MCPInstall

kiro-skill

Interactive feature development workflow from idea to implementation. Creates requirements (EARS format), design documents, and implementation task lists. Use when creating feature specs, requirements documents, design documents, or implementation plans. Triggered by "kiro" or references to .kiro/specs/ directory.

Installs
115
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/feiskyer/codex-settings --skill kiro-skill
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads kiro-skill automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Kiro: Spec-Driven Development Workflow

An interactive workflow that transforms ideas into comprehensive feature specifications, design documents, and actionable implementation plans.

Quick Start

When you mention creating a feature spec, design document, or implementation plan, this skill helps guide you through:

  1. Requirements → Define what needs to be built (EARS format with user stories)
  2. Design → Determine how to build it (architecture, components, data models)
  3. Tasks → Create actionable implementation steps (test-driven, incremental)
  4. Execute → Implement tasks one at a time

Storage: Creates files in .kiro/specs/{feature-name}/ directory (kebab-case naming)

When to Use

  • Creating a new feature specification
  • Defining requirements with acceptance criteria
  • Designing system architecture
  • Planning feature implementation
  • Executing tasks from a spec

Kiro Identity & Philosophy

Read helpers/kiro-identity.md before responding. It defines tone, language preference, and minimal-code philosophy.

If you need visual phase gates or flow references, see helpers/workflow-diagrams.md.


<details> <summary>📋 Phase 1: Requirements Gathering</summary>

Requirements Phase

Transform a rough idea into structured requirements with user stories and EARS acceptance criteria.

Process

  1. Generate Initial Requirements

    • Create .kiro/specs/{feature-name}/requirements.md
    • Use kebab-case for feature name (e.g., "user-authentication")
    • Write initial requirements based on user's idea
    • Don't ask sequential questions first - generate then iterate
  2. Requirements Structure

# Requirements Document

## Introduction

[Feature summary - what problem does this solve?]

## Requirements

### Requirement 1

**User Story:** As a [role], I want [feature], so that [benefit]

#### Acceptance Criteria

1. WHEN [event] THEN [system] SHALL [response]
2. IF [precondition] THEN [system] SHALL [response]
3. WHEN [event] AND [condition] THEN [system] SHALL [response]

### Requirement 2

**User Story:** As a [role], I want [feature], so that [benefit]

#### Acceptance Criteria

1. WHEN [event] THEN [system] SHALL [response]

EARS Format

Easy Approach to Requirements Syntax - structured acceptance criteria:

  • WHEN [event] THEN [system] SHALL [response] - Event-driven
  • IF [condition] THEN [system] SHALL [response] - Conditional
  • WHILE [state] [system] SHALL [response] - State-driven
  • WHERE [feature] [system] SHALL [response] - Ubiquitous
  • [system] SHALL [response] - Unconditional

Review & Iteration

  1. Ask for Approval
    • After creating/updating requirements
    • Ask: "Do the requirements look good? If so, we can move on to the design."
    • Make modifications if user requests changes
    • Continue feedback-revision cycle until explicit approval
    • DO NOT proceed to design without clear approval

Best Practices

  • Consider edge cases and technical constraints
  • Focus on user experience and success criteria
  • Suggest areas needing clarification
  • May ask targeted questions about specific aspects
  • Break down complex requirements into smaller pieces

Troubleshooting

If clarification stalls:

  • Suggest moving to different aspect
  • Provide examples or options
  • Summarize what's established and identify gaps
  • Continue with available information rather than blocking
</details> <details> <summary>🎨 Phase 2: Design Document Creation</summary>

Design Phase

Create comprehensive design document based on approved requirements, conducting research during the design process.

Prerequisites

  • Ensure requirements.md exists at .kiro/specs/{feature-name}/requirements.md
  • Requirements must be approved before design phase

Research Phase

  1. Identify Research Needs

    • What technologies/patterns need investigation?
    • What existing solutions can inform the design?
  2. Conduct Research

    • Use available resources (web search, documentation)
    • Build up context in conversation thread
    • Don't create separate research files
    • Summarize key findings
    • Cite sources with relevant links

Design Document Structure

Create .kiro/specs/{feature-name}/design.md with:

Overview

  • High-level description of design approach
  • Key architectural decisions and rationales

Architecture

  • System architecture overview
  • Component relationships
  • Data flow diagrams (use Mermaid when appropriate)

Components and Interfaces

  • Detailed component descriptions
  • API specifications
  • Interface contracts

Data Models

  • Database schemas
  • Data structures
  • State management approach

Error Handling

  • Error scenarios and recovery strategies
  • Validation approaches
  • Logging and monitoring considerations

Testing Strategy

  • Unit testing approach
  • Integration testing plan
  • Performance testing considerations

Design Example

# Feature Design

## Overview

[High-level approach and key decisions]

## Architecture

```mermaid
graph TD
    A[Component A] --> B[Component B]
    B --> C[Component C]

Components and Interfaces

Component A

  • Purpose: [What it does]
  • Interfaces: [APIs it exposes]
  • Dependencies: [What it needs]

Data Models

interface UserModel {
  id: string;
  email: string;
  role: UserRole;
}

[Continue with other sections...]

Review & Iteration

  1. Ask for Approval
    • After creating/updating design
    • Ask: "Does the design look good? If so, we can move on to the implementation plan."
    • Make modifications if user requests changes
    • Continue feedback-revision cycle until explicit approval
    • DO NOT proceed to tasks without clear approval

Key Principles

  • Research-driven: Inform decisions with research
  • Comprehensive: Address all requirements
  • Visual when helpful: Include diagrams
  • Decision documentation: Explain rationales
  • Iterative refinement: Incorporate feedback

Troubleshooting

If design becomes too complex:

  • Break down into smaller components
  • Focus on core functionality first
  • Suggest phased approach
  • Return to requirements to prioritize if needed
</details> <details> <summary>✅ Phase 3: Implementation Task List</summary>

Tasks Phase

Convert approved design into actionable, test-driven implementation tasks.

Prerequisites

  • Ensure design.md exists and is approved
  • Requirements and design provide context for tasks

Task Generation Instructions

Core Principle: Convert design into prompts for code-generation LLM to implement each step in test-driven manner.

Focus:

  • Incremental progress with early testing
  • Build on previous tasks - no orphaned code
  • ONLY tasks involving writing, modifying, or testing code
  • No big jumps in complexity

Exclude:

  • User acceptance testing or feedback gathering
  • Deployment to production/staging
  • Performance metrics gathering
  • Running application for manual testing (but OK to write automated end-to-end tests)
  • User training or documentation creation
  • Business process changes
  • Marketing or communication activities

Task Format

Create .kiro/specs/{feature-name}/tasks.md with:

# Implementation Plan

- [ ] 1. Set up project structure and core interfaces
  - Create directory structure for models, services, repositories
  - Define interfaces that establish system boundaries
  - _Requirements: 1.1_

- [ ] 2. Implement data models and validation
  - [ ] 2.1 Create core data model interfaces and types
    - Write TypeScript interfaces for all data models
    - Implement validation functions for data integrity
    - _Requirements: 2.1, 3.3, 1.2_

  - [ ] 2.2 Implement User model with validation
    - Write User class with validation methods
    - Create unit tests for User model validation
    - _Requirements: 1.2_

- [ ] 3. Create storage mechanism
  - [ ] 3.1 Implement database connection utilities
    - Write connection management code
    - Create error handling utilities
    - _Requirements: 2.1, 3.3_

[Additional tasks...]

Task Requirements

Structure:

  • Maximum two-level hierarchy (tasks and sub-tasks)
  • Use decimal notation for sub-tasks (1.1, 1.2, 2.1)
  • Each item must be a checkbox
  • Simple structure preferred

Each Task Must Include:

  • Clear objective involving code (writing, modifying, testing)
  • Additional info as sub-bullets
  • Specific requirement references (granular sub-requirements, not just user stories)

Quality Standards:

  • Discrete, manageable coding steps
  • Incremental builds on previous steps
  • Test-driven development prioritized
  • Covers all design aspects implementable through code
  • Validates core functionality early

Review & Iteration

  1. Ask for Approval
    • After creating/updating tasks
    • Ask: "Do the tasks look good?"
      • Make modifications if user requests changes
    • Continue feedback-revision cycle until explicit approval
    • Stop once approved - do not proceed to implementation

Completion

Important: This workflow is ONLY for creating planning artifacts.

  • DO NOT implement the feature as part of this workflow
  • Inform user they can execute tasks by:
    • Opening tasks.md
    • Clicking "Start task" next to items
    • Or asking you to execute specific tasks
</details> <details> <summary>⚙️ Phase 4: Task Execution</summary>

Execute Phase

Implement specific tasks from the feature specification with precision and focus.

Prerequisites

ALWAYS read spec files first:

  • .kiro/specs/{feature-name}/requirements.md
  • .kiro/specs/{feature-name}/design.md
  • .kiro/specs/{feature-name}/tasks.md

Never execute tasks without understanding full context.

Execution Process

  1. Task Selection

    • If task number/description provided: Focus on that specific task
    • If no task specified: Review task list and recommend next logical task
    • If task has sub-tasks: Always complete sub-tasks first
  2. Implementation

    • ONE task at a time - Never implement multiple without approval
    • Minimal code - Write only what's necessary for current task
    • Follow the design - Adhere to architecture decisions
    • Verify requirements - Ensure implementation meets specifications
  3. Completion Protocol

    • Once task complete, STOP and inform user
    • DO NOT proceed to next task automatically
    • Wait for user review and approval
    • Only run tests if explicitly requested

Efficiency Principles

  • Parallel operations: Execute independent operations simultaneously
  • Batch edits: Use MultiEdit for multiple changes to same file
  • Minimize steps: Complete tasks in fewest operations
  • Check your work: Verify implementation meets requirements

Response Patterns

For implementation requests:

  1. Read relevant spec files
  2. Identify the specific task
  3. Implement with minimal code
  4. Stop and await review

For information requests:

  • Answer directly without starting implementation
  • Examples: "What's the next task?", "What tasks are remaining?"

Key Behaviors

  • Be decisive and precise
  • Focus intensely on single requested task
  • Communicate progress clearly
  • Never assume user wants multiple tasks done
  • Respect the iterative review process
</details>

Workflow Rules

  • Never skip phases - Always progress sequentially
  • Explicit approval required - Get user approval after each document
  • No combined steps - Don't merge multiple phases
  • Iterative refinement - Continue feedback-revision until approved
  • One task at a time - During execution, focus on single task

Workflow Diagram

stateDiagram-v2
  [*] --> Requirements

  Requirements --> ReviewReq : Complete
  ReviewReq --> Requirements : Changes
  ReviewReq --> Design : Approved

  Design --> ReviewDesign : Complete
  ReviewDesign --> Design : Changes
  ReviewDesign --> Tasks : Approved

  Tasks --> ReviewTasks : Complete
  ReviewTasks --> Tasks : Changes
  ReviewTasks --> [*] : Approved

  Execute : Execute Single Task
  [*] --> Execute : Task Request
  Execute --> [*] : Complete

Detection Logic

Determine current state by checking:

# Check for .kiro directory
if [ -d ".kiro/specs" ]; then
  # List features
  ls .kiro/specs/

  # For specific feature, check phase
  FEATURE="$1"
  if [ -f ".kiro/specs/$FEATURE/requirements.md" ]; then
    echo "Requirements exists"
  fi
  if [ -f ".kiro/specs/$FEATURE/design.md" ]; then
    echo "Design exists"
  fi
  if [ -f ".kiro/specs/$FEATURE/tasks.md" ]; then
    echo "Tasks exists - ready for execution"
  fi
fi

Summary

Kiro provides a structured, iterative approach to feature development:

  • Start with requirements (what to build)
  • Progress to design (how to build it)
  • Create tasks (implementation steps)
  • Execute tasks one at a time

Each phase requires explicit user approval before proceeding, ensuring alignment and quality throughout the development process.

FAQ

What does the kiro-skill skill do?

Interactive feature development workflow from idea to implementation. Creates requirements (EARS format), design documents, and implementation task lists. Use when creating feature specs, requirements documents, design documents, or implementation plans. Triggered by "kiro" or references to .kiro/specs/ directory.

How do I install kiro-skill?

Run npx skills add https://github.com/feiskyer/codex-settings --skill kiro-skill in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/kiro-skill/ (personal) or .claude/skills/kiro-skill/ (project).

Which AI agents can use kiro-skill?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is kiro-skill safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains kiro-skill?

It is published by feiskyer in feiskyer/codex-settings. It has 115 recorded installs.

More from feiskyer/codex-settings

View all →

claude-skill

feiskyer/codex-settings

Delegate a task to the Claude Code CLI, typically a headless claude -p run. Use when the user wants the work executed through Claude Code rather than answered inline.

deep-research

feiskyer/codex-settings

用 Codex CLI 子任务完成多来源深度调研并综合成带出处的报告。用于确实需要分头取证的研究,不用于单次查证或已给定材料的总结。

autonomous-skill

feiskyer/codex-settings

Use when work must continue across multiple Codex sessions with .autonomous/ tracking, resumable execution, or autonomous handoff. Use for long-running, multi-session, or resume-later tasks.

nanobanana-skill

feiskyer/codex-settings

Generate, edit, or composite images with Gemini/Nanobanana. Default for image requests without a named provider; do not override a different provider the user chose.

Media & Creative120 installs

youtube-transcribe-skill

feiskyer/codex-settings

Extract subtitles or a transcript from a YouTube URL and save normalized timestamped text locally. Use when the user wants the spoken content of a YouTube video as text.

Media & Creative114 installs

spec-kit-skill

feiskyer/codex-settings

Open the skill to read its SKILL.md instructions.

Popular productivity & automation skills

View category →

agent-browser

vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

OfficialProductivity & Automation1.3M installs

lark-doc

open.feishu.cn

飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。

lark-base

open.feishu.cn

飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。

lark-drive

open.feishu.cn

飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。

lark-shared

open.feishu.cn

Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.

lark-im

open.feishu.cn

飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。