devtu-create-tool

Create new scientific tools for ToolUniverse framework with proper structure, validation, and testing. Use when users need to add tools to ToolUniverse, implement new API integrations, create tool wrappers for scientific databases/services, expand ToolUniverse capabilities, or follow ToolUniverse contribution guidelines. Supports creating tool classes, JSON configurations, validation, error handling, and test examples.

Quality

87%

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

Quality

Content

82%Weight 40%Scale 1-5

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

A strong, actionable SKILL.md body with executable code, a clear three-step registration workflow, and well-signaled references. It loses points for repeated verification content, a time-sensitive '2026' marker, an implicit retry loop, and one orphaned bundle file.

Suggestions

Remove the time-sensitive '#1 issue in 2026' marker (and the '90% of Failures' claim) or move it to a notes/deprecated section — time-sensitive claims date the skill and penalize conciseness.

Consolidate the duplicated verification content: the inline 3-step verification script, the Quick Commands block, and the Testing checklist overlap — keep one canonical verification block and link to references/testing-guide.md for the rest.

Link references/quick-reference.md from the body's References section (or remove it from the bundle) so every bundle file is reachable via navigation.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and domain-specific (Top 7 Mistakes, two-stage architecture, code blocks) without explaining basics Claude already knows, but verification content is repeated across the Testing section, Verification Script, and Quick Commands, and the time-sensitive '#1 issue in 2026' marker adds datable noise.	4 / 5
Actionability	It provides a complete executable Python tool class, a full JSON configuration, concrete validation commands (python3 -m json.tool, py_compile, test_new_tools.py -v), and a runnable 3-step verification script — copy-paste ready examples covering the common multi-operation tool pattern.	5 / 5
Workflow Clarity	The Three-Step Registration (class -> default_config.py marked 'MOST COMMONLY MISSED' -> auto wrapper) is clearly sequenced with explicit validation checkpoints (per-step asserts, '0 failures' target) and a Top 7 Mistakes checklist, but the validate -> fix -> re-validate feedback loop is implied rather than spelled out as explicitly as the anchor-5 example.	4 / 5
Progressive Disclosure	The body is a clean overview with a dedicated References section linking one-level-deep to testing-guide, advanced-patterns, implementation-guide, and tool-improvement-checklist (all verified to exist), but the bundle file quick-reference.md is orphaned — present in references/ but never linked from the body, a minor navigation gap.	4 / 5
	Total	17 / 20 Passed

Description

92%Weight 40%Scale 1-5

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

A high-quality description that concretely states what the skill does and gives explicit, multi-trigger 'Use when' guidance scoped to the named ToolUniverse framework. The only minor gap is synonym coverage in the trigger terms.

Dimension	Reasoning	Score
Specificity	It lists multiple concrete actions — 'creating tool classes, JSON configurations, validation, error handling, and test examples' plus 'implement new API integrations, create tool wrappers' — giving comprehensive coverage of what the skill does, matching the anchor-5 level of multiple specific concrete actions.	5 / 5
Completeness	It explicitly answers both 'what' ('Create new scientific tools for ToolUniverse framework with proper structure, validation, and testing') and 'when' (a concrete 'Use when users need to...' clause listing multiple triggers), matching the anchor-5 example of clearly answering both with concrete trigger phrases.	5 / 5
Trigger Term Quality	The 'Use when...' clause covers several natural phrases users would say ('add tools to ToolUniverse', 'implement new API integrations', 'create tool wrappers', 'follow contribution guidelines'), but it stops short of the comprehensive synonym coverage of anchor 5.	4 / 5
Distinctiveness Conflict Risk	The description is anchored to a specific named framework ('ToolUniverse') with triggers all scoped to that framework, giving it a clear niche with minimal risk of firing for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: skills/devtu-create-tool/SKILL.md
Commit: 1b02920

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.