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 necessar...
42
Quality
11%
Does it follow best practices?
Impact
100%
1.05xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-agent-tool-builder/SKILL.mdQuality
Discovery
0%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 is severely truncated and provides no actionable information for skill selection. It reads like the beginning of an essay about tool design philosophy rather than a functional skill description. Without concrete actions, trigger terms, or usage guidance, Claude cannot effectively select this skill.
Suggestions
Complete the description and specify concrete actions (e.g., 'Designs tool schemas, validates tool inputs, generates tool documentation').
Add a 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when creating MCP tools, designing function schemas, or building agent integrations').
Remove philosophical preamble and focus on what the skill does and when to use it in a concise format.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description is truncated and only contains abstract language about 'AI agents' and 'tools' without listing any concrete actions. No specific capabilities are described. | 1 / 3 |
Completeness | The description is truncated and fails to answer either 'what does this do' or 'when should Claude use it'. There is no 'Use when...' clause or equivalent guidance. | 1 / 3 |
Trigger Term Quality | The visible portion contains technical jargon ('AI agents', 'hallucinates', 'tokens') but no natural keywords a user would say when needing this skill. No actionable trigger terms present. | 1 / 3 |
Distinctiveness Conflict Risk | The vague reference to 'tools' and 'AI agents' is extremely generic and could conflict with virtually any skill involving tool usage or agent behavior. | 1 / 3 |
Total | 4 / 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 skeleton or outline with no substantive content. It identifies relevant topics (tool schema design, error handling, anti-patterns) but provides zero actionable guidance, no code examples, and no actual instructions. The content appears truncated mid-sentence and the pattern/anti-pattern sections are empty headers.
Suggestions
Add executable code examples for tool schema design, showing a complete JSON Schema with description best practices
Fill in the Pattern sections with concrete guidance - e.g., actual input examples, error response formats, and validation approaches
Expand Anti-Patterns with specific examples of what NOT to do and why (e.g., show a vague description vs. a clear one)
Add a workflow for designing a new tool: 1) Define purpose, 2) Design schema, 3) Write description, 4) Add examples, 5) Test with LLM
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is relatively brief but includes some unnecessary philosophical framing ('Your core insight...') that Claude already understands. The capabilities list and pattern headers without content add tokens without value. | 2 / 3 |
Actionability | The skill provides no concrete code, commands, or executable examples. Pattern sections are empty headers with no actual guidance. Anti-patterns are listed but not explained or demonstrated. | 1 / 3 |
Workflow Clarity | There is no workflow defined. The skill lists capabilities and pattern names but provides no steps, sequences, or processes for actually building agent tools. | 1 / 3 |
Progressive Disclosure | The structure with sections (Patterns, Anti-Patterns, Related Skills) shows organizational intent, but the sections are empty shells. No references to detailed documentation exist, and the content that should be present is simply missing. | 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
- boisenoise/skills-collections
- Commit
5c5ae21
- 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.