CtrlK
BlogDocsLog inGet started
Tessl Logo

scienceworld-heating-apparatus-setup

This skill positions a container with a substance onto a heating device (stove, oven) and activates the device. It should be triggered when a task requires melting, boiling, or heating a substance. The skill moves the prepared container to the heating element and turns it on.

64

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./experiments/src/skills/scienceworld/scienceworld-heating-apparatus-setup/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

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

The body is well-structured with a clear sequenced procedure, concrete scienceworld action patterns, and a verification step. Its main defects are references to bundled scripts (setup_heater.py, monitor_temperature.py) that do not exist in the bundle.

Suggestions

Add the missing scripts (setup_heater.py, monitor_temperature.py) to a scripts/ directory, or remove the references and inline the concrete action steps they would perform.

Add a feedback loop after the Verify Setup step (e.g., what to do if the device is not 'turned on' or the container is not listed on it) to lift workflow clarity.

Tighten the Purpose section, which restates the frontmatter description, to improve token efficiency.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete action patterns and no padding of concepts Claude already knows; the Purpose section lightly restates the description and could be trimmed.

4 / 5

Actionability

Concrete executable action patterns ('move <SUBSTANCE> to <CONTAINER>', 'activate <HEATING_DEVICE>', 'look at <HEATING_DEVICE>') cover the common cases, but the referenced bundled scripts do not exist in the bundle, leaving a gap.

4 / 5

Workflow Clarity

A clear four-step sequence with an explicit verification checkpoint (step 4, expected observation) is present; it lacks a feedback loop for what to do if verification fails, so it stops short of a 5.

4 / 5

Progressive Disclosure

Section structure is good and references/thermal_procedures.md exists, but the body directs Claude to bundled setup_heater.py and monitor_temperature.py which are absent from the bundle, creating broken navigation.

3 / 5

Total

15

/

20

Passed

Description

78%Weight 40%Scale 1-5

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 clear, third-person description that answers both what the skill does and when to trigger it using natural terms. Its main weakness is specificity: it lists only two actions and repeats them rather than broadening coverage.

DimensionReasoningScore

Specificity

Names the domain and two concrete actions ('positions a container with a substance onto a heating device', 'activates the device'), but the second sentence merely restates them rather than expanding coverage, so it is not comprehensive.

3 / 5

Completeness

It explicitly answers 'what' (positions a prepared container onto a heating element and turns it on) and 'when' with a concrete trigger clause ('It should be triggered when a task requires melting, boiling, or heating a substance').

5 / 5

Trigger Term Quality

'melting, boiling, or heating a substance' are natural terms a user would say, giving good keyword coverage, though a few synonyms (e.g., 'warming', 'cooking') are absent.

4 / 5

Distinctiveness Conflict Risk

The niche—placing a prepared container on a stove/oven and activating it—is mostly distinct with clear triggers, with only minor overlap risk against closely related scienceworld heating skills.

4 / 5

Total

16

/

20

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
zjunlp/SkillNet
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.