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

88%

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

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 setup walkthrough with strong validation and troubleshooting loops, held back by over-explanation of basics Claude already knows and progressive-disclosure gaps: a broken API_KEYS_REFERENCE.md link, four orphaned bundle scripts, and reference-grade content inlined rather than split out.

Suggestions

Remove or relocate basic-concept explanations (what a config file is, how to open a terminal, 'widely used by Python developers') to tighten the body and respect Claude's competence.

Fix the broken reference: either create references/API_KEYS_REFERENCE.md and move the Tier 1/Tier 2 key tables into it, or remove the dangling link on line 245.

Wire up the four provided scripts (check_prerequisites.py, diagnose_setup.py, list_tool_categories.py, verify_installation.py) into the setup/troubleshooting steps, and move the full CLI table and prompt cheat sheet into reference files so the SKILL.md body stays an overview.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete commands and tables, but includes explanations Claude already knows — 'Config files are plain text that store settings — like a preference list for the app', terminal-opening instructions, and 'It's widely used by Python developers' — that could be trimmed without losing clarity.

3 / 5

Actionability

Fully executable throughout: copy-paste curl/uvx commands, a complete CLI subcommand table with real examples, three runnable Coding API patterns, ready-to-paste MCP JSON config blocks, and API-key tables with registration links covering the common cases.

5 / 5

Workflow Clarity

A clearly sequenced multi-step process (Step 1 choose mode -> Step 2 install uv -> CLI/SDK/MCP setup -> Step 3 keys -> Step 4 test together -> Step 5 skills) with explicit validation checkpoints ('Verify: uv --version', JSON validation before restart, test-together confirmation) and error-recovery loops via the 'If issues' and Common Issues sections.

5 / 5

Progressive Disclosure

Section structure is clear and references/mcp-configs.md is a well-signaled one-level reference, but the body references a non-existent API_KEYS_REFERENCE.md, never points to the four provided scripts/ files, and inlines large reference-grade material (full CLI table, Tier 1+2 key tables, 12-prompt cheat sheet, client config/memory tables) that belongs in separate files.

3 / 5

Total

16

/

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.

A strong, third-person description that clearly states capabilities across all three access modes and gives explicit, natural trigger phrases for when to invoke the skill. It is slightly verbose but loses nothing on specificity, completeness, trigger quality, or distinctiveness.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across all three modes — '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' — giving comprehensive coverage rather than vague domain naming.

5 / 5

Completeness

Explicitly answers both 'what' (install and configure ToolUniverse across MCP/CLI/SDK modes with a detailed coverage list) and 'when' ('Use when user asks how to set up ToolUniverse... or mentions installing ToolUniverse or setting up scientific tools') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage including synonyms and concrete commands users would actually say: 'how do I use ToolUniverse', 'what's the best way to access tools', 'command line', 'tu command', 'coding API', 'tu build', plus 'configuring MCP servers' and 'troubleshooting installation'.

5 / 5

Distinctiveness Conflict Risk

Names the specific product ToolUniverse and a clear niche (scientific database tool setup); triggers are product-specific ('tu command', 'tu build', 'tooluniverse'), so overlap with other skills is minimal.

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.