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
40
Quality
27%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent/skills/agent-tool-builder/SKILL.mdQuality
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 syllabus rather than a functional skill description. It contains conceptual explanations ('Key insight: Tool descriptions are more important...') instead of actionable guidance, lacks explicit trigger conditions, and appears to be truncated. The description would benefit from concrete actions and clear 'Use when' triggers.
Suggestions
Add an explicit 'Use when...' clause with trigger phrases like 'designing tools', 'creating MCP tools', 'writing tool schemas', 'function definitions for AI'
Replace conceptual explanations with concrete actions: 'Designs tool schemas, writes effective tool descriptions, implements MCP-compliant tools, validates tool definitions'
Remove the editorial commentary ('Key insight...') and ensure the description is complete (currently truncated)
| 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 (tool design concepts) but completely lacks a 'Use when...' clause or any explicit trigger guidance. The description reads more like a course overview 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', 'define function', 'API definition'. Terms are more conceptual than what users would naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on AI tool design and MCP standard provides some distinctiveness, but 'JSON Schema' and 'validation' could overlap with general API or schema-related skills. The broad framing around 'how AI agents interact with the world' is quite generic. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
22%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 stub - it provides philosophical framing and links to sub-skills but contains no actionable content in the main file. The content appears truncated mid-sentence. While the progressive disclosure structure (linking to sub-skills) is reasonable, the main SKILL.md fails to provide any concrete guidance, examples, or workflows that would help Claude actually build agent tools.
Suggestions
Add a concrete 'Quick Start' section with an executable example of a well-designed tool schema (JSON Schema + description)
Include at least one complete before/after example showing a vague tool description vs. a clear one
Add a brief workflow: 1) Define schema 2) Write description 3) Add examples 4) Handle errors - with validation checkpoints
Complete the truncated content and remove the redundant 'Capabilities' list since sub-skills already cover these
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The philosophical framing ('Your core insight...') adds some value but could be tighter. The capabilities list is redundant given the sub-skill links. Content is cut off mid-sentence suggesting incomplete state. | 2 / 3 |
Actionability | No concrete code, commands, or executable examples. The content describes philosophy and links to sub-skills but provides zero actionable guidance in the main file itself. | 1 / 3 |
Workflow Clarity | No workflow, sequence, or process is defined. The skill lists capabilities and links but doesn't explain how to actually build a tool or what steps to follow. | 1 / 3 |
Progressive Disclosure | Good use of sub-skill links for detailed topics, but the main file provides almost no overview content - it's essentially just a table of contents with philosophy. The quick-start content is missing entirely. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
90%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
- Dokhacgiakhoa/antigravity-ide
- Commit
3395991
- Reviewed
Table of Contents
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.