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

Passed

No findings from the security scan

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.

The body is highly actionable with a clear, validated multi-step workflow and good progressive-disclosure structure. Its main weakness is conciseness — it over-explains a few concepts Claude already knows — plus a broken in-body reference to a non-existent API_KEYS_REFERENCE.md and unused script bundle files.

Suggestions

Remove or shrink hand-holding prose that Claude doesn't need (e.g., the 'What is ToolUniverse?' analogy, 'Config files are plain text...', and the 'safe, standard command' reassurance after the uv install curl) to tighten the conciseness score.

Fix or remove the broken [API_KEYS_REFERENCE.md](API_KEYS_REFERENCE.md) link — either add the file to the bundle or point the inline Tier 1/2 tables to references/mcp-configs.md or another existing file.

Reference the four scripts/ files (check_prerequisites.py, diagnose_setup.py, list_tool_categories.py, verify_installation.py) from the relevant setup steps so the bundled tooling is discoverable instead of orphaned.

DimensionReasoningScore

Conciseness

The ~430-line body is mostly efficient but contains several explanations Claude does not need — e.g., 'Config files are plain text that store settings — like a preference list for the app', 'This is a safe, standard command that downloads and installs uv', and the 'What is ToolUniverse?' plain-language analogy. These passages could be trimmed without losing clarity.

3 / 5

Actionability

Fully executable guidance throughout — copy-paste bash install commands, complete JSON MCP config blocks, three concrete Python calling patterns, a CLI subcommand table with working examples, config file locations with access paths, and env-var setup commands covering all common cases.

5 / 5

Workflow Clarity

A clearly sequenced Step 1–Step 5 flow with explicit validation checkpoints — 'Verify: uv --version', JSON validation via 'python3 -m json.tool', the 'do it WITH the user' test-together step, and error-recovery guidance ('A trailing comma... is the usual cause') plus the 'tooluniverse-doctor' health check.

5 / 5

Progressive Disclosure

SKILL.md acts as a guided overview with one-level-deep references (references/mcp-configs.md exists and is cleanly signaled) and sibling skills, with most content appropriately placed. Below 5 because the body references [API_KEYS_REFERENCE.md](API_KEYS_REFERENCE.md) which does not exist in the bundle, and the provided scripts/ (check_prerequisites.py, diagnose_setup.py, list_tool_categories.py, verify_installation.py) are 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.

The description is exemplary: it names the product, enumerates concrete capabilities across all three access modes, lists specific clients and CLI subcommands, and provides both a 'Use when...' clause and explicit natural-language trigger phrases. It is comprehensive yet free of vague fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions with comprehensive coverage — 'Install and configure', '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', 'agentic tools, code executor', 'API key walkthrough', 'skill installation', 'upgrading'.

5 / 5

Completeness

Explicitly answers both 'what' (install and configure ToolUniverse across MCP/CLI/SDK with enumerated coverage) and 'when' via a clear 'Use when...' clause plus an 'Also triggers for...' line with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms and exact user phrases — 'how do I use ToolUniverse', 'what's the best way to access tools', 'command line', 'tu command', 'coding API', 'tu build', plus 'set up ToolUniverse', 'configuring MCP servers', 'troubleshooting installation'.

5 / 5

Distinctiveness Conflict Risk

Product-specific name 'ToolUniverse' with distinct triggers ('tu command', 'tu build', 'MCP vs CLI vs SDK') carves a clear niche with minimal conflict risk 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.