A comprehensive versioned development pipeline that orchestrates AI agents through analysis, coding, review, and deployment stages.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install dev-pipeline
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install dev-pipeline using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Dev Pipeline?
Dev Pipeline is a sophisticated workflow orchestration tool designed to bring rigorous structure to AI-driven software development within the Openclaw Skills ecosystem. It acts as a bridge between high-level project management and low-level code execution by integrating deeply with version-manager and project-manager skills.
By leveraging the advanced reasoning of models like Claude Opus, Dev Pipeline ensures that every development cycle follows a standardized lifecycle: from requirement analysis and architectural planning to iterative coding and automated peer reviews. This skill is essential for developers looking to build maintainable, version-controlled software using AI agents while maintaining high standards for code integrity and documentation.
Dev Pipeline Use Cases
- Implementing a standardized software development lifecycle (SDLC) for AI-driven projects.
- Automating the generation of detailed development plans and SQL schemas from markdown requirements.
- Maintaining strict version control and automated changelogs for iterative feature releases.
- Orchestrating complex coding tasks by offloading heavy-lifting to sub-agents to optimize token usage in Openclaw Skills.
- Enforcing quality gates through automated AI code reviews and iterative bug-fixing loops.
How Dev Pipeline Works
- The user initializes a new version using the init command, which triggers version-manager to prepare the environment and project-manager to update the tracking board.
- The analyze command reads requirements and uses an AI oracle to generate a structured DEV_PLAN.md including task IDs and file output lists.
- Upon user confirmation, the write command invokes the AI to generate or modify source code files according to strict formatting rules.
- The review command performs a technical audit of the new code, assigning quality scores and identifying critical issues or warnings.
- If issues are found, the fix command performs targeted updates based on the review report until the code passes the quality gate.
- Finally, the deploy and seal commands validate code integrity, archive the full version, and finalize the release documentation.
Dev Pipeline Setup
To get started with Dev Pipeline as part of your Openclaw Skills toolkit, follow these steps:
- Create a configuration file at
.dev-pipeline/config.json:
{
"project": {
"name": "your-project-name",
"repo_path": "."
},
"oracle": {
"model": "claude-opus-4-6",
"engine": "op46"
}
}
- Initialize your first version:
dev-pipeline init v1.0.0
- Start the analysis phase:
dev-pipeline analyze
Dev Pipeline Data Schema & Taxonomy
Dev Pipeline maintains project state and documentation through a structured directory and file system:
| File/Path | Description |
|---|---|
.state.json |
The central state machine tracking current version, task ID, and workflow status. |
.dev-pipeline/config.json |
Project-specific settings, including AI model selection and project paths. |
versions/vX.X.X/docs/DEV_PLAN.md |
The AI-generated architectural blueprint and task breakdown. |
versions/vX.X.X/docs/REVIEW_TASK_[ID].md |
Detailed code review reports including quality scores and issue logs. |
REQUIREMENTS.md |
The input document used as the source of truth for the analysis phase. |
Dev Pipeline Advanced Features
- Sub-agent Collaboration: Supports spawning independent worker agents via sessions_spawn to handle heavy AI tasks, keeping the main session context clean and avoiding token overflow in Openclaw Skills.
- Multi-Agent Orchestration: Enables parallel processing of different development tasks by distributing them across multiple sub-agents.
- Integrated Safety Checks: Automatically blocks deployment if file size variances exceed 20% or if version validation fails.
- Persistent Sub-agents: Allows for long-running worker sessions that maintain local context for complex, multi-step feature development.
- Automated Changelog Integration: Syncs directly with project-manager to update kanban boards and release notes in real-time.
SKILL.md
Loading
Related Openclaw Skills
Content Ops Automation System
A comprehensive social media operation system for automated content harvesting, AI-driven redesign, and multi-platform publishing management.
Microsoft 365 Integration
A comprehensive integration allowing AI agents to manage Outlook emails, Microsoft Calendar, OneDrive files, and To Do tasks.
Bring Shopping
A Node.js-powered integration for managing Bring! shopping lists using email and password credentials.
Weather Check
A comprehensive weather data skill providing real-time conditions and multi-day forecasts for any global location via name or coordinates.
Development Task & Versioning Manager
A standardized development task management skill that enforces strict semantic versioning and mandatory project archiving to prevent code loss.
Dev Workflow
A unified automation orchestrator that manages the end-to-end development lifecycle from initial setup to final version sealing.
Featured*
