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

32%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/antigravity-agent-tool-builder/SKILL.md

Quality

Content

42%

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

The skill excels at actionability with rich, executable code examples across multiple frameworks and languages, making it genuinely useful for tool building. However, it is significantly over-long and verbose, mixing frontmatter-style metadata (Capabilities, Scope, When to Use, Limitations) into the body, explaining concepts Claude already knows, and cramming everything into one monolithic file without progressive disclosure. The lack of a cohesive end-to-end workflow connecting the individual patterns is a notable gap.

Suggestions

Move metadata sections (Capabilities, Scope, When to Use, Limitations, Collaboration, Related Skills) into YAML frontmatter — they consume ~80 lines of body content without adding actionable guidance.

Split the monolithic file into focused sub-files (e.g., SCHEMA_DESIGN.md, ERROR_HANDLING.md, MCP_TOOLS.md, TOOL_RUNNER.md) and reference them from a concise overview in SKILL.md.

Add a clear end-to-end workflow section at the top: 'Design schema → Write descriptions → Implement with error handling → Validate schema → Test with LLM → Iterate', with explicit checkpoints.

Remove explanatory text Claude already knows (e.g., 'MCP is Anthropic's open standard for connecting AI agents to external systems', error category taxonomies) and trim descriptions to essential, non-obvious guidance.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~400+ lines. It explains concepts Claude already knows (what JSON Schema is, what MCP is, basic error handling categories), includes unnecessary metadata sections (Capabilities, Scope, When to Use, Limitations) that belong in frontmatter not body content, and repeats similar patterns multiple times. The 'Validation Checks' section reads like linter rules rather than actionable guidance. Significant token waste throughout.	1 / 3
Actionability	The skill provides extensive, concrete, executable code examples across Python and TypeScript. Tool schemas are complete JSON with realistic data, the error handling pattern includes a full dataclass implementation, MCP server code is copy-paste ready, and the parallel execution pattern shows both correct and incorrect approaches. Very high actionability.	3 / 3
Workflow Clarity	The skill covers multiple patterns but lacks a clear sequential workflow for building a tool end-to-end. There's no explicit 'design → implement → validate → test with LLM' workflow with checkpoints. The validation checks section lists rules but doesn't integrate them into a step-by-step process. The error handling pattern has good structure internally but the overall skill lacks a cohesive workflow with feedback loops.	2 / 3
Progressive Disclosure	Everything is in a single monolithic file with no references to external files. The content covers tool schema design, input examples, error handling, MCP, tool runners, and parallel execution all inline — much of this could be split into separate reference files. There are no bundle files and no cross-references. The Collaboration/Delegation section references other skills but doesn't link to actual files for deeper content.	1 / 3
	Total	7 / 12 Passed

Description

22%

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 a motivational introduction to a blog post rather than a functional skill description. It lacks concrete actions, has no 'Use when...' clause, and relies on vague, aspirational language ('the difference between an agent that works and one that hallucinates') instead of specifying what the skill actually does. The few relevant keywords present are buried in promotional prose.

Suggestions

Replace the philosophical opening with concrete actions, e.g., 'Designs tool schemas, writes tool descriptions, implements error handling and validation for AI agent tool-use interfaces.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when designing function-calling tools, writing tool schemas, creating MCP tools, or improving tool descriptions for AI agents.'

Remove marketing language ('the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens') and replace with specific, actionable capability statements.

Dimension	Reasoning	Score
Specificity	The description uses vague, abstract language like 'interact with the world' and 'tool design from schema to error handling.' It does not list concrete actions the skill performs—it reads more like a marketing pitch than a capability description.	1 / 3
Completeness	The 'what' is vaguely implied (covers tool design) but not concretely stated, and there is no 'when' clause or explicit trigger guidance. The absence of a 'Use when...' clause caps this at 2, and the weak 'what' brings it to 1.	1 / 3
Trigger Term Quality	It includes some relevant keywords like 'tool design,' 'schema,' 'error handling,' and 'AI agents,' but misses many natural user terms such as 'function calling,' 'API tools,' 'tool use,' 'tool definitions,' or 'MCP.' The opening sentence is more philosophical than functional.	2 / 3
Distinctiveness Conflict Risk	The mention of 'tool design' and 'schema' provides some specificity, but phrases like 'AI agents' and 'interact with the world' are broad enough to overlap with general agent-building or API design skills.	2 / 3
	Total	6 / 12 Passed

Validation

81%

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 — 9 / 11 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	9 / 11 Passed

Repository: boisenoise/skills-collections
Commit: aff357c

Reviewed: 1 day 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.