devtu-optimize-skills

Optimize ToolUniverse skills for better report quality, evidence handling, and user experience. Apply patterns like tool verification, foundation data layers, disambiguation-first, evidence grading, quantified completeness, and report-only output. Use when reviewing skills, improving existing skills, or creating new ToolUniverse research skills.

Quality

88%

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

85%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 well-structured, actionable body that sequences a multi-phase workflow with validation and feedback loops and cleanly offloads detail to verified reference files. It is slightly verbose in the Pattern 14/15 inline expansions and has minor template placeholders.

Suggestions

Move the full Pattern 14 and Pattern 15 inline detail (interpretation tables, download-URL tables, computational-procedure templates) into a references file, keeping only a one-line summary and link in SKILL.md to tighten conciseness.

Replace bracketed template placeholders like `[Name]`, `[When to use this]`, and `[exact download page URL]` with at least one fully worked concrete example so the guidance is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Dense tables and terse bullets keep the body efficient with no basic-concept padding, though the Pattern 14/15 sections repeat some detail that could be consolidated into the references files.	4 / 5
Actionability	Provides concrete commands (`python3 -m tooluniverse.cli run`, `get_tool_info()`), working code templates, and interpretation tables mapping values to meaning, with only minor placeholder gaps in templates like `[Name]`.	4 / 5
Workflow Clarity	Phases -1 through 3 are explicitly sequenced with validation (tool verification before calls), fallback chains (Primary -> Fallback 1 -> Fallback 2 -> document unavailable), and a test-first feedback loop (test -> fix -> 100% pass -> complete).	5 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references to four real, present files (optimization-patterns.md, testing-standards.md, case-studies.md, checklists.md) and an organized Additional References section.	5 / 5
	Total	18 / 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 strong, complete description that names a clear niche and concrete actions with explicit 'Use when' triggers. The only soft spot is trigger-term quality, where terms are domain-specific rather than broadly natural.

Suggestions

Broaden trigger terms beyond the ToolUniverse niche with more general phrasings like 'Use when a research skill produces shallow reports, unreliable tool calls, or missing evidence' to catch users who don't name the platform.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete pattern actions ('tool verification, foundation data layers, disambiguation-first, evidence grading, quantified completeness, and report-only output') providing comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (optimize skills / apply named patterns) and 'when' ('Use when reviewing skills, improving existing skills, or creating new ToolUniverse research skills') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ('reviewing skills, improving existing skills, or creating new ToolUniverse research skills') with synonym coverage, though the terms are tied to a niche domain rather than everyday vocabulary.	4 / 5
Distinctiveness Conflict Risk	The narrow 'ToolUniverse research skills' niche has distinct triggers and minimal conflict risk with other generic skills.	5 / 5
	Total	19 / 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/devtu-optimize-skills/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.