CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-install-skills

Detect and auto-install missing ToolUniverse research skills. Checks common Claude Code/Cursor/Codex skill directories for the canary file, and installs any missing skills if none found. Use when the plugin's research skills aren't loading, when migrating between clients, or when verifying a skill installation.

75

Quality

92%

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

85%

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 workflow for a simple self-contained task. The only weakness is token redundancy from restating the client directory list in three places rather than defining it once.

Suggestions

Define the set of client directories once (e.g., in the Client Detection table) and reference it from the Detection and Installation sections to avoid restating all eight paths three times.

Move the Client Detection section before Installation so the detected client drives step 2's target directory without the reader having to jump forward.

Make the installation copy step branch on detection output rather than presenting seven commented-out alternatives, which would tighten the script and reduce tokens.

DimensionReasoningScore

Conciseness

Mostly efficient with no concept over-explanation, but the eight client directory paths are repeated three times (detection ls chain, installation cp comments, and the client-detection table), which could be consolidated.

2 / 3

Actionability

Fully executable, copy-paste-ready bash: the detection chain, the sparse git clone + cp installation steps, and the post-install verification ls are all concrete commands rather than pseudocode.

3 / 3

Workflow Clarity

Clear sequence with explicit branching (file path vs NOT_INSTALLED) and a verification checkpoint after install ('Confirm success: ls .../SKILL.md'), satisfying the validation requirement for a batch cp operation.

3 / 3

Progressive Disclosure

A simple single-purpose skill (~70 lines) with no bundle files and well-organized sections (Detection, Installation, Client Detection, After Installation); self-contained structure is appropriate here.

3 / 3

Total

11

/

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.

A well-crafted description: it states concrete capabilities, gives explicit 'Use when' triggers covering realistic user situations, and is narrowly scoped to a specific plugin, minimizing conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Detect and auto-install missing ToolUniverse research skills', 'Checks common Claude Code/Cursor/Codex skill directories for the canary file', and 'installs any missing skills if none found'.

3 / 3

Completeness

Explicitly answers both what (detect/auto-install missing skills via canary-file check) and when (the 'Use when...' clause lists three concrete triggering situations).

3 / 3

Trigger Term Quality

Natural trigger scenarios a user would voice: 'research skills aren't loading', 'migrating between clients', and 'verifying a skill installation' — good coverage of plausible user phrasings.

3 / 3

Distinctiveness Conflict Risk

Scoped to a named plugin ('ToolUniverse research skills') and a canary-file convention across specific client dirs, giving it a clear niche unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.