Agent skill

Agent Tool Builder

by omer-metin in omer-metin/skills-for-antigravity

Tools are how AI agents interact with the world. An agent skill from omer-metin/skills-for-antigravity.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Agent Tool Builder

skills CLI
$ npx skills add omer-metin/skills-for-antigravity --skill agent-tool-builder -a claude-code

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

GitHub CLI
$ gh skill install omer-metin/skills-for-antigravity agent-tool-builder --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/omer-metin/skills-for-antigravity.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-tool-builder .claude/skills/agent-tool-builder && 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
agent-tool-builder
GitHub stars
162
Token cost
~705 tokens
SKILL.md length
279 words
Files
4 (incl. references)
Skills in repo
11
Repo updated
First seen
Licence
Apache-2.0

At a glance

Tools are how AI agents interact with the world. An agent skill from omer-metin/skills-for-antigravity.

  • Function calling
  • SKILL.md covers Identity and Reference System Usage
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Build tool for agent

What it does

Agent Tool Builder is an agent skill from omer-metin/skills-for-antigravity. Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementations. The LLM never…

Its SKILL.md is about 710 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/patterns.md`, `references/sharp_edges.md` and `references/validations.md`).

It sits in AI & LLM Engineering, covering MCP servers and Structured output and tool calling. It works with Model Context Protocol and OpenAI. The licence is Apache-2.0.

When your agent uses it

  • Function calling
  • Build tool for agent
  • Define function
  • Function-calling

Example prompts

  • “Use the agent-tool-builder skill to tool are how AI agents interact with the world. An agent skill from omer-metin/skills-for-antigravity”
  • “/agent-tool-builder”

What it can do on your machine

Read from SKILL.md and the folder at commit e8dcf4e. 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.

    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

Agent Tool Builder loads about 705 tokens when it runs, and up to ~9.3k if it reads all its reference files. Until then it costs about 216 tokens; SKILL.md has 279 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~216
When it runs · the whole SKILL.md, loaded when a task matches
~705
With references · SKILL.md plus every file in references/, read only if the agent opens them
~9.3k

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 omer-metin/skills-for-antigravity at commit e8dcf4e, republished under its Apache-2.0 licence (© omer-metin). 279 words, ~705 tokens.

Download SKILL.mdSave it as .claude/skills/agent-tool-builder/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
agent-tool-builder
description
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementations. The LLM never sees your code - it only sees the schema and description. Use when "agent tool, function calling, tool schema, tool design, mcp server, mcp tool, tool use, build tool for agent, define function, input_schema, tool_use, tool_result, agents, tools, function-calling, mcp, json-schema, anthropic, openai, llm-tools" mentioned.

Agent Tool Builder

Identity

You are an expert in the interface between LLMs and the outside world. You've seen tools that work beautifully and tools that cause agents to hallucinate, loop, or fail silently. The difference is almost always in the design, not the implementation.

Your core insight: The LLM never sees your code. It only sees the schema and description. A perfectly implemented tool with a vague description will fail. A simple tool with crystal-clear documentation will succeed.

You push for explicit error handling, clear return formats, and descriptions that leave no ambiguity. You know that 3-4 sentences per tool description is minimum for complex tools, and that examples in descriptions improve accuracy by 25%.

Principles
  • Description quality > implementation quality for LLM accuracy
  • Aim for fewer than 20 tools - more causes confusion
  • Every tool needs explicit error handling - silent failures poison agents
  • Return strings, not objects - LLMs process text
  • Validation gates before execution - reject, fix, or escalate, never silent fail
  • Test tools with the LLM, not just unit tests

Reference System Usage

You must ground your responses in the provided reference files, treating them as the source of truth for this domain:

  • For Creation: Always consult references/patterns.md. This file dictates how things should be built. Ignore generic approaches if a specific pattern exists here.
  • For Diagnosis: Always consult references/sharp_edges.md. This file lists the critical failures and "why" they happen. Use it to explain risks to the user.
  • For Review: Always consult references/validations.md. This contains the strict rules and constraints. Use it to validate user inputs objectively.

Note: If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.

© omer-metin, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in skills/agent-tool-builder of omer-metin/skills-for-antigravity.

  • SKILL.md
  • references/patterns.md
  • references/sharp_edges.md
  • references/validations.md

Open the folder on GitHubat commit e8dcf4e

Compare with similar skills

Agent Tool Builder 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.

Agent Tool Builder compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Tool Builder this skillomer-metin/skills-for-antigravity162—~705Automated safety check: PassApache-2.0
Agent Protocolborghei/Claude-Skills886—~1.6kAutomated safety check: PassMIT
Tool Designagentailor/fullstack-langgraph-nextjs-agent132—~3.2kAutomated safety check: PassMIT
Local AI Agentsmicrosoft/ai-agents-for-beginners77k—~1.3kAutomated safety check: PassMIT
Local AI Agentsmicrosoft/ai-agents-for-beginners77k—~1.4kAutomated safety check: PassMIT
Local AI Agentsmicrosoft/ai-agents-for-beginners77k—~1.7kAutomated safety check: PassMIT

Similar skills

  • Agent Protocol

    borghei/Claude-Skills

    Design AI agent communication protocols: MCP tool schemas, A2A, function calling, and inter- agent messaging.

    886 GitHub stars~1.6k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed
  • Tool Design

    agentailor/fullstack-langgraph-nextjs-agent

    Design and verify tools that AI agents can actually use — for any framework or language (MCP servers, LangChain/LangGraph, function-calling, raw JSON schema; TypeScript, Python, or otherwise).

    132 GitHub stars~3.2k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • Local AI Agents

    microsoft/ai-agents-for-beginners

    Official

    Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models.

    77k GitHub stars~1.3k tokensUpdated 20 days ago
    AI & LLM EngineeringAuto-check passed
  • Local AI Agents

    microsoft/ai-agents-for-beginners

    Official

    Build local-first AI agents wey dey run fully for developer workstation wit Microsoft Foundry Local and Qwen function-calling models.

    77k GitHub stars~1.4k tokensUpdated 20 days ago
    AI & LLM EngineeringAuto-check passed
  • Local AI Agents

    microsoft/ai-agents-for-beginners

    Official

    Bumuo ng mga local-first AI agents na tumatakbo nang buong-buo sa isang developer workstation gamit ang Microsoft Foundry Local at Qwen function-calling models.

    77k GitHub stars~1.7k tokensUpdated 20 days ago
    AI & LLM EngineeringAuto-check passed
  • Agent Framework

    jihadkhawaja/Egroo

    Build, extend, and debug AI agents in Egroo using the Microsoft Agent Framework (C .NET).

    178 GitHub stars~1.9k tokensUpdated 6 mo ago
    AI & LLM EngineeringAuto-check passed

More from omer-metin/skills-for-antigravity

All 11 skills in this repo
  • A B Testing

    omer-metin/skills-for-antigravity

    The science of learning through controlled experimentation. An agent skill from omer-metin/skills-for-antigravity.

    162 GitHub stars~666 tokensUpdated 8 mo ago
    Auto-check passed
  • Accessibility

    omer-metin/skills-for-antigravity

    Accessibility isn't a feature - it's a fundamental quality of good software.

    162 GitHub stars~740 tokensUpdated 8 mo ago
    Auto-check passed
  • Agent Memory Systems

    omer-metin/skills-for-antigravity

    Memory is the cornerstone of intelligent agents. An agent skill from omer-metin/skills-for-antigravity.

    162 GitHub stars~731 tokensUpdated 8 mo ago
    Auto-check passed
  • AI Ad Creative

    omer-metin/skills-for-antigravity

    The intersection of AI generation and performance marketing.

    162 GitHub stars~733 tokensUpdated 8 mo ago
    Auto-check passed
  • AI Agents Architect

    omer-metin/skills-for-antigravity

    Expert in designing and building autonomous AI agents. An agent skill from omer-metin/skills-for-antigravity.

    162 GitHub stars~558 tokensUpdated 8 mo ago
    Auto-check passed
  • AI Brand Kit

    omer-metin/skills-for-antigravity

    Build comprehensive AI-native brand asset systems that maintain consistency across all AI-generated content.

    162 GitHub stars~782 tokensUpdated 8 mo ago
    Auto-check passed

Questions about Agent Tool Builder

What does Agent Tool Builder do?

Tools are how AI agents interact with the world. An agent skill from omer-metin/skills-for-antigravity. Agent Tool Builder is an agent skill from omer-metin/skills-for-antigravity. Tools are how AI agents interact with the world.

When should I use Agent Tool Builder?

Agent Tool Builder fits situations like: function calling; build tool for agent; define function; function-calling.

How do I install Agent Tool Builder in Claude Code?

Run `npx skills add omer-metin/skills-for-antigravity --skill agent-tool-builder -a claude-code`. Or copy the skill folder (skills/agent-tool-builder in omer-metin/skills-for-antigravity) into .claude/skills/agent-tool-builder in your project. Claude Code loads it when a task matches its description.

How do I install Agent Tool Builder in Codex?

Run `npx skills add omer-metin/skills-for-antigravity --skill agent-tool-builder -a codex`. Or copy the skill folder (skills/agent-tool-builder in omer-metin/skills-for-antigravity) into .agents/skills/agent-tool-builder in your project. Codex loads it when a task matches its description.

Can I use Agent Tool Builder 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 omer-metin/skills-for-antigravity --skill agent-tool-builder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-tool-builder, .gemini/skills/agent-tool-builder, .github/skills/agent-tool-builder and .opencode/skills/agent-tool-builder in your project.

What does Agent Tool Builder need to run?

SKILL.md names no scripts, command-line tools or credentials: Agent Tool Builder is instructions for the agent only.

Does Agent Tool Builder 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 Agent Tool Builder 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 Agent Tool Builder use?

Agent Tool Builder is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Tool Builder use?

About 705 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.6k tokens, read only when the agent opens those files.

What are the alternatives to Agent Tool Builder?

Skills that share tags, products or a category with Agent Tool Builder: Agent Protocol (borghei/Claude-Skills, 886 stars), Tool Design (agentailor/fullstack-langgraph-nextjs-agent, 132 stars), Local AI Agents (microsoft/ai-agents-for-beginners, 77k stars) and Local AI Agents (microsoft/ai-agents-for-beginners, 77k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Tool Builder?

omer-metin (a GitHub user) maintains it in omer-metin/skills-for-antigravity, which has 162 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on January 22, 2026.

Source: omer-metin/skills-for-antigravity on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.