agent-tool-builder

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 implementa

Install with Tessl CLI

npx tessl i github:duclm1x1/Dive-Ai --skill agent-tool-builder

What are skills?

Review — 23%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Discovery

32%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description reads like marketing copy or a course overview rather than a functional skill description. It explains concepts and provides 'key insights' but fails to specify concrete actions Claude should take or when to invoke this skill. The description also appears truncated, ending mid-sentence.

Suggestions

Add an explicit 'Use when...' clause with trigger terms like 'design a tool', 'MCP server', 'tool schema', 'function definition', 'agent tools'

Replace conceptual language with concrete actions: 'Designs tool schemas, writes tool descriptions, validates JSON Schema definitions, creates MCP-compliant tool specifications'

Remove editorial commentary ('Key insight...', 'the difference between...') and focus on actionable capability statements

Dimension	Reasoning	Score
Specificity	Names the domain (tool design for AI agents) and mentions some actions like 'JSON Schema best practices, description writing, validation' but these are topics rather than concrete actions Claude would perform. Missing specific verbs like 'create', 'validate', 'generate'.	2 / 3
Completeness	Describes what the skill covers conceptually but has no explicit 'Use when...' clause or trigger guidance. The description reads more like a course syllabus than actionable skill guidance. Also appears truncated mid-sentence.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'tool design', 'JSON Schema', 'MCP standard', 'error handling', but missing common user phrases like 'create a tool', 'write tool schema', 'MCP server', or 'function calling'.	2 / 3
Distinctiveness Conflict Risk	The MCP and tool design focus provides some distinctiveness, but 'AI agents' and 'JSON Schema' could overlap with general coding or API skills. The niche is identifiable but not sharply defined.	2 / 3
	Total	7 / 12 Passed

Implementation

14%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is essentially a skeleton or outline with no substantive content. It lists capabilities and pattern names but provides zero executable guidance, code examples, or actual instructions. The content appears truncated and would not help Claude perform any tool-building tasks.

Suggestions

Add complete, executable JSON Schema examples for tool definitions with proper descriptions

Include concrete code examples showing tool error handling patterns that help LLMs recover

Provide a step-by-step workflow for designing and validating a new tool schema

Complete the truncated content and either fill in the pattern sections with actionable guidance or link to separate detailed files

Dimension	Reasoning	Score
Conciseness	The content is relatively brief but includes some unnecessary philosophical framing ('You are an expert...', 'Your core insight...') that Claude doesn't need. The capabilities list and pattern headers add tokens without providing actionable content.	2 / 3
Actionability	The skill provides no concrete code, commands, or executable examples. Pattern sections like 'Tool Schema Design' and 'Tool Error Handling' are just headers with descriptions but no actual schemas, code samples, or specific guidance on how to implement them.	1 / 3
Workflow Clarity	There is no workflow or sequence of steps provided. The skill mentions concepts like 'Tool Schema Design' and 'Tool Error Handling' but doesn't explain how to actually perform these tasks or in what order. No validation checkpoints are present.	1 / 3
Progressive Disclosure	The content appears to be truncated mid-sentence ('explicit error hand') and provides only stub headers without actual content. There are no references to detailed documentation, no linked files, and the structure suggests content that was never completed.	1 / 3
	Total	5 / 12 Passed

Validation

90%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Reviewed: 11 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.