A continuous delivery orchestration skill that automates PingCode work item resolution, branching, merge requests, code reviews, and reporting.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install e2e-delivery
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install e2e-delivery using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The e2e-delivery driver is designed to streamline the software development and release pipeline. By taking a PingCode work item URL, ID, or a natural language description, it manages five main execution phases: preparation, development, submission, verification, and delivery. It functions as a stateful orchestrator that continuously updates local session files using dedicated Python scripts to prevent data loss or flow corruption. It offers structured assistance for developers looking to automate repetitive Git and project management operations.
Integrating with Openclaw Skills, this automation engine reduces manual overhead by automatically initiating branching, checking local builds, creating merge requests, and validating merge conditions. The process handles human intervention points with non-blocking waiting states, guaranteeing that code reviews and deployment checkpoints are respected before finalizing delivery.
Ensure that ee-cli, hi, and git are installed on your system. To use this with other Openclaw Skills, check your local configuration file:
# Check status or perform SSO login
ee-cli login
# Configure REDoc integration properties
cat <<EOF > ~/.claude/e2e-delivery/config.json
{
"redocParentId": "YOUR_REDOC_PARENT_PAGE_ID"
}
EOF
The orchestration processes run autonomously, triggering sub-skills like pingcode-assistant-pro or hi-docs when necessary.
The execution state is managed via a JSON session file located at ~/.claude/e2e-sessions/<workitem-id>.json. All file updates must be handled by scripts/session.py to preserve automatic field population (e.g., durationMs, updatedAt).
| Location | File Pattern | Purpose |
|---|---|---|
| Session Records | ~/.claude/e2e-sessions/<workitem-id>.json |
Maintains execution phase and state history |
| Local Reports | docs/e2e-reports/<workitem-id>-<yyyymmdd>.md |
Markdown delivery report compiled upon success |
| Configuration | ~/.claude/e2e-delivery/config.json |
Global settings such as REDoc parent ID |
Loading
A comprehensive command-line interface and MCP server to orchestrate Scrapfly scraping, automated rendering, screenshots, and remote CDP browser sessions.

Ghost Eye functions as an image preprocessing bridge, converting visual data into rich OCR text and scene descriptions for pure-text LLMs.

A set of architectural principles for coordinating stateless scraping and stateful Cloud Browser interactions using a connected Scrapfly MCP server.

An AI-powered log aggregation and anomaly detection tool for live monitoring of Kubernetes namespace pods.

A diagnostic utility that binary-searches multipart part-count limits to identify upload thresholds and prevent HTTP 413 errors.

Convert SVG content, geographic maps, and Chinese character stroke orders into fully editable PowerPoint presentations.








































