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.

Quality

57%

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 ./skills/antigravity-agent-tool-builder/SKILL.md

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

Quality

Content

65%

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

The content is highly actionable with strong executable examples and validation guidance, but it is a monolithic single-file document that could be split into reference files and tightened for token efficiency. Workflow checkpoints are present in places but inconsistent.

Suggestions

Move the large code-reference blocks (MCP server, tool runner, parallel execution) into separate reference files and link them from a concise overview.

Add explicit validate->fix->retry checkpoints to the schema-design and MCP workflows rather than only the error-handling section.

Trim the recurring weather example and the conceptual opening that restates the description.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete code, but the weather example recurs across multiple sections and the opening restates the description's conceptual pitch; it could be tightened to lean 3.	2 / 3
Actionability	Provides fully executable Python, TypeScript, and JSON Schema examples plus BAD/GOOD comparisons and a concrete validation-checks section; guidance is copy-paste ready.	3 / 3
Workflow Clarity	Patterns are sequenced with 'When to use' headers and the error-handling section shows feedback loops, but most workflows lack explicit validate->fix->retry checkpoints for risky operations, which caps the score at 2.	2 / 3
Progressive Disclosure	No bundle files exist and ~700 lines of code examples and API reference are inlined in one file; sections are organized, but content that should be split into reference files is not.	2 / 3
	Total	9 / 12 Passed

Description

50%

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

The description is clear and on-domain but reads as a conceptual pitch rather than a trigger-rich capability statement. It lacks an explicit 'Use when' clause and natural user-facing trigger terms.

Suggestions

Add a 'Use when...' clause listing concrete user triggers (e.g., 'Use when designing agent tools, writing JSON Schemas, adding function-calling, or building MCP servers').

Replace the opening conceptual framing with a direct list of concrete actions the skill performs.

Include natural terms a user would say ('function calling', 'tool schema', 'MCP server', 'tool use') rather than abstract phrasing.

Dimension	Reasoning	Score
Specificity	Names the domain ('tool design') and a span ('from schema to error handling') but does not list multiple concrete actions like 'design schemas', 'write descriptions', 'add validation'; matches anchor 2.	2 / 3
Completeness	It states what the skill covers ('tool design from schema to error handling') but has no 'Use when...' clause or explicit trigger guidance, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Phrases like 'AI agents interact with the world', 'function calling', and 'tool design' are relevant but conceptual rather than the natural keywords a user would say; coverage of common variations is partial.	2 / 3
Distinctiveness Conflict Risk	'Tool design' is a recognizable niche but the description is broad enough to overlap with api-design, backend, or prompt-engineering skills, so it is not clearly distinct.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (715 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: boisenoise/skills-collections
Path: skills/antigravity-agent-tool-builder/SKILL.md
Commit: c27161a

Reviewed: about 2 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.