All skills
Skillintermediate

Everything Claude Code for Kiro

Bring [Everything Claude Code](https://github.com/anthropics/courses/tree/master/everything-claude-code) (ECC) workflows to [Kiro](https://kiro.dev). This repository provides custom agents, skills, hooks, steering files, and scripts that can be installed into any Kiro project with a single command.

Claude Code Knowledge Pack7/10/2026

Overview

Everything Claude Code for Kiro

Bring Everything Claude Code (ECC) workflows to Kiro. This repository provides custom agents, skills, hooks, steering files, and scripts that can be installed into any Kiro project with a single command.

Quick Start

# Go to .kiro folder
cd .kiro

# Install to your project
./install.sh /path/to/your/project

# Or install to the current directory
./install.sh

# Or install globally (applies to all Kiro projects)
./install.sh ~

The installer uses non-destructive copy — it will not overwrite your existing files.

Component Inventory

ComponentCountLocation
Agents (JSON)16.kiro/agents/*.json
Agents (MD)16.kiro/agents/*.md
Skills18.kiro/skills/*/SKILL.md
Steering Files16.kiro/steering/*.md
IDE Hooks10.kiro/hooks/*.kiro.hook
Scripts2.kiro/scripts/*.sh
MCP Examples1.kiro/settings/mcp.json.example
Documentation5docs/*.md

What's Included

Agents

Agents are specialized AI assistants with specific tool configurations.

Format:

  • IDE: Markdown files (.md) - Access via automatic selection or explicit invocation
  • CLI: JSON files (.json) - Access via /agent swap command

Both formats are included for maximum compatibility.

Note: Agent models are determined by your current model selection in Kiro, not by the agent configuration.

AgentDescription
plannerExpert planning specialist for complex features and refactoring. Read-only tools for safe analysis.
code-reviewerSenior code reviewer ensuring quality and security. Reviews code for CRITICAL security issues, code quality, React/Next.js patterns, and performance.
tdd-guideTest-Driven Development specialist enforcing write-tests-first methodology. Ensures 80%+ test coverage with comprehensive test suites.
security-reviewerSecurity vulnerability detection and remediation specialist. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
architectSoftware architecture specialist for system design, scalability, and technical decision-making. Read-only tools for safe analysis.
build-error-resolverBuild and TypeScript error resolution specialist. Fixes build/type errors with minimal diffs, no architectural changes.
doc-updaterDocumentation and codemap specialist. Updates codemaps and documentation, generates docs/CODEMAPS/*, updates READMEs.
refactor-cleanerDead code cleanup and consolidation specialist. Removes unused code, duplicates, and refactors safely.
go-reviewerGo code review specialist. Reviews Go code for idiomatic patterns, error handling, concurrency, and performance.
python-reviewerPython code review specialist. Reviews Python code for PEP 8, type hints, error handling, and best practices.
database-reviewerDatabase and SQL specialist. Reviews schema design, queries, migrations, and database security.
e2e-runnerEnd-to-end testing specialist. Creates and maintains E2E tests using Playwright or Cypress.
harness-optimizerTest harness optimization specialist. Improves test performance, reliability, and maintainability.
loop-operatorVerification loop operator. Runs comprehensive checks and iterates until all pass.
chief-of-staffExecutive assistant for project management, coordination, and strategic planning.
go-build-resolverGo build error resolution specialist. Fixes Go compilation errors, dependency issues, and build problems.

Usage in IDE:

  • You can run an agent in / in a Kiro session, e.g., /code-reviewer.
  • Kiro's Spec session has native planner, designer, and architects that can be used instead of planner and architect agents.

Usage in CLI:

  1. Start a chat session
  2. Type /agent swap to see available agents
  3. Select an agent to switch (e.g., code-reviewer after writing code)
  4. Or start with a specific agent: kiro-cli --agent planner

Skills

Skills are on-demand workflows invocable via the / menu in chat.

SkillDescription
tdd-workflowEnforces test-driven development with 80%+ coverage including unit, integration, and E2E tests. Use when writing new features or fixing bugs.
coding-standardsUniversal coding standards and best practices for TypeScript, JavaScript, React, and Node.js. Use when starting projects, reviewing code, or refactoring.
security-reviewComprehensive security checklist and patterns. Use when adding authentication, handling user input, creating API endpoints, or working with secrets.
verification-loopComprehensive verification system that runs build, type check, lint, tests, security scan, and diff review. Use after completing features or before creating PRs.
api-designRESTful API design patterns and best practices. Use when designing new APIs or refactoring existing endpoints.
frontend-patternsReact, Next.js, and frontend architecture patterns. Use when building UI components or optimizing frontend performance.
backend-patternsNode.js, Express, and backend architecture patterns. Use when building APIs, services, or backend infrastructure.
e2e-testingEnd-to-end testing with Playwright or Cypress. Use when adding E2E tests or improving test coverage.
golang-patternsGo idioms, concurrency patterns, and best practices. Use when writing Go code or reviewing Go projects.
golang-testingGo testing patterns with table-driven tests and benchmarks. Use when writing Go tests or improving test coverage.
python-patternsPython idioms, type hints, and best practices. Use when writing Python code or reviewing Python projects.
python-testingPython testing with pytest and coverage. Use when writing Python tests or improving test coverage.
database-migrationsDatabase schema design and migration patterns. Use when creating migrations or refactoring database schemas.
postgres-patternsPostgreSQL-specific patterns and optimizations. Use when working with PostgreSQL databases.
docker-patternsDocker and containerization best practices. Use when creating Dockerfiles or optimizing container builds.
deployment-patternsDeployment strategies and CI/CD patterns. Use when setting up deployments or improving CI/CD pipelines.
search-firstSearch-first development methodology. Use when exploring unfamiliar codebases or debugging issues.
agentic-engineeringAgentic software engineering patterns and workflows. Use when working with AI agents or building agentic systems.

Usage:

  1. Type / in chat to open the skills menu
  2. Select a skill (e.g., tdd-workflow when starting a new feature, security-review when adding auth)
  3. The agent will guide you through the workflow with specific instructions and checklists

Note: For planning complex features, use the planner agent instead (see Agents section above).

Steering Files

Steering files provide always-on rules and context that shape how the agent works with your code.

FileInclusionDescription
coding-style.mdautoCore coding style rules: immutability, file organization, error handling, and code quality standards. Loaded in every conversation.
security.mdautoSecurity best practices including mandatory checks, secret management, and security response protocol. Loaded in every conversation.
testing.mdautoTesting requirements: 80% coverage minimum, TDD workflow, and test types (unit, integration, E2E). Loaded in every conversation.
development-workflow.mdautoDevelopment process, PR workflow, and collaboration patterns. Loaded in every conversation.
git-workflow.mdautoGit commit conventions, branching strategies, and version control best practices. Loaded in every conversation.
patterns.mdautoCommon design patterns and architectural principles. Loaded in every conversation.
performance.mdautoPerformance optimization guidelines and profiling strategies. Loaded in every conversation.
lessons-learned.mdautoProject-specific patterns and learnings. Edit this file to capture your team's conventions. Loaded in every conversation.
typescript-patterns.mdfileMatch: *.ts,*.tsxTypeScript-specific patterns, type safety, and best practices. Loaded when editing TypeScript files.
python-patterns.mdfileMatch: *.pyPython-specific patterns, type hints, and best practices. Loaded when editing Python files.
golang-patterns.mdfileMatch: *.goGo-specific patterns, concurrency, and best practices. Loaded when editing Go files.
swift-patterns.mdfileMatch: *.swiftSwift-specific patterns and best practices. Loaded when editing Swift files.
dev-mode.mdmanualDevelopment context mode. Invoke with #dev-mode for focused development.
review-mode.mdmanualCode review context mode. Invoke with #review-mode for thorough reviews.
research-mode.mdmanualResearch context mode. Invoke with #research-mode for exploration and learning.

Steering files with auto inclusion are loaded automatically. No action needed — they apply as soon as you install them.

To create your own, add a markdown file to .kiro/steering/ with YAML frontmatter:

---
inclusion: auto        # auto | fileMatch | manual
description: Brief explanation of what this steering file contains
fileMatchPattern: "*.ts"  # required if inclusion is fileMatch
---

Your rules here...

Hooks

Kiro supports two types of hooks:

  1. IDE Hooks - Standalone JSON files in .kiro/hooks/ (for Kiro IDE)
  2. CLI Hooks - Embedded in agent configurations (for kiro-cli)

IDE Hooks (Standalone Files)

These hooks appear in the Agent Hooks panel in the Kiro IDE and can be toggled on/off. Hook files use the .kiro.hook extension.

HookTriggerActionDescription
quality-gateManual (userTriggered)runCommandRuns build, type check, lint, and tests via quality-gate.sh. Click to trigger comprehensive quality checks.
typecheck-on-editFile edited (*.ts, *.tsx)askAgentChecks for type errors when TypeScript files are edited to catch issues early.
console-log-checkFile edited (*.js, *.ts, *.tsx)askAgentChecks for console.log statements to prevent debug code from being committed.
tdd-reminderFile created (*.ts, *.tsx)askAgentReminds you to write tests first when creating new TypeScript files.
git-push-reviewBefore shell commandaskAgentReviews git push commands to ensure code quality before pushing.
code-review-on-writeAfter write operationaskAgentTriggers code review after file modifications.
auto-formatFile edited (*.ts, *.tsx, *.js)askAgentChecks for formatting issues and fixes them inline without spawning a terminal.
extract-patternsAgent stopsaskAgentSuggests patterns to add to lessons-learned.md after completing work.
session-summaryAgent stopsaskAgentProvides a summary of work completed in the session.
doc-file-warningBefore write operationaskAgentWarns before modifying documentation files to ensure intentional changes.

IDE Hook Format:

{
  "version": "1.0.0",
  "enabled": true,
  "name": "hook-name",
  "description": "What this hook does",
  "when": {
    "type": "fileEdited",
    "patterns": ["*.ts"]
  },
  "then": {
    "type": "runCommand",
    "command": "npx tsc --noEmit"
  }
}

Required fields: version, enabled, name, description, when, then

Available trigger types: fileEdited, fileCreated, fileDeleted, userTriggered, promptSubmit, agentStop, preToolUse, postToolUse

CLI Hooks (Embedded in Agents)

CLI hooks are embedded within agent configuration files for use with kiro-cli.

Example: See .kiro/agents/tdd-guide-with-hooks.json for an agent with embedded hooks.

CLI Hook Format:

{
  "name": "my-agent",
  "hooks": {
    "postToolUse": [
      {
        "matcher": "fs_write",
        "command": "npx tsc --noEmit"
      }
    ]
  }
}

Available triggers: agentSpawn, userPromptSubmit, preToolUse, postToolUse, stop

See .kiro/hooks/README.md for complete documentation on both hook types.

Scripts

Shell scripts used by hooks to perform quality checks and formatting.

ScriptDescription
quality-gate.shDetects your package manager (pnpm/yarn/bun/npm) and runs build, type check, lint, and test commands. Skips checks gracefully if tools are missing.
format.shDetects your formatter (biome or prettier) and auto-formats the specified file. Used by formatting hooks.

Project Structure

.kiro/
├── agents/                       # 16 agents (JSON + MD formats)
│   ├── planner.json              # Planning specialist (CLI)
│   ├── planner.md                # Planning specialist (IDE)
│   ├── code-reviewer.json        # Code review specialist (CLI)
│   ├── code-reviewer.md          # Code review specialist (IDE)
│   ├── tdd-guide.json            # TDD specialist (CLI)
│   ├── tdd-guide.md              # TDD specialist (IDE)
│   ├── security-reviewer.json    # Security specialist (CLI)
│   ├── security-reviewer.md      # Security specialist (IDE)
│   ├── architect.json            # Architecture specialist (CLI)
│   ├── architect.md              # Architecture specialist (IDE)
│   ├── build-error-resolver.json # Build error specialist (CLI)
│   ├── build-error-resolver.md   # Build error specialist (IDE)
│   ├── doc-updater.json          # Documentation specialist (CLI)
│   ├── doc-updater.md            # Documentation specialist (IDE)
│   ├── refactor-cleaner.json     # Refactoring specialist (CLI)
│   ├── refactor-cleaner.md       # Refactoring specialist (IDE)
│   ├── go-reviewer.json          # Go review specialist (CLI)
│   ├── go-reviewer.md            # Go review specialist (IDE)
│   ├── python-reviewer.json      # Python review specialist (CLI)
│   ├── python-reviewer.md        # Python review specialist (IDE)
│   ├── database-reviewer.json    # Database specialist (CLI)
│   ├── database-reviewer.md      # Database specialist (IDE)
│   ├── e2e-runner.json           # E2E testing specialist (CLI)
│   ├── e2e-runner.md             # E2E testing specialist (IDE)
│   ├── harness-optimizer.json    # Test harness specialist (CLI)
│   ├── harness-optimizer.md      # Test harness specialist (IDE)
│   ├── loop-operator.json        # Verification lo