create-tooluniverse-skill

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

Quality

58%

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

63%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.

The skill body is a lean, well-sequenced orchestration overview with real validation steps, but its actionability leans on deferred templates and its reference table names files that largely do not exist in the bundle. Fixing reference accuracy and inlining a few executable steps would materially raise quality.

Suggestions

Correct the Reference Files table to use the actual bundle paths (e.g. references/devtu_optimize_integration.md, references/implementation_agnostic_format.md, references/tool_testing_workflow.md, references/skill_standards_checklist.md, assets/skill_template/*) and reference skill_standards_checklist.md and tool_testing_workflow.md explicitly.

Inline a minimal concrete example for the highest-friction steps (e.g. a short test_tools_template.py invocation snippet and a python_implementation.py phase skeleton) so Claude can act without opening every reference.

Make the validation feedback loop explicit in Phase 6 (e.g. "If tests fail: fix in Phase 4, re-run tests, only proceed when green") to strengthen workflow_clarity.

Dimension	Reasoning	Score
Conciseness	The body is efficient: compact phase/principle tables and bullets assume Claude's competence and avoid explaining known concepts, with only minor padding (intro line and a slightly redundant Quality Indicators section) keeping it just below the leanest anchor.	4 / 5
Actionability	Guidance names concrete artifacts (python_implementation.py, test_skill.py) and specific sub-skills to invoke (devtu-create-tool, devtu-fix-tool) with durations, but the executable detail is deferred to template/reference files rather than given inline, leaving key steps incomplete.	3 / 5
Workflow Clarity	A clear 7-phase sequence with durations and an explicit validation phase (run test suite, validate against checklist, manual verification) is present, but the test-first feedback loops (fail -> fix -> retest) are implicit rather than spelled out.	4 / 5
Progressive Disclosure	The body is well-structured as an overview with a dedicated, clearly signaled Reference Files table, but most referenced filenames (OPTIMIZE_INTEGRATION.md, IMPLEMENTATION_AGNOSTIC.md, TESTING_GUIDE.md, SKILL_TEMPLATE.md, QUICKSTART_TEMPLATE.md, VALIDATION_CHECKLIST.md, PACKAGING_TEMPLATE.md, PARAMETER_VERIFICATION.md, CODE_TEMPLATES.md) do not match the actual bundle files, and two real reference files are never referenced, impairing navigation.	3 / 5
	Total	14 / 20 Passed

Description

53%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.

The description is clear and reasonably specific about what the skill does but omits any explicit trigger/"Use when" guidance, capping completeness. It is distinct within its niche yet would benefit from natural trigger phrases and synonym coverage.

Suggestions

Add an explicit "Use when..." clause naming concrete triggers, e.g. "Use when the user asks to build or scaffold a new ToolUniverse skill, author a skill from a domain, or needs a test-driven workflow for skill creation."

Broaden trigger term coverage with natural synonyms/extensions users might say (e.g. "build a skill", "scaffold", "author") rather than only "create ToolUniverse skills".

Optionally enumerate 2-3 concrete sub-actions (domain analysis, tool discovery/testing, agnostic docs) to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	"Create high-quality ToolUniverse skills following test-driven, implementation-agnostic methodology" names the domain and one concrete action (create skills) with qualifying methodology, but does not list multiple distinct concrete actions to reach comprehensive coverage.	3 / 5
Completeness	The description gives a clear "what" (create ToolUniverse skills via a test-driven, implementation-agnostic methodology) but provides no "when" / "Use when" trigger clause, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	"ToolUniverse skills" and "create ... skills" are relevant keywords, but no synonyms, variations, or natural user phrasings beyond the single domain noun, missing common variations.	3 / 5
Distinctiveness Conflict Risk	The "ToolUniverse skills" niche is mostly distinct with only minor overlap risk against closely related skill-building skills (e.g. devtu-optimize-skills, devtu-create-tool referenced in the body), fitting above the 3 anchor.	4 / 5
	Total	13 / 20 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: 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.