Kiro is an agentic IDE and CLI tool developed by Amazon that enables Spec-Driven Development and highly automated agent workflows.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install kiro
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 kiro 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 Kiro Development Workflow?
Kiro represents a shift toward agentic software engineering by combining a specialized IDE with a powerful CLI. It centers on the philosophy of Spec-Driven Development (SDD), where developers and AI agents collaborate on structured Markdown specifications to ensure requirements are fully understood before a single line of code is written. By integrating Openclaw Skills, Kiro allows for a seamless transition from prototyping to production through deep context awareness and extensible automation.
The platform's power lies in its ability to understand not just code, but the intent behind it. Through the use of steering files and hooks, Kiro provides a framework where the AI agent acts as a true collaborator, adhering to project-specific rules and triggering automated tasks based on developer actions. This ensures that high-quality, standardized code is produced consistently across the entire development lifecycle.
Kiro Development Workflow Use Cases
- Orchestrating complex feature development using structured specifications and task decomposition.
- Automating repetitive development tasks like formatting and unit testing through event-driven hooks.
- Enforcing architectural standards and project-specific coding styles using steering rules.
- Connecting the AI agent to external data sources and tools like GitHub via the Model Context Protocol.
- Scaling development velocity by delegating implementation tasks to an agent that understands the full project context.
How Kiro Development Workflow Works
- Initialize a Spec to define high-level requirements and acceptance criteria in a structured format.
- Collaborate with the Kiro agent to refine the technical design and architecture within the spec documents.
- Automatically generate a detailed task list that breaks down the implementation into manageable steps.
- Execute tasks using the Agentic Chat, which implements code while following project-specific steering rules.
- Trigger automated hooks on file changes to validate the implementation and ensure continuous quality.
Kiro Development Workflow Setup
Kiro can be used as a standalone desktop application or via the command line. To get started with the CLI and Openclaw Skills integration, use the following steps:
# Install the Kiro CLI via npm
npm install -g @kiro/cli
# Create a new specification for a feature
kiro spec create "your-feature-name"
After installation, configure your environment by creating a .kiro directory in your project root to house your hooks, steering rules, and MCP configurations.
Kiro Development Workflow Data Schema & Taxonomy
Kiro uses a structured file-based system to manage agent context and automation logic. This organization allows Openclaw Skills to effectively manage project state:
| Component | Path | Format | Description |
|---|---|---|---|
| Specs | .kiro/specs/ |
Markdown | Contains requirements.md, design.md, and tasks.md. |
| Steering | .kiro/steering/ |
Markdown | Rules for code style, tech stack, and project context. |
| Hooks | .kiro/hooks.yaml |
YAML | Definitions for automated triggers on file events. |
| MCP Config | .kiro/mcp.json |
JSON | Configuration for Model Context Protocol servers. |
Kiro Development Workflow Advanced Features
- Multi-agent support through Model Context Protocol (MCP) server integration for external tool access.
- Domain-specific capability expansion using Powers for specialized library or framework knowledge.
- Event-driven automation pipeline that triggers custom actions on file saves or git events.
- Context-aware Agentic Chat that references specs and steering rules to minimize hallucinations.
- Seamless migration path for existing VS Code environments, including extensions and settings.
SKILL.md
Loading
Related Openclaw Skills
pdf2ofd: High-Fidelity PDF to OFD Converter
A specialized skill for converting PDFs to the Chinese National Standard OFD format with character-level precision and transparency support.
Variant Design
Transform prompts into three distinct UI design variations using a professional design system and anti-AI-slop quality gates.
Tavily Search
A high-performance web search skill that leverages the Tavily API to provide AI agents with real-time web results and concise summaries.
Tavily Search Skill
A high-performance search engine integration specifically designed to provide AI agents with structured, LLM-ready web data and deep research capabilities.
Intelligent Content Summary & Project Review
An automated utility for generating intelligent summaries and performing comprehensive project post-mortems across multiple content types.
FusionBench
FusionBench is a powerful benchmark and toolkit designed for deep model fusion, supporting over 30 merging algorithms for LLMs and vision models.
Featured*
