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%

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 guide with strong validation checkpoints, but it carries a lot of inline reference-style content in SKILL.md that would benefit from being moved into reference files, and it contains a broken internal link to a non-existent API_KEYS_REFERENCE.md.

Suggestions

Move the 12-item Prompt cheat sheet, the full Common Issues table, and the Team / Project-Level Setup section into dedicated reference files (e.g. references/prompts.md, references/troubleshooting.md, references/team-setup.md), leaving SKILL.md as a lean overview with one-level-deep pointers — this addresses both conciseness and progressive_disclosure.

Create the missing references/API_KEYS_REFERENCE.md file that Step 3 links to (or repoint the link to a real file), so the "See API_KEYS_REFERENCE.md for the complete list" navigation resolves instead of dead-ending.

Trim explanatory asides that restate things Claude already knows — e.g. the parenthetical "(This is a safe, standard command that downloads and installs `uv`…)" and the "Config files are plain text that store settings — like a preference list for the app" passage — to reclaim tokens without losing actionability.

DimensionReasoningScore

Conciseness

The ~420-line body is dense and actionable rather than fluffy, but it is long and includes content that could be tightened or offloaded — the 12-item "Prompt cheat sheet", the full "Common Issues" table, the "Team / Project-Level Setup" section, and mild padding like "This is a safe, standard command that downloads and installs `uv`, a small package manager" and the plain-language explanation of what config files are.

2 / 3

Actionability

Fully executable guidance throughout: the `curl -LsSf …/install.sh | sh` uv install, `uvx --from tooluniverse tu …` commands with real examples, all 9 CLI subcommands with concrete invocations, three complete Python Coding-API patterns, copy-paste JSON MCP config, and `export NCBI_API_KEY=…` shell snippets.

3 / 3

Workflow Clarity

Clear Step 1→5 sequence (choose mode → install uv → setup per mode → API keys → test together → skills) with explicit validation checkpoints: `uv --version`, `python3 -m json.tool < <config> > /dev/null && echo "JSON OK"`, the test-together checks, and a `tooluniverse-doctor` health-check feedback loop for error recovery.

3 / 3

Progressive Disclosure

Sections are well-organized and one real one-level-deep reference exists (`references/mcp-configs.md`, signaled via "See [references/mcp-configs.md]"), but the body is largely monolithic with inline content that should be split out (CLI subcommand table, prompt cheat sheet, common-issues table), and the inline `[API_KEYS_REFERENCE.md](API_KEYS_REFERENCE.md)` link points to a file that does not exist in the bundle.

2 / 3

Total

10

/

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.

An exemplary description: third-person voice, concrete capabilities across all three access modes, explicit "Use when…" triggers, and natural phrasings a user would actually say. It is long but every clause names a specific capability or trigger rather than padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across three modes — "MCP server (chat-based), CLI (command line with 9 subcommands), or Python SDK (Coding API with 3 calling patterns)" plus uv/uvx setup, "MCP configuration for 12+ AI clients", "full CLI reference (tu list/grep/find/info/run/test/status/build/serve)", API key walkthrough, skill installation, and upgrading.

3 / 3

Completeness

Explicitly answers both: what it does ("Install and configure ToolUniverse for any use case…") and when to use it ("Use when user asks how to set up ToolUniverse, which access mode to use…"), with an explicit "Also triggers for…" clause.

3 / 3

Trigger Term Quality

Strong coverage of natural user phrasings: "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", and "troubleshooting installation" — all things a user would naturally say.

3 / 3

Distinctiveness Conflict Risk

Tightly scoped to ToolUniverse via distinctive triggers ("ToolUniverse", "tu command", "tu build", "tu list/grep/find/info/run/test/status/build/serve"); unlikely to fire for an unrelated skill.

3 / 3

Total

12

/

12

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.