create-tooluniverse-skill

Create high-quality ToolUniverse skills following test-driven, implementation-agnostic methodology.

Quality

63%

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/create-tooluniverse-skill/SKILL.md

Quality

Content

77%

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

The content is concise and well-structured with a clear, validated multi-phase workflow, but its actionability relies heavily on cross-references and several of those referenced files do not actually exist in the bundle. Fixing the reference paths would meaningfully improve both actionability and progressive disclosure.

Suggestions

Correct the reference file names to match the actual bundle (e.g. 'OPTIMIZE_INTEGRATION.md' -> 'devtu_optimize_integration.md', 'TESTING_GUIDE.md' / 'PARAMETER_VERIFICATION.md' -> 'tool_testing_workflow.md', 'IMPLEMENTATION_AGNOSTIC.md' -> 'implementation_agnostic_format.md', 'VALIDATION_CHECKLIST.md' -> 'skill_standards_checklist.md') so navigation resolves.

Inline one or two concrete actionable snippets (e.g. a minimal test-script invocation or a parameter-correction example) so the skill is not fully dependent on external files for actionable detail.

Confirm that SKILL_TEMPLATE.md, QUICKSTART_TEMPLATE.md, and CODE_TEMPLATES.md either exist in assets/skill_template under their referenced names or are renamed in the body to the actual files (SKILL.md, QUICK_START.md, python_implementation.py).

Dimension	Reasoning	Score
Conciseness	The body is lean and table-driven, listing the 10 pillars and a 7-phase workflow with durations and no padding or explanation of concepts Claude already knows; every section earns its place.	3 / 3
Actionability	It names concrete tools and paths (e.g. 'devtu-create-tool', 'test_tools_template.py', '/src/tooluniverse/data/*.json'), but most detailed guidance is delegated to 'See X.md' pointers rather than giving copy-paste-ready in-skill instruction.	2 / 3
Workflow Clarity	The 7-phase workflow is clearly sequenced with explicit validation checkpoints (Phase 6: 'Run test suite, validate checklist, manual verify') and a feedback loop ('Use devtu-fix-tool if new tools fail tests'), matching the anchor for clear sequence with explicit validation steps.	3 / 3
Progressive Disclosure	The body has a well-organized 'Reference Files' table and points outward to detail files, but the referenced files (OPTIMIZE_INTEGRATION.md, TESTING_GUIDE.md, CODE_TEMPLATES.md, etc.) do not exist in the bundle; the actual reference files have different names, so navigation is broken.	2 / 3
	Total	10 / 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 concise and names a clear domain plus methodology, but it provides only one action verb and no explicit use-when trigger guidance. Adding a "Use when..." clause with natural trigger phrases would raise both completeness and trigger-term quality.

Suggestions

Add a 'Use when ...' clause with natural trigger phrases such as 'Use when creating a new ToolUniverse skill, authoring a skill, or building a tool integration.'

List multiple concrete actions instead of one verb, e.g. 'Design, test, document, and package ToolUniverse skills'.

Include natural user-facing keywords alongside the methodology jargon (e.g. 'build', 'author', 'create a skill') rather than only 'test-driven, implementation-agnostic'.

Dimension	Reasoning	Score
Specificity	The description names the domain ("ToolUniverse skills") and a methodology ("test-driven, implementation-agnostic") but offers only one concrete action ("Create high-quality ... skills"), rather than multiple specific actions.	2 / 3
Completeness	It states what the skill does but has no "Use when..." clause or equivalent trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	"ToolUniverse skills" is a relevant keyword, but "test-driven" and "implementation-agnostic" are methodology jargon rather than natural user phrasing, and common variations (e.g. "build a skill", "author a ToolUniverse skill") are missing.	2 / 3
Distinctiveness Conflict Risk	The "ToolUniverse skills" niche is reasonably distinct, but the generic "Create high-quality skills" framing could overlap with other skill-authoring skills, so it is not a fully conflict-free trigger.	2 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: skills/create-tooluniverse-skill/SKILL.md
Commit: 089eb8e

Reviewed: about 7 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.