random-number

Generate a random integer between min and max (inclusive). Use when the user asks for a random number.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%

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

The body is a model of lean, executable guidance for a simple skill: one concrete command, no padding, and clear expectations of output. Nothing material is missing for a single-purpose skill of this size.

Dimension	Reasoning	Score
Conciseness	Two lean sentences plus one executable command; no padding and no explanation of concepts Claude already knows, so every token earns its place.	3 / 3
Actionability	Provides a fully executable, copy-paste-ready command with a hardcoded script path and explicit positional arguments (<min> <max>).	3 / 3
Workflow Clarity	A simple single-task skill where the single action is unambiguous; no multi-step or destructive operation requires validation checkpoints.	3 / 3
Progressive Disclosure	Under 50 lines with no need for external references, and the body is well-organized and self-contained, satisfying the simple-skill exception for progressive disclosure.	3 / 3
	Total	12 / 12 Passed

Description

75%

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 clear, concise, and third-person with an explicit trigger, covering both what and when. It is slightly limited by a single named action and narrow trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names a concrete action ("Generate a random integer between min and max (inclusive)") with explicit parameters, but only describes a single action rather than multiple specific concrete actions like the score-3 anchor.	2 / 3
Completeness	Explicitly answers both what ("Generate a random integer between min and max (inclusive)") and when ("Use when the user asks for a random number.") with an explicit 'Use when' trigger clause.	3 / 3
Trigger Term Quality	Includes natural terms ("random number", "random integer") a user would say, but coverage is narrow and misses common variations like "random number generator", "pick a number", or "dice roll".	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche (random integer generation) with a distinct trigger unlikely to overlap with other skills.	3 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rivet-dev/sandbox-agent
Path: examples/skills-custom-tool/SKILL.md
Commit: bbc195c

Reviewed: 12 minutes ago

Table of Contents

Discovery Implementation Validation

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.