Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Tool Use Architect

ASecurity

Design and implement Claude tool/function calling patterns with error handling, parallel execution, and validation. Based on Anthropic's Claude Cookbooks.

2 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgogitapidatabase

Works with

api

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add Marine-softdrink524/claude-skills --skill tool-use-architect --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Tool Use Architect?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Tool Use Architect
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/marine-softdrink524-tool-use-architect/badge)](https://www.skillsdirectory.com/skills/marine-softdrink524-tool-use-architect)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: tool-use-architect
description: Design and implement Claude tool/function calling patterns with error handling, parallel execution, and validation. Based on Anthropic's Claude Cookbooks.
license: MIT
metadata:
  author: Anthropic
  source: https://github.com/anthropics/anthropic-cookbook/tree/main/tool_use
  version: "1.0"
  category: ai-engineering
---

# Tool Use Architect

You are an expert at designing tool-calling architectures for AI agents, enabling Claude to interact with APIs, databases, and external services.

## Tool Definition Pattern

```json
{
  "name": "get_weather",
  "description": "Get current weather for a location. Use when user asks about weather conditions.",
  "input_schema": {
    "type": "object",
    "properties": {
      "location": {
        "type": "string",
        "description": "City name, e.g. 'San Francisco, CA'"
      },
      "unit": {
        "type": "string",
        "enum": ["celsius", "fahrenheit"],
        "description": "Temperature unit"
      }
    },
    "required": ["location"]
  }
}
```

## Design Rules

### 1. Naming
- Use `snake_case` for tool names
- Use verb_noun pattern: `get_user`, `create_order`, `search_products`
- Be specific: `search_products` not `search`

### 2. Descriptions
- Explain WHEN to use the tool, not just WHAT it does
- Include examples of valid inputs
- Document edge cases and limitations

### 3. Input Schema
- Always define `required` fields
- Use `enum` for fixed-value parameters
- Add `description` to every property
- Use `format` for emails, dates, URLs

### 4. Error Handling
```
Tool Result Patterns:
✅ Success: {"status": "success", "data": {...}}
❌ Error:   {"status": "error", "message": "User not found", "code": "NOT_FOUND"}
⚠️ Partial: {"status": "partial", "data": {...}, "warnings": [...]}
```

## Multi-Tool Orchestration

### Sequential (Dependent)
```
1. search_user(email) → user_id
2. get_orders(user_id) → orders[]
3. get_order_details(order_id) → details
```

### Parallel (Independent)
```
Parallel:
  ├── get_weather(location)
  ├── get_news(topic)
  └── get_calendar(date)
→ Combine results in response
```

## Tool Categories

| Category | Tools | Example |
|----------|-------|---------|
| Data Retrieval | GET endpoints | `get_user`, `search_docs` |
| Data Mutation | POST/PUT/DELETE | `create_order`, `update_profile` |
| Computation | Math/Logic | `calculate_tax`, `convert_currency` |
| External APIs | 3rd party | `send_email`, `create_ticket` |
| System | Infrastructure | `run_query`, `check_status` |

## Safety Guidelines
- Never expose raw database queries as tools
- Validate and sanitize all tool inputs
- Implement rate limiting for external API calls
- Log all tool invocations for audit
- Use confirmation for destructive actions (delete, send)
- Always handle tool errors gracefully in the conversation

Attribution

Marine-softdrink524Marine-softdrink524
View sourceMore from Marine-softdrink524 →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →