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.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/chunhualiao/skill-releaserWhat 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.mdand 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
- "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?"
- "Review the current status of my 'data-analyzer' project. Is it ready for publication on ClawHub, or are there missing files?"
- "The repo looks good, I approve the publication. Go ahead and push the skill to ClawHub."
Tips & Limitations
- Pre-requisites: You must ensure
ghCLI 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.mddescribing 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
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-chunhualiao-skill-releaser": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution, external-api
Related Skills
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.
save-to-obsidian
Saves markdown content to remote Obsidian vault via SSH
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.
openclaw-docker-setup
Install and configure a fully operational Dockerized OpenClaw instance on macOS from scratch. Includes browser pairing, Discord channel setup, and optional Gmail/Google Drive integration. Use when user asks to "install openclaw docker", "set up dockerized openclaw", "openclaw in docker", or "isolated openclaw instance".
Wechat Article Forge
Skill by chunhualiao