agent-tool-builder

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.

Quality

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/agent-tool-builder/SKILL.md

The canonical home for this skill is agent-tool-builder in sickn33/agentic-awesome-skills

Quality

Content

14%Scale 1-3

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 an outline or stub with no substantive content. It names relevant concepts (tool schema design, error handling, anti-patterns) but provides zero concrete guidance, examples, or executable code. The content appears truncated ('explicit error hand') and most sections are empty headers, making it unusable as a skill file.

Suggestions

Add concrete, executable code examples for tool schema design—e.g., a complete JSON Schema for a tool with description, parameters, and examples.

Fill in the Anti-Patterns sections with specific bad examples and corrections showing what to avoid and what to do instead.

Add a step-by-step workflow for designing and validating a new tool, including validation checkpoints (e.g., schema validation, testing with sample LLM calls).

Either flesh out the Patterns sections with actionable content or link to separate detailed files for each pattern (e.g., 'See [SCHEMA_DESIGN.md](SCHEMA_DESIGN.md) for full guide').

Dimension	Reasoning	Score
Conciseness	The content is relatively short but wastes tokens on vague philosophical statements ('The LLM never sees your code') and empty section headers with no actual content. The 'Capabilities' list and 'When to Use' section add no actionable value.	2 / 3
Actionability	There is no concrete code, no executable examples, no specific commands, and no actual tool schemas shown. Every section is either a label or a vague description—nothing is copy-paste ready or instructive enough to act on.	1 / 3
Workflow Clarity	There is no workflow, no sequenced steps, and no validation checkpoints. The 'Patterns' and 'Anti-Patterns' sections are just headers with no content explaining what to do or in what order.	1 / 3
Progressive Disclosure	The content is a skeleton of headers with almost no body content. There are no references to external files, no navigation structure, and the anti-patterns sections are completely empty. It's neither a useful overview nor a detailed guide.	1 / 3
	Total	5 / 12 Passed

Description

0%Scale 1-3

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 as a persona or role-play prompt rather than a skill description. It provides zero information about what concrete actions the skill performs, includes no trigger terms a user would naturally use, and completely lacks any 'when to use' guidance. It would be essentially unusable for skill selection among a set of available skills.

Suggestions

Replace the persona narrative with concrete actions the skill performs, e.g., 'Designs and reviews tool/function schemas for LLM agents, validates parameter types, and identifies failure modes like hallucination loops or silent errors.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about designing tools for AI agents, debugging agent tool calls, or improving function calling schemas.'

Remove first/second person framing ('You are an expert...You've seen...') and rewrite in third person describing capabilities, e.g., 'Reviews and improves LLM tool definitions...'

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. It uses abstract, narrative language about 'the interface between LLMs and the outside world' and 'tools that work beautifully' without specifying what the skill actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. There is no 'Use when...' clause or equivalent trigger guidance, and the capabilities are entirely unstated.	1 / 3
Trigger Term Quality	There are no natural user-facing trigger terms. Words like 'LLMs', 'hallucinate', 'loop', and 'fail silently' are technical jargon that users are unlikely to use when requesting help. The description reads like a persona introduction, not a skill selector.	1 / 3
Distinctiveness Conflict Risk	The description is extremely generic — it could apply to tool design, API design, agent debugging, prompt engineering, or many other skills. There is nothing that carves out a clear niche or distinguishes it from other skills.	1 / 3
	Total	4 / 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

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/agent-tool-builder/SKILL.md
Commit: 7520423

Reviewed: ~11 hours 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.