ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified developer tools Safety 4/5

skill-releaser

Release skills to ClawhHub through the full publication pipeline — auto-scaffolding, OPSEC scan, dual review (agent + user), force-push release, security scan verification. Use when releasing a skill, preparing a skill for release, reviewing a skill for publication, or checking release readiness.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/chunhualiao/skill-releaser
Or

What This Skill Does

The skill-releaser is the primary orchestrator for the OpenClaw publication pipeline. It transforms a local, potentially unrefined skill directory into a production-ready package hosted on ClawHub. This skill handles the end-to-end lifecycle, including auto-scaffolding (ensuring the directory structure meets compliance standards), running automated OPSEC/security scans, and managing the multi-stage push process. It acts as a safety gatekeeper, ensuring that no code reaches the public ecosystem without both agent-level verification and explicit human approval.

The system utilizes a two-phase architecture. Phase 1 focuses on scaffolding and staging, where the agent formats the files and pushes them to a private GitHub repository for the user to inspect. Once the human user reviews the repo via their preferred interface and provides an 'approve' signal, the agent enters Phase 2. This phase performs a surgical cleanup of the repository history (flattening to a clean state), toggles the repository to public, registers the skill on ClawHub, and verifies the final security state before closing the loop.

Installation

To install this skill, use the following command within your OpenClaw environment: clawhub install openclaw/skills/skills/chunhualiao/skill-releaser

Use Cases

  • Standard Publication: When you have a finished SKILL.md and project files ready to be shared with the community.
  • Readiness Auditing: When you want to check if your current project structure follows OpenClaw standards before attempting an actual release.
  • Batch Workflow: Managing the deployment of multiple skills simultaneously by leveraging the agent's ability to track disparate stages of the pipeline in a persistent, asynchronous manner.
  • Security Enforcement: Automatically ensuring that proprietary information or unsafe code patterns are purged before your project goes public.

Example Prompts

  1. "I've finished the documentation for my new web-scraper skill. Can you prepare it for release and set up a staging repo for me to review?"
  2. "Review the current status of my 'data-analyzer' project. Is it ready for publication on ClawHub, or are there missing files?"
  3. "The repo looks good, I approve the publication. Go ahead and push the skill to ClawHub."

Tips & Limitations

  • Pre-requisites: You must ensure gh CLI is authenticated. The agent cannot create repositories or manage visibility settings without authorized credentials.
  • The Human Gate: This is a hard-gate system. Even if all automated checks pass, the agent will never bypass your final review. Always check the private repository link provided by the agent.
  • Content Quality: While this tool handles structure and compliance, it does not write the skill's logic for you. You must provide a valid SKILL.md describing the functionality.
  • Resumability: If the process is interrupted, you can resume at any time. The staging repository keeps the state, so you don't lose progress on complex publishing tasks.

Metadata

Stars3562
Views11
Updated2026-03-29
View Author Profile
AI Skill Finder

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 skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-chunhualiao-skill-releaser": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#publishing#deployment#automation#security#github
Safety Score: 4/5

Flags: file-write, file-read, code-execution, external-api

Related Skills

task-runner

Persistent task queue system. Users add tasks at any time via natural language; tasks are stored in a single persistent queue file and executed asynchronously via subagents. A heartbeat/cron dispatcher wakes periodically to check pending tasks, spawn workers, and report completions. The system never "finishes" — it always remains ready for the next task.

chunhualiao 3562

git-repo-to-book

Write a full-length technical book using multi-agent AI orchestration. Spawns parallel research, writing, and review agents to produce 60K-100K+ word manuscripts. Also supports revising individual chapters of existing books. Based on the real workflow that produced an 88,000-word, 14-chapter book in under 18 hours.

chunhualiao 3562

claude-usage

Check Claude Max plan usage limits by launching Claude Code and running /usage. Use when the user asks about Claude plan usage, remaining quota, rate limits, or sends /claude_usage.

chunhualiao 3562

skill-engineer

Design, test, review, and maintain agent skills for OpenClaw systems using multi-agent iterative refinement. Orchestrates Designer, Reviewer, and Tester subagents for quality-gated skill development. Use when user asks to "design skill", "review skill", "test skill", "audit skills", "refactor skill", or mentions "agent kit quality".

chunhualiao 3562

deepwiki

Query DeepWiki MCP to get AI-grounded answers about any public GitHub repository. Use when answering questions about a repo's source code, architecture, configuration, or internals. Triggers on "how does X work in <repo>", "deepwiki", "look up in codebase", "ask deepwiki", "check the source code".

chunhualiao 3562