?

Enforce release discipline for AI agents and developers. Prevents version spam, forces quality checks before publishing, and maintains a 24-hour cooldown bet... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 515 次。

如何安装 Release Discipline?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install mupeng-release-discipline」即可一键安装,无需额外配置。

Release Discipline 是免费的吗?

是的,Release Discipline 完全免费(开源免费),可自由下载、安装和使用。

Release Discipline 支持哪些平台?

Release Discipline 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Release Discipline?

由 mupengi-bot(@mupengi-bot)开发并维护,当前版本 v1.0.0。

💬 留言讨论