A robust framework for executing complex implementation plans by dispatching fresh AI subagents for every task with a mandatory two-stage review process.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install subagent-driven-development-2
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 subagent-driven-development-2 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 Subagent-Driven Development?
Subagent-Driven Development is a sophisticated workflow designed for Openclaw Skills that prioritizes code integrity and architectural consistency. By isolating each task within a fresh subagent, the system eliminates context pollution and prevents the technical debt often associated with long-running AI sessions. This skill is particularly effective for developers who have a pre-defined implementation plan and need a reliable way to transform that plan into production-grade code without constant human intervention.
The core philosophy centers on specialized roles: an Implementer to write the code, a Spec Reviewer to ensure functional compliance, and a Code Reviewer to enforce maintainability. This multi-layered approach ensures that every change within Openclaw Skills environments is vetted for both compliance and quality before being integrated into the development branch.
Subagent-Driven Development Use Cases
- Executing multi-task implementation plans within a single session without manual handoffs.
- Scaling development through autonomous subagents while maintaining strict architectural standards.
- Implementing features that require Test-Driven Development (TDD) and rigorous code reviews.
- Managing complex refactoring tasks where context isolation is critical to avoid regression.
How Subagent-Driven Development Works
- The controller reads the implementation plan and extracts all tasks into a centralized TodoWrite manifest.
- A fresh Implementer subagent is dispatched for the current task, receiving full architectural context and specific task requirements.
- After implementation and self-review, a Spec Reviewer subagent verifies that the code matches the original specifications exactly.
- Once spec-compliant, a Code Reviewer subagent analyzes the git SHAs to ensure clean code, maintainability, and high test coverage.
- Upon final approval from both reviewers, the task is marked complete, and the controller moves to the next item in the plan.
Subagent-Driven Development Setup
To integrate this skill into your environment, use the following command:
npx clawhub@latest install subagent-driven-development
Ensure you have an implementation plan ready so the Openclaw Skills controller can accurately extract tasks and shared architectural context.
Subagent-Driven Development Data Schema & Taxonomy
The skill manages its workflow through a structured metadata taxonomy and task tracking:
| Component | Description |
|---|---|
| TodoWrite | A centralized file or state object tracking the status of all extracted tasks. |
| Task Context | A payload containing specific requirements, architectural dependencies, and coding conventions. |
| Review Logs | Documentation of spec compliance and code quality approvals per task. |
| Git SHAs | Reference points for reviewers to analyze changes between implementation and review phases. |
Subagent-Driven Development Advanced Features
- Fresh Context Isolation: Automatically resets subagent memory per task to prevent context drift and hallucinations within the Openclaw Skills ecosystem.
- Two-Stage Quality Gates: Mandatory separation of functional verification (spec) and structural verification (quality).
- Automated Re-review Loops: Triggers recursive implementation fixes and reviews until all quality bars are met.
- Cross-Task Analysis: Performs a final holistic review of the entire development branch to ensure inter-task consistency.
SKILL.md
Loading
Related Openclaw Skills
Subagent-Driven Development
A high-precision execution framework that dispatches fresh subagents for independent tasks with automated two-stage review cycles.
Startup Metrics
A comprehensive framework for tracking and optimizing core startup KPIs from Seed through Series A.
shadcn-ui
A comprehensive skill for building accessible, high-performance user interfaces using shadcn/ui, Radix UI, and Tailwind CSS.
Local Testnet Setup for Uniswap
A comprehensive tool to launch a local Anvil testnet forking live chains with pre-deployed Uniswap contracts and multi-token funded accounts.
Submit UniswapX Limit Order
A specialized skill for executing gasless, MEV-protected limit orders via UniswapX Dutch auctions.
Tailwind Design System
A robust framework for building production-ready, type-safe component libraries using Tailwind CSS, CVA, and compound component patterns.
Featured*
