CtrlK
BlogDocsLog inGet started
Tessl Logo

setup-tooluniverse

Install and configure ToolUniverse for any use case — MCP server (chat-based), CLI (command line with 9 subcommands), or Python SDK (Coding API with 3 calling patterns). Covers uv/uvx setup, MCP configuration for 12+ AI clients (Cursor, Claude Desktop, Windsurf, VS Code, Codex, Gemini CLI, Trae, Cline, etc.), full CLI reference (tu list/grep/find/info/run/test/status/build/serve), Coding API quickstart, agentic tools, code executor, API key walkthrough, skill installation, and upgrading. Use when user asks how to set up ToolUniverse, which access mode to use (MCP vs CLI vs SDK), configuring MCP servers, using the CLI, troubleshooting installation, upgrading, or mentions installing ToolUniverse or setting up scientific tools. Also triggers for "how do I use ToolUniverse", "what's the best way to access tools", "command line", "tu command", "coding API", "tu build".

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

The canonical home for this skill is setup-tooluniverse in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 thorough, highly actionable multi-mode setup guide with strong workflow sequencing and validation checkpoints. Its main weaknesses are some user-facing explanatory padding and a broken/missing reference plus an unreferenced scripts bundle.

Suggestions

Remove or compress the plain-language concept explainers ('What is ToolUniverse?', 'Config files are plain text...', the uv install reassurance) since they target end-users rather than the agent and dilute token efficiency.

Fix the broken API_KEYS_REFERENCE.md reference by either adding the file to the bundle or inlining the complete key list, since the body promises it 'for the complete list with all tiers'.

Surface the existing helper scripts (check_prerequisites.py, diagnose_setup.py, verify_installation.py, list_tool_categories.py) in the body — e.g., in the troubleshooting or Common Issues sections — so the scripts/ bundle is discoverable.

DimensionReasoningScore

Conciseness

Mostly efficient executable guidance, but includes end-user-facing explainer padding ('Think of it like a universal remote', 'Config files are plain text that store settings — like a preference list', 'This is a safe, standard command...') that a capable agent could do without or tighten.

3 / 5

Actionability

Fully executable throughout — copy-paste bash commands, complete JSON MCP config, working Python snippets for all three Coding API patterns, and client-specific config file paths with access instructions.

5 / 5

Workflow Clarity

Clear Step 1→5 sequence with 'Continue to Step' markers, explicit validation (json.tool check, 'validate before restarting', uv --version), error-recovery feedback loops (Common Issues table, tooluniverse-doctor), and a Test-Together checkpoint.

5 / 5

Progressive Disclosure

Good structure with a verified one-level-deep reference (references/mcp-configs.md), but the body cites API_KEYS_REFERENCE.md which is absent from the bundle, and the provided scripts/ bundle is never referenced from the body.

4 / 5

Total

17

/

20

Passed

Description

100%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.

An exemplary description: concrete, comprehensive, and trigger-rich, clearly stating both what the skill does and when to invoke it. It avoids fluff and uses distinctive tool-specific language to minimize conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions with comprehensive coverage — 'uv/uvx setup', 'MCP configuration for 12+ AI clients', 'full CLI reference (tu list/grep/find/info/run/test/status/build/serve)', 'Coding API quickstart', 'API key walkthrough', 'skill installation, and upgrading'.

5 / 5

Completeness

Explicitly answers both 'what' (install/configure across three modes and all covered topics) and 'when' ('Use when user asks how to set up ToolUniverse... Also triggers for...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural-language triggers including exact user phrases ('how do I use ToolUniverse', 'tu command', 'coding API', 'tu build') plus synonyms (MCP vs CLI vs SDK) and access-mode variations.

5 / 5

Distinctiveness Conflict Risk

The 'ToolUniverse' proper noun and tool-specific triggers ('tu command', 'tu build') carve a clear niche with minimal overlap against other skills.

5 / 5

Total

20

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
mims-harvard/ToolUniverse
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.