scienceworld-device-activator

Activates a device (e.g., blast furnace, stove) to initiate a process like heating. Use this skill when you have placed materials inside a device and need to start its operation. Takes a device name as input and outputs a confirmation of activation, enabling tasks that require energy input or material processing to progress.

Quality

83%

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

92%

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

A lean, highly actionable skill body with a clear validated workflow, weakened only by an unlinked reference file that contains useful device-specific detail not surfaced from the overview.

Suggestions

Add a one-line pointer in the body to the existing bundle, e.g., '## Device specifics — see [device_specifications.md](references/device_specifications.md) for per-device temperatures, safety protocols, and confirmation outputs.'

Consider pulling the per-device confirmation-output strings from the reference into the workflow's verify steps so activation success can be checked against exact expected text.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no explanation of concepts Claude already knows; each section (Purpose, Core Workflow, Key Actions, Example, Important Notes) earns its place and nothing is padded.	3 / 3
Actionability	Provides concrete, executable commands ('look at <DEVICE>', 'activate <DEVICE>', 'deactivate <DEVICE>', 'use thermometer on <MATERIAL>') plus a fully worked melt-lead example that is effectively copy-paste ready with appropriate placeholders.	3 / 3
Workflow Clarity	A clear 6-step sequence with explicit validation checkpoints (verify contents, confirm 'turned off', confirm 'turned on' after activation) and a reinforcing note to always verify activation succeeded; as a simple single-purpose skill this meets the bar.	3 / 3
Progressive Disclosure	The body is well-organized into clear sections, but the provided bundle file references/device_specifications.md (operating temperatures, safety protocols, confirmation outputs) is never referenced or signaled from the body, so navigation to deeper detail is missing.	2 / 3
	Total	11 / 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.

A strong, specific description with explicit what/when triggers and a clear niche, held back only by second-person voice in the trigger clause and somewhat limited keyword variation.

Suggestions

Rewrite the trigger in third person to avoid the specificity penalty, e.g., 'Use when materials have been placed inside a device and its operation must be started.'

Broaden trigger term coverage by adding common phrasings like 'turn on', 'light', or 'fire up' alongside 'activate' and 'start'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Activates a device', 'initiate a process like heating', 'Takes a device name as input', 'outputs a confirmation of activation'), which would be a 3, but the trigger clause 'Use this skill when you have placed materials' uses second-person voice, which the rubric penalizes by reducing specificity by 1.	2 / 3
Completeness	Explicitly answers what ('Activates a device (e.g., blast furnace, stove) to initiate a process like heating') and when ('Use this skill when you have placed materials inside a device and need to start its operation') with an explicit trigger clause.	3 / 3
Trigger Term Quality	Includes relevant natural terms ('activate', 'start its operation', 'heating', 'blast furnace', 'stove') but misses common variations a user might say such as 'turn on', 'light', 'fire up', or 'heat up', so coverage is good but not complete.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche (activating pre-loaded devices in a simulation) with a distinct situational trigger tied to having already placed materials inside, making it unlikely to fire for the wrong skill.	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: zjunlp/SkillNet
Path: experiments/src/skills/scienceworld/scienceworld-device-activator/SKILL.md
Commit: 7bb9a48

Reviewed: 1 day 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.