CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-sdk

Build AI scientist systems with the ToolUniverse Python SDK for scientific research. Covers the 3 calling patterns (`tu.run` portable dict API, `tu.tools.X` function API, direct class instantiation), tool loading, batch execution, MCP server integration, and embedding-based tool search. Use for SDK programming, custom tool composition, benchmarking pipelines, and integrating ToolUniverse into research workflows.

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

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and highly actionable with executable examples throughout, but workflow clarity is capped by missing validation checkpoints for batch operations, and progressive disclosure is weakened by a referenced REFERENCE.md that does not exist.

Suggestions

Add explicit validation/verification checkpoints to the batch and pipeline workflows (e.g., assert expected keys before building compound_calls, check run_batch results for errors) to lift workflow_clarity past 2.

Either create the referenced REFERENCE.md (and a references/ bundle) or remove the dangling link, so progressive disclosure points to real one-level-deep material.

Consider moving the Tool Categories table and detailed Configuration/Hooks content into REFERENCE.md to keep SKILL.md as a tighter overview.

DimensionReasoningScore

Conciseness

The body is lean and code-driven with no padding or explanation of concepts Claude already knows, matching the level-3 'lean and efficient; assumes Claude's competence' anchor rather than the level-2 'could be tightened'.

3 / 3

Actionability

Fully executable, copy-paste-ready code appears throughout — install commands, quick start, batch execution, pipeline, and error handling with real imports and method names — matching the level-3 anchor.

3 / 3

Workflow Clarity

Sequencing is present (load_tools before calls, try/finally close, a Critical Notes checklist), but the batch/pipeline operations lack explicit validation checkpoints, so per the batch-operations guideline workflow_clarity is capped at 2 rather than reaching the level-3 validated-workflow anchor.

2 / 3

Progressive Disclosure

Sections are well organized and a one-level reference is signaled, but the referenced REFERENCE.md and its bundle directory do not exist, so navigation is undermined; this sits above the level-1 monolithic/nested case but below the level-3 'well-signaled one-level-deep references' anchor.

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.

The description is specific, uses natural third-person trigger phrasing, and clearly states both what the skill does and when to use it, with a distinct niche unlikely to conflict with other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — '3 calling patterns (`tu.run` portable dict API, `tu.tools.X` function API, direct class instantiation), tool loading, batch execution, MCP server integration, and embedding-based tool search' — matching the level-3 anchor rather than the partial level-2.

3 / 3

Completeness

Explicitly answers 'what' (the capability list) and 'when' via the 'Use for SDK programming...' trigger clause, satisfying the level-3 'both what AND when' anchor; the explicit 'Use for' guidance prevents the level-2 cap.

3 / 3

Trigger Term Quality

Natural user phrasing is well covered — 'SDK programming, custom tool composition, benchmarking pipelines, and integrating ToolUniverse into research workflows' — going beyond the 'some relevant keywords' of level 2; voice is third person.

3 / 3

Distinctiveness Conflict Risk

The ToolUniverse SDK niche is specific with distinct triggers unlikely to fire for unrelated skills, matching the level-3 'clear niche with distinct triggers'.

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.