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

73%

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/devtu-optimize-skills/SKILL.md

Quality

Content

62%

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

A well-organized, highly actionable skill body with a clear validated workflow and real bundle files. Its main weaknesses are conciseness (long inline templates and tables that duplicate reference material) and actionability (code templates are scaffolds with placeholders rather than executable examples).

Suggestions

Move the full computational-procedure and download-and-process templates (Patterns 14-15) into references/optimization-patterns.md, leaving only a one-line pointer and the key rules in SKILL.md.

Replace bracketed-placeholder Python templates with at least one complete, runnable example using real inputs so the guidance is copy-paste ready.

Consolidate the Common Anti-Patterns and Quick Fixes tables (which partly restate Pattern fixes) into the reference file to reduce inline duplication.

Dimension	Reasoning	Score
Conciseness	The body is dense and information-rich but long (230+ lines) with repeated tables and inline templates that could live in references; while not padded with concepts Claude already knows, it could be tightened by moving the full computational-procedure and download templates out of the main file.	2 / 3
Actionability	Provides many concrete commands (e.g. `python3 -m tooluniverse.cli run`, `get_tool_info()`) and code templates, but the inline Python templates are skeleton/pseudocode with bracketed placeholders rather than fully executable, copy-paste-ready examples.	2 / 3
Workflow Clarity	Presents a clearly sequenced Phase -1 through Phase 3 workflow with validation checkpoints (tool verification before calls, fallback chains, retry-vs-fix distinction, mandatory checklists), matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	References to the four bundle files are present and real, but the body still inlines substantial detail (Patterns 14-15, full templates, anti-pattern and quick-fix tables) that overlaps with or could be deferred to optimization-patterns.md; signaling is adequate but the split is not as clean as a one-level-deep overview.	2 / 3
	Total	9 / 12 Passed

Description

85%

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 description that explicitly covers both what and when, with concrete named patterns and a clear niche. Trigger term quality is the weakest area — the natural-language triggers a user would actually say are generic compared to the internal pattern jargon.

Suggestions

Add more natural user-spoken trigger phrasings (e.g. 'Use when a skill's report is too short, lacks evidence, or returns no data') alongside the pattern jargon so triggers match how users actually phrase requests.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('reviewing skills, improving existing skills, or creating new ToolUniverse research skills') and names specific patterns ('tool verification, foundation data layers, disambiguation-first, evidence grading, quantified completeness, and report-only output'), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers both what ('Optimize ToolUniverse skills... Apply patterns like...') and when with an explicit 'Use when reviewing skills, improving existing skills, or creating new ToolUniverse research skills' clause, satisfying the explicit-trigger anchor.	3 / 3
Trigger Term Quality	Includes some natural terms ('reviewing skills', 'improving existing skills', 'creating new skills'), but these are broad; it lacks the specific trigger phrasings a user would naturally say, leaning on internal jargon like 'disambiguation-first' and 'foundation data layers'.	2 / 3
Distinctiveness Conflict Risk	Scoped to a clear niche ('ToolUniverse research skills') with distinct optimization patterns, making it unlikely to trigger for unrelated skills; conflicts are minimal.	3 / 3
	Total	11 / 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/devtu-optimize-skills/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.