tooluniverse-claude-code-plugin

Install the ToolUniverse Claude Code plugin in one step — provides MCP server with 1000+ scientific tools, 120+ research skills, slash commands, hooks, and the research agent. Use for first-time plugin install, troubleshooting plugin not loading, verifying MCP server connection, listing API key requirements, or configuring auto-update.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

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

The body is highly actionable with a clear, validated install workflow and good single-file organization. The only weakness is conciseness, where the maintainer section and some rationale prose could be trimmed or split out.

Suggestions

Move or condense the 'For plugin maintainers' section (release process, pip vs plugin release lines) into a separate reference file or skill, since it is not part of the user-facing install flow and inflates the token budget.

Tighten the auto-update rationale paragraphs: keep the single Python snippet and the trust-boundary note, but trim the explanatory prose that restates how background updates behave.

Consider splitting the large 'What you get' component table and API-keys detail into a referenced file so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with no pedagogical fluff, but the auto-update rationale paragraphs and the substantial 'For plugin maintainers' section add explanation that could be tightened; not every token earns its place as the score-3 anchor requires.	2 / 3
Actionability	Provides fully executable, copy-paste-ready bash and JSON (marketplace add, install, the Python auto-update snippet, .mcp.json env block) plus a numbered diagnostic script with concrete FIX actions; matches the score-3 anchor.	3 / 3
Workflow Clarity	Clear sequenced install flow with an explicit verification checkpoint ('claude plugin list' expecting 'tooluniverse (enabled)') and a numbered diagnostic checklist with validate-then-fix feedback loops, including a guard before the destructive rm -rf.	3 / 3
Progressive Disclosure	A single self-contained file with well-signaled sections (Prerequisites, Install, Verify, API keys, Troubleshooting) and one-level external references; per scoring_notes a skill with no bundle files can score 3 when well-organized.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 specific, uses natural trigger terms, answers both 'what' and 'when' explicitly, and is clearly distinguishable. Third-person voice is used throughout with no over-claims or fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions (install, troubleshoot plugin not loading, verify MCP connection, list API key requirements, configure auto-update) plus a concrete component inventory; matches the score-3 anchor and is comprehensive rather than the partial score-2.	3 / 3
Completeness	Explicitly states both what it does (one-step install providing the MCP server, skills, commands, hooks, agent) and when to use it via the 'Use for first-time plugin install, troubleshooting...' clause, matching the score-3 anchor.	3 / 3
Trigger Term Quality	Natural user phrases like 'first-time plugin install', 'plugin not loading', 'verifying MCP server connection', and 'configuring auto-update' give good coverage of terms a user would actually say; not merely technical jargon.	3 / 3
Distinctiveness Conflict Risk	Names the specific ToolUniverse plugin with distinct install/troubleshoot triggers, occupying a clear niche unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 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: 1 missing	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-claude-code-plugin/SKILL.md
Commit: 089eb8e

Reviewed: about 8 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.