CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tooluniverse-claude-code-plugin

Install the ToolUniverse Claude Code plugin in one step — provides MCP server with 2,700+ scientific tools, 160+ 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

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 highly actionable, well-sequenced install guide with excellent verification and self-diagnosis loops — nearly everything is copy-paste executable. Its weaknesses are repetition (the same fixes appear in the sections, troubleshooting table, and diagnosis list) and the inlined maintainer-focused release-process section that serves a different audience than the install flow.

Suggestions

Deduplicate guidance that appears in multiple places: consolidate the global-skills removal and uv-shadowing fixes into the troubleshooting/diagnosis sections and drop their repeated treatments elsewhere.

Move the "For plugin maintainers" release-process section into a separate reference file (e.g. MAINTAINERS.md) referenced one level deep, keeping SKILL.md focused on the user-facing install flow.

Trim explanatory asides such as the auto-update trust-boundary rationale to a one-line note so the install path stays lean.

DimensionReasoningScore

Conciseness

Mostly efficient but with more than minor tightening opportunities: the global-skills removal guidance appears three times (dedicated section, troubleshooting table row, and diagnosis check #6), the uv-shadowing fix appears in both the table and check #3, and the auto-update trust-boundary rationale is a multi-line aside. This fits the "mostly efficient but includes some unnecessary explanation or could be tightened" anchor rather than anchor 4's "minor instances".

3 / 5

Actionability

Fully executable, copy-paste-ready commands throughout — "claude plugin marketplace add mims-harvard/ToolUniverse", "uvx --from tooluniverse tu --version" as a non-hanging server proxy, a complete .mcp.json JSON snippet, and idempotent numbered checks with explicit FIX commands. Matches the anchor for fully executable guidance covering common cases.

5 / 5

Workflow Clarity

Clear sequence (prerequisites → install → restart → "Verify it worked" with "claude plugin list") plus an explicit feedback loop in the diagnosis section ("apply the `FIX` for whatever fails, then restart Claude Code"). Matches the anchor with explicit validation steps and error-recovery loops; not 4 because checkpoints are present at each stage, and no destructive/batch cap applies.

5 / 5

Progressive Disclosure

The file is well-sectioned and the API-key list is properly deferred one level deep ("setup-tooluniverse skill → API_KEYS_REFERENCE.md"), but the "For plugin maintainers" section inlines another audience's release-process detail (auto-release workflow, version baselines, pip release line) into a user-facing install skill. That fits the anchor for content that should be separate being inline, rather than anchor 4's "minor organization gaps".

3 / 5

Total

16

/

20

Passed

Description

87%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 description: it names the product, states a concrete one-step action, inventories what the plugin provides, and gives an explicit "Use for..." clause with natural trigger phrases covering install, troubleshooting, verification, keys, and auto-update. The only weakness is that capability coverage leans on a component list rather than skill-performed actions, leaving a couple of natural trigger variants unsaid.

DimensionReasoningScore

Specificity

Quotes a concrete primary action ("Install the ToolUniverse Claude Code plugin in one step") and concrete tasks ("troubleshooting plugin not loading", "verifying MCP server connection", "configuring auto-update"), matching the anchor for several specific actions with minor gaps. Not a 5 because "provides MCP server with 2,700+ scientific tools, 160+ research skills, slash commands, hooks" enumerates components/state rather than actions the skill performs.

4 / 5

Completeness

Explicitly answers what ("Install the ToolUniverse Claude Code plugin in one step — provides MCP server with 2,700+ scientific tools...") and when ("Use for first-time plugin install, troubleshooting plugin not loading, verifying MCP server connection...") with concrete trigger phrases — the exact anchor-5 pattern; not 4 because the when-clause is fully explicit rather than merely adequate.

5 / 5

Trigger Term Quality

Natural user phrasings are well covered — "first-time plugin install", "plugin not loading", "MCP server connection", "API key requirements", "auto-update" — matching the anchor for good keyword coverage with a few natural terms missing. Not a 5 because common variants like "plugin not working", "setup", or "update the plugin" are absent.

4 / 5

Distinctiveness Conflict Risk

Names a specific product ("ToolUniverse Claude Code plugin") with a clear install/troubleshoot niche and distinct triggers, so it is unlikely to fire for the wrong skill — a clear match for the minimal-conflict-risk anchor.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.