Agent skill

Creating Kiro Agents

by pr-pm in pr-pm/prpm

A skill your agent uses when building custom Kiro AI agents or when user asks for agent configurations - provides JSON structure, tool configuration, prompt patterns, and security best practices for…

MITAuto-check passedAI & LLM Engineering

Install Creating Kiro Agents

skills CLI
$ npx skills add pr-pm/prpm --skill creating-kiro-agents -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install pr-pm/prpm creating-kiro-agents --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/pr-pm/prpm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/creating-kiro-agents .claude/skills/creating-kiro-agents && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
creating-kiro-agents
GitHub stars
122
Used in
1 other repo
Token cost
~1.9k tokens
SKILL.md length
432 words
Files
1
Skills in repo
35
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when building custom Kiro AI agents or when user asks for agent configurations - provides JSON structure, tool configuration, prompt patterns, and security best practices for…

  • Works in 3 steps: Specialization Over Generalization → Least Privilege → Clear, Structured Prompts
  • Building custom Kiro AI agents
  • SKILL.md covers When to Use, Quick Reference, Core Principles and Common Patterns, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Creating Kiro Agents is an agent skill from pr-pm/prpm. Use when building custom Kiro AI agents or when user asks for agent configurations - provides JSON structure, tool configuration, prompt patterns, and security best practices for specialized development assistants

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Prompt engineering. The repository describes itself as: The universal registry for AI coding tools. The licence is MIT.

When your agent uses it

  • Building custom Kiro AI agents
  • User asks for agent configurations - provides JSON structure
  • Tool configuration
  • Prompt patterns

Example prompts

  • “/creating-kiro-agents”

Requirements

  • Node.js

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Specialization Over Generalization
  2. Least Privilege
  3. Clear, Structured Prompts

What it can do on your machine

Read from SKILL.md and the folder at commit 5f993e6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json, bash and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Creating Kiro Agents loads about 1.9k tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 432 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from pr-pm/prpm at commit 5f993e6, republished under its MIT licence (© pr-pm). 432 words, ~1,893 tokens.

Download SKILL.mdSave it as .claude/skills/creating-kiro-agents/SKILL.md (or your agent's skills folder).
name
creating-kiro-agents
description
Use when building custom Kiro AI agents or when user asks for agent configurations - provides JSON structure, tool configuration, prompt patterns, and security best practices for specialized development assistants

Creating Kiro Agents

Expert guidance for creating specialized Kiro AI agents with proper configuration, tools, and security.

When to Use

Use when:

  • User asks to create a Kiro agent
  • Need specialized AI assistant for specific workflow
  • Building domain-focused development tools
  • Configuring agent tools and permissions

Don't use for:

  • Generic AI prompts (not Kiro-specific)
  • Project documentation (use steering files instead)
  • One-off assistant interactions

Quick Reference

Minimal Agent Structure
json
{
  "name": "agent-name",
  "description": "One-line purpose",
  "prompt": "System instructions",
  "tools": ["fs_read", "fs_write"]
}
File Location
  • Project: .kiro/agents/<name>.json
  • Global: ~/.kiro/agents/<name>.json
Common Tools
  • fs_read - Read files
  • fs_write - Write files (requires allowedPaths)
  • execute_bash - Run commands (requires allowedCommands)
  • MCP server tools (varies by server)

Core Principles

1. Specialization Over Generalization

✅ Good: backend-api-specialist - Express.js REST APIs ❌ Bad: general-helper - does everything

2. Least Privilege

Grant only necessary tools and paths.

json
{
  "toolsSettings": {
    "fs_write": {
      "allowedPaths": ["src/api/**", "tests/api/**"]
    },
    "execute_bash": {
      "allowedCommands": ["npm test", "npm run build"]
    }
  }
}
3. Clear, Structured Prompts

✅ Good:

markdown
You are a backend API expert specializing in Express.js and MongoDB.

## Focus Areas
- RESTful API design
- Security best practices (input validation, auth)
- Error handling with proper status codes
- MongoDB query optimization

## Standards
- Always use async/await
- Implement proper logging
- Validate all inputs
- Use TypeScript interfaces

❌ Bad: "You are a helpful coding assistant."

Common Patterns

Backend Specialist
json
{
  "name": "backend-dev",
  "description": "Node.js/Express API development with MongoDB",
  "prompt": "Backend development expert. Focus on API design, database optimization, and security.\n\n## Core Principles\n- RESTful conventions\n- Input validation\n- Error handling\n- Query optimization",
  "tools": ["fs_read", "fs_write", "execute_bash"],
  "toolsSettings": {
    "fs_write": {
      "allowedPaths": ["src/api/**", "src/routes/**", "src/models/**"]
    }
  }
}
Code Reviewer
json
{
  "name": "code-reviewer",
  "description": "Reviews code against team standards",
  "prompt": "You review code for:\n- Quality and readability\n- Security issues\n- Performance problems\n- Standard compliance\n\nProvide constructive feedback with examples.",
  "tools": ["fs_read"],
  "resources": ["file://.kiro/steering/review-checklist.md"]
}
Test Writer
json
{
  "name": "test-writer",
  "description": "Writes comprehensive Vitest test suites",
  "prompt": "Testing expert using Vitest.\n\n## Test Requirements\n- Unit tests for all functions\n- Edge case coverage\n- Proper mocking\n- AAA pattern (Arrange, Act, Assert)\n- Descriptive test names",
  "tools": ["fs_read", "fs_write"],
  "toolsSettings": {
    "fs_write": {
      "allowedPaths": ["**/*.test.ts", "**/*.spec.ts", "tests/**"]
    }
  }
}
Frontend Specialist
json
{
  "name": "frontend-dev",
  "description": "React/Next.js development with TypeScript",
  "prompt": "Frontend expert in React, Next.js, and TypeScript.\n\n## Focus\n- Component architecture\n- Performance optimization\n- Accessibility (WCAG)\n- Responsive design",
  "tools": ["fs_read", "fs_write"],
  "toolsSettings": {
    "fs_write": {
      "allowedPaths": ["src/components/**", "src/app/**", "src/styles/**"]
    }
  }
}

Advanced Configuration

MCP Servers
json
{
  "mcpServers": {
    "database": {
      "command": "mcp-server-postgres",
      "args": ["--host", "localhost"],
      "env": {
        "DB_URL": "${DATABASE_URL}"
      }
    },
    "fetch": {
      "command": "mcp-server-fetch",
      "args": []
    }
  },
  "tools": ["fs_read", "db_query", "fetch"],
  "allowedTools": ["fetch"]
}
Lifecycle Hooks
json
{
  "hooks": {
    "agentSpawn": ["git fetch origin", "npm run db:check"],
    "userPromptSubmit": ["git status --short"]
  }
}
Resource Loading
json
{
  "resources": [
    "file://.kiro/steering/api-standards.md",
    "file://.kiro/steering/security-policy.md"
  ]
}

Workflow

  1. Clarify Requirements

    • What domain/task?
    • What tools needed?
    • What file paths?
    • What standards to follow?
  2. Design Configuration

    • Choose appropriate pattern
    • Set tool restrictions
    • Write clear prompt
    • Reference steering files
  3. Create Agent File

    bash
    # Create in project
    touch .kiro/agents/my-agent.json
    
    # Or global
    touch ~/.kiro/agents/my-agent.json
  4. Test Agent

    bash
    kiro agent use my-agent
    kiro "What can you help me with?"

Common Mistakes

MistakeProblemFix
Granting all toolsSecurity riskOnly grant necessary tools
Vague promptsIneffective agentBe specific about domain and standards
No path restrictionsAgent can modify any fileUse allowedPaths for fs_write
Generic namesHard to find/rememberUse descriptive names: react-component-creator
Missing descriptionUnclear purposeAdd one-sentence description
Multiple domainsUnfocused agentCreate separate specialized agents

Best Practices

Show full SKILL.md (184 more words)Show less
Naming
  • Use kebab-case: backend-specialist, not BackendSpecialist
  • Be specific: react-testing-expert, not helper
  • Indicate domain: aws-infrastructure, mobile-ui-designer
Prompts
  1. Define expertise area clearly
  2. List specific focus areas
  3. Specify standards/conventions
  4. Provide pattern examples
  5. Set clear expectations
Security
  1. Grant minimum necessary tools
  2. Restrict file paths with allowedPaths
  3. Whitelist commands with allowedCommands
  4. Use allowedTools for safe operations
  5. Validate all configurations

Troubleshooting

Agent Not Found
  • Check file is in .kiro/agents/
  • Verify .json extension
  • Validate JSON syntax (use JSON validator)
Tools Not Working
  • Verify tool names (check spelling)
  • Check allowedPaths restrictions
  • Ensure MCP servers are installed
  • Review allowedTools list
Prompt Ineffective
  • Be more specific about tasks
  • Add concrete examples
  • Reference team standards
  • Structure with markdown headers

Integration with PRPM

bash
# Install Kiro agent from registry
prpm install @username/agent-name --as kiro --subtype agent

# Publish your agent
prpm init my-agent --subtype agent
# Edit canonical format, then:
prpm publish

Real-World Impact

Effective agents:

  • Save time on repetitive tasks
  • Enforce team standards automatically
  • Reduce context switching
  • Provide consistent code quality
  • Enable workflow automation

Example: A test-writer agent that only writes to test files prevents accidental modification of source code while ensuring comprehensive test coverage.


Key Takeaway: Specialize agents for specific domains, restrict tools to minimum necessary, and write clear prompts with concrete standards.

© pr-pm, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/creating-kiro-agents of pr-pm/prpm.

Open the folder on GitHubat commit 5f993e6

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in pr-pm/prpm, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Creating Kiro Agents next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Creating Kiro Agents compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Creating Kiro Agents this skillpr-pm/prpm1221 repos~1.9kAutomated safety check: PassMIT
Codex Fable5baskduf/FableCodex437—~1.6kAutomated safety check: PassAGPL-3.0
Prompt Template Authoringnicobailon/pi-prompt-template-model321—~1.3kAutomated safety check: PassMIT
Context Auditundefined-ui/second-brain-os1k—~802Automated safety check: PassMIT
Asd Ste100 SkillTwiTech-LAB/devchain101—~1.2kAutomated safety check: PassMIT
AI Chatwindmill-labs/windmill18k—~672Automated safety check: PassCustom licence

Similar skills

  • Codex Fable5

    baskduf/FableCodex

    Apply a Claude Fable 5 inspired operating style inside Codex.

    437 GitHub stars~1.6k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed
  • Prompt Template Authoring

    nicobailon/pi-prompt-template-model

    Write and run custom Pi prompt templates (slash commands) for this extension.

    321 GitHub stars~1.3k tokensUpdated 17 days ago
    AI & LLM EngineeringAuto-check passed
  • Context Audit

    undefined-ui/second-brain-os

    Audit an agent's context layout against the four places: system prompt, tools, history, tail.

    1k GitHub stars~802 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Asd Ste100 Skill

    TwiTech-LAB/devchain

    Write or rewrite English with ASD-STE100 Simplified Technical English rules: one meaning per word, active voice, simple tenses, one instruction per sentence.

    101 GitHub stars~1.2k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed
  • AI Chat

    windmill-labs/windmill

    Guidance for improving the Windmill AI chat (copilot), especially global mode — tools, prompts, and context-window discipline.

    18k GitHub stars~672 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Writing Claude Directives

    ed3dai/ed3d-plugins

    A skill your agent uses when writing instructions that guide Claude behavior - skills, CLAUDE.md files, agent prompts, system prompts.

    250 GitHub stars~2.4k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

More from pr-pm/prpm

All 35 skills in this repo
  • Reference for writing Claude Code agent files: location, frontmatter fields, validation limits, tool and model choices, and the required content format.

    122 GitHub starsUsed in 3 repos~4k tokens
    Auto-check passed
  • Covers how to build, configure and publish Claude Code hooks: event types, exit codes, JSON I/O, and PRPM packaging.

    122 GitHub starsUsed in 2 repos~3.9k tokens
    Auto-check: notes
  • Shows how to write .claude/rules/ files correctly: paths frontmatter instead of globs, quoted glob patterns, global rules and conversion of Cursor rules.

    122 GitHub starsUsed in 2 repos~551 tokens
    Auto-check passed
  • Reference for writing portable Agent Skills packages, covering SKILL.md frontmatter limits, name rules, directory layout and where Codex CLI, GitHub Copilot and Amp look for skills.

    122 GitHub starsUsed in 1 repo~1.5k tokens
    Auto-check passed
  • A skill your agent uses when creating OpenCode agents - provides markdown format with YAML frontmatter, mode/tools/permission configuration, and best practices for specialized AI assistants

    122 GitHub starsUsed in 1 repo~2k tokens
    Auto-check passed
  • A skill your agent uses when implementing Stripe webhook endpoints and getting 'Raw body not available' or signature verification errors - provides raw body parsing solutions and subscription period…

    122 GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed

Questions about Creating Kiro Agents

What does Creating Kiro Agents do?

A skill your agent uses when building custom Kiro AI agents or when user asks for agent configurations - provides JSON structure, tool configuration, prompt patterns, and security best practices for…. Creating Kiro Agents is an agent skill from pr-pm/prpm.

When should I use Creating Kiro Agents?

Creating Kiro Agents fits situations like: building custom Kiro AI agents; user asks for agent configurations - provides JSON structure; tool configuration; prompt patterns.

How do I install Creating Kiro Agents in Claude Code?

Run `npx skills add pr-pm/prpm --skill creating-kiro-agents -a claude-code`. Or copy the skill folder (.claude/skills/creating-kiro-agents in pr-pm/prpm) into .claude/skills/creating-kiro-agents in your project. Claude Code loads it when a task matches its description.

How do I install Creating Kiro Agents in Codex?

Run `npx skills add pr-pm/prpm --skill creating-kiro-agents -a codex`. Or copy the skill folder (.claude/skills/creating-kiro-agents in pr-pm/prpm) into .agents/skills/creating-kiro-agents in your project. Codex loads it when a task matches its description.

Can I use Creating Kiro Agents in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pr-pm/prpm --skill creating-kiro-agents -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/creating-kiro-agents, .gemini/skills/creating-kiro-agents, .github/skills/creating-kiro-agents and .opencode/skills/creating-kiro-agents in your project.

What does Creating Kiro Agents need to run?

SKILL.md names no scripts, command-line tools or credentials: Creating Kiro Agents is instructions for the agent only. Our summary lists: Node.js.

Does Creating Kiro Agents access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Creating Kiro Agents safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Creating Kiro Agents use?

Creating Kiro Agents is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Creating Kiro Agents use?

About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Creating Kiro Agents?

Skills that share tags, products or a category with Creating Kiro Agents: Codex Fable5 (baskduf/FableCodex, 437 stars), Prompt Template Authoring (nicobailon/pi-prompt-template-model, 321 stars), Context Audit (undefined-ui/second-brain-os, 1k stars) and Asd Ste100 Skill (TwiTech-LAB/devchain, 101 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Creating Kiro Agents?

pr-pm (a GitHub organization) maintains it in pr-pm/prpm, which has 122 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on October 6, 2026.

Source: pr-pm/prpm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.