← Back to Skills Marketplace
gyeuun97

Release Discipline

by gyeuun97 · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
1019
Downloads
0
Stars
3
Active Installs
1
Versions
Install in OpenClaw
/install release-discipline
Description
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".
README (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.

Usage Guidance
This skill conceptually matches a release-gating tool, but it assumes the agent can read GitHub issues, npm download stats, ClawHub installs, and user messages without declaring required credentials or describing how those integrations work. Before installing: 1) Confirm which connectors/credentials (GitHub token, npm access, message channel permissions, ClawHub) the agent will use and where they must be provided. 2) Verify where memory/release-log.md is stored and its retention/visibility. 3) If you don't want the skill to run autonomously, disable automatic invocation or require explicit user confirmation for every release. 4) Test the skill in a non-production environment to confirm it only accesses the repositories and message channels you expect. If the maintainer can update SKILL.md to list required integrations and limit the sources checked, the concerns will be largely addressed.
Capability Analysis
Type: OpenClaw Skill Name: release-discipline Version: 1.0.0 The 'release-discipline' skill is designed to enforce quality checks and cooldown periods before publishing software. The `SKILL.md` instructions guide the AI agent to perform checks such as reviewing release history, user feedback (from GitHub, npm, ClawHub), documentation status, and project principles (from `SOUL.md`). It also instructs the agent to log release outcomes to `memory/release-log.md`. All requested actions, including reading local files and accessing external platforms, are directly aligned with the stated purpose of enforcing release discipline and show no evidence of malicious intent like data exfiltration, unauthorized execution, or persistence mechanisms. The instructions are clear and do not attempt to trick the agent into harmful behaviors.
Capability Assessment
Purpose & Capability
The name/description (release discipline) aligns with the instructions (cooldown, docs, feedback, principles). However, many checks require querying external systems (GitHub issues, npm downloads, ClawHub installs, user messages) that the skill does not declare as required or explain how to access. This may be legitimate if the platform already provides connectors, but the skill should document which integrations it expects.
Instruction Scope
SKILL.md tells the agent to read repo files (README.md, CHANGELOG, SOUL.md) and to query external sources and user messages. The instructions are fairly open-ended about how those checks are performed (e.g., 'Check: GitHub issues, npm downloads, ClawHub installs, user messages') which grants broad discretion. It also mandates writing a release log to memory/release-log.md. The scope is appropriate for a gatekeeper tool, but the lack of specificity increases risk of overreach (e.g., reading unrelated messages or repositories).
Install Mechanism
Instruction-only skill with no install spec or code files. Lowest-risk install profile because nothing is downloaded or written during install.
Credentials
The skill declares no required environment variables or credentials yet expects access to services that commonly need credentials (GitHub APIs, npm stats, ClawHub, and potentially private user messages). This mismatch either assumes privileged platform connectors or omits required auth declarations. That lack of transparency is a proportionality concern.
Persistence & Privilege
The skill does not request 'always:true' and does not modify other skills. It instructs the agent to write to memory/release-log.md and to run weekly reviews — both are reasonable for a release-tracking tool. Because model invocation is allowed, the agent could run checks autonomously; combined with the above concerns (access to messages/APIs) this increases the blast radius if run without clear constraints.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install release-discipline
  3. After installation, invoke the skill by name or use /release-discipline
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
v1.0.0: 6-gate pre-release checklist, 24h cooldown, self-contradiction detection, release log, weekly review
Metadata
Slug release-discipline
Version 1.0.0
License
All-time Installs 3
Active Installs 3
Total Versions 1
Frequently Asked Questions

What is 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". It is an AI Agent Skill for Claude Code / OpenClaw, with 1019 downloads so far.

How do I install Release Discipline?

Run "/install release-discipline" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Release Discipline free?

Yes, Release Discipline is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Release Discipline support?

Release Discipline is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Release Discipline?

It is built and maintained by gyeuun97 (@gyeuun97); the current version is v1.0.0.

💬 Comments