agent-builder SKILL.md skillA

agent-builder from keyuchen21/agentic-engineering-handbook is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add keyuchen21/agentic-engineering-handbook/agent-builder@git:20260613.5c7b9b8

Pins git:20260613.5c7b9b8 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
keyuchen21/agentic-engineering-handbook
Path
tutorials/agent-loop/skills/agent-builder/SKILL.md
Versions recorded
1
Latest version
git:20260613.5c7b9b8, committed Jun 13, 2026
Size
4,713 bytes
Repository stars
558
License
MIT

Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code, Cursor, or similar agent internals (5) want to build agents for business, research, creative, or operational tasks Keywords: agent, assistant, autonomous, workflow, tool use…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Agent Builder

Build AI agents for any domain - customer service, research, operations, creative work, or specialized business processes.

## The Core Philosophy

> **The model already knows how to be an agent. Your job is to get out of the way.**

An agent is not complex engineering. It's a simple loop that invites the model to act:

```
LOOP:
  Model sees: context + available capabilities
  Model decides: act or respond
  If act: execute capability, add result, continue
  If respond: return to user
```

**That's it.** The magic isn't in the code - it's in the model. Your code just provides the opportunity.

## The Three Elements

### 1. Capabilities (What can it DO?)

Atomic actions the agent can perform: search, read, create, send, query, modify.

**Design principle**: Start with 3-5 capabilities. Add more only when the agent consistently fails because a capability is missing.

### 2. Knowledge (What does it KNOW?)

Domain expertise injected on-demand: policies, workflows, best practices, schemas.

**Design principle**: Make knowledge available, not mandatory. Load it when relevant, not upfront.

### 3. Context (What has happened?)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add keyuchen21/agentic-engineering-handbook/agent-builder@sha256:4b88e0f4c19caf58

The line at the top of this page pins the label git:20260613.5c7b9b8, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_vdbto2g4mffp45rd.svg)](https://markdownregistry.com/a/art_vdbto2g4mffp45rd)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jun 13, 2026.

versioncommittedcommitsizeaudit
git:20260613.5c7b9b8 latest2026-06-13 5c7b9b8 4,713 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4713 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

keyuchen21/agentic-engineering-handbook · 558 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_vdbto2g4mffp45rd
GET https://markdownregistry.com/api/v1/resolve?ref=keyuchen21/agentic-engineering-handbook/agent-builder
GET https://markdownregistry.com/api/v1/blob/4b88e0f4c19caf58f38ca6bd27e55d8ab94ebf0ad54d4ffb7da83559e020dbc7

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from keyuchen21/agentic-engineering-handbook

code-review SKILL.md skill
keyuchen21/agentic-engineering-handbook · tutorials/agent-loop/skills/code-review/SKILL.md · Perform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review…
git:20260613.5c7b9b8 · audit A · 558 stars
mcp-builder SKILL.md skill
keyuchen21/agentic-engineering-handbook · tutorials/agent-loop/skills/mcp-builder/SKILL.md · Build MCP (Model Context Protocol) servers that give Claude new capabilities. Use when user wants to create an MCP…
git:20260613.5c7b9b8 · audit A · 558 stars
pdf SKILL.md skill
keyuchen21/agentic-engineering-handbook · tutorials/agent-loop/skills/pdf/SKILL.md · Process PDF files - extract text, create PDFs, merge documents. Use when user asks to read PDF, create PDF, or work…
git:20260613.5c7b9b8 · audit A · 558 stars

Every file in keyuchen21/agentic-engineering-handbook

Other files named agent-builder

agent-builder SKILL.md skill
block/berd · distro/skills/agent-builder/SKILL.md · Create, edit, or inspect Berd agents/personas stored as Agent Markdown files with YAML frontmatter under…
git:20260820.b4fd399 · audit A · 988 stars
agent-builder SKILL.md skill
mathews-tom/armory · skills/agent-builder/SKILL.md · Build AI agents and automate Claude Code programmatically via the Claude Agent SDK and headless CLI mode. Covers Python…
v1.1.1 · audit A · 334 stars
agent-builder SKILL.md skill
testdouble/han · han-plugin-builder/skills/agent-builder/SKILL.md · Builds a new Claude Code agent (subagent) from scratch through a relentless, evidence-based interview that walks the…
git:20260818.55bdb1d · audit A · 319 stars
agent-builder SKILL.md skill
aaaaqwq/agi-super-team · skills/agent-builder/SKILL.md · Build agent from spec: code, skill, config, launchd
git:20260421.9d3e41d · audit A · 109 stars
agent-builder SKILL.md skill
naveedharri/benai-skills · plugins/all-skills/skills/agent-builder/SKILL.md · Build Anthropic Managed Agents through a non-technical conversation. The skill asks the user what kind of agent they…
git:20260916.a3b1e15 · audit A · 71 stars
agent-builder SKILL.md skill
starchild-ai-agent/official-skills · agent-builder/SKILL.md · Build focused micro-agents with names, tasks, schedules, and team coordination. Use when spinning up specialized…
v2.0.1 · audit A · 28 stars
agent-builder SKILL.md skill
sodam-ai/sodam-agent · plugins/autonomy-team/skills/agent-builder/SKILL.md · 기존 역할로 해결되지 않는 반복 역량 부족을 확인해 프로젝트 역할을 만들 때 적용합니다.
git:20261020.19ccf3f · audit A · 16 stars
agent-builder SKILL.md skill
synaptiai/synapti-marketplace · plugins/ai-first-org-design-kit/skills/agent-builder/SKILL.md · Generate role-specific agent system prompts, tool permissions, and self-review checklists from organizational design…
git:20260726.1f35e1f · audit A · 7 stars

Browse by kind, by grade A, or by owner.