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.

Quality

76%

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

Fix and improve this skill with Tessl

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

Quality

Content

63%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 presents a clear, well-sequenced procedure with concrete action patterns and a useful, real one-level-deep reference file. Its biggest defect is that both scripts it instructs the agent to use are missing from the bundle, which undermines actionability and leaves the reference structure partially dangling.

Suggestions

Ship `setup_heater.py` and `monitor_temperature.py` in a `scripts/` directory, or remove the script references and inline the action patterns as the canonical procedure.

Fix the wording "reliable, error-prone steps (1-4)" — as written it claims the script is for error-prone steps; presumably 'error-free' is intended.

Trim the Purpose section, which duplicates the frontmatter description, and add a brief recovery action for the case where the Verify Setup observation does not match (e.g., re-move the container or re-activate the device).

Dimension	Reasoning	Score
Conciseness	The body is lean overall — terse action patterns like `move <SUBSTANCE> to <CONTAINER>` and compact notes — but the Purpose section restates the frontmatter description almost verbatim and labels like "High Freedom Decision:" add little, giving minor instances of padding rather than the fully lean top anchor.	4 / 5
Actionability	Concrete action patterns are given for every step (e.g., `activate <HEATING_DEVICE>`, `look at <HEATING_DEVICE>` with an expected observation), but the body twice directs the reader to bundled scripts — "Use the bundled `setup_heater.py` script for reliable, error-prone steps (1-4)" and "Use the bundled `monitor_temperature.py` script" — and neither file exists in the bundle, leaving key executable guidance incomplete.	3 / 5
Workflow Clarity	The four-step Core Procedure is clearly sequenced and includes an explicit verification step ("Verify Setup:... Expected Observation: The device is 'turned on' and the container is listed as being on it"), plus error-recovery guidance (teleport if items are not visible). It falls short of a 5 because there is no loop for what to do if verification fails — failure recovery only covers item discovery.	4 / 5
Progressive Disclosure	Sections are well organized and the reference to `references/thermal_procedures.md` is real, one level deep, and clearly signaled, but scoring against the actual bundle reveals two of the three referenced paths (`setup_heater.py`, `monitor_temperature.py`) do not exist, leaving navigation partially broken and the structure only adequately organized.	3 / 5
	Total	14 / 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 solid description that explicitly covers both what the skill does and when to use it, with natural trigger verbs and an appropriately narrow niche. Its main weaknesses are repetitive phrasing of the same two actions and slightly thin synonym coverage for triggering terms.

Dimension	Reasoning	Score
Specificity	The description names the domain and concrete actions — "positions a container with a substance onto a heating device (stove, oven) and activates the device" — but the second sentence ("moves the prepared container to the heating element and turns it on") merely restates the same two actions rather than broadening coverage, matching the anchor for 1-2 concrete actions without comprehensiveness.	3 / 5
Completeness	Both questions are explicitly answered: the 'what' ("positions a container with a substance onto a heating device... and activates the device") and an explicit 'when' with concrete trigger phrases ("triggered when a task requires melting, boiling, or heating a substance"), matching the top anchor. A 4 would require the 'when' to be less explicit, which it is not.	5 / 5
Trigger Term Quality	"It should be triggered when a task requires melting, boiling, or heating a substance" provides good natural-verb coverage, but common variations users might say (melt, warm up, cook, boil water) are missing, fitting 'good keyword coverage; a few natural terms missing' rather than the comprehensive synonym coverage of a 5.	4 / 5
Distinctiveness Conflict Risk	The niche is fairly distinct — apparatus setup for melting/boiling/heating on a stove or oven with clear device-specific triggers — with only minor overlap risk against closely related cooking or temperature-measurement skills, fitting 'mostly distinct; minor overlap risk'.	4 / 5
	Total	16 / 20 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-heating-apparatus-setup/SKILL.md
Commit: 358ec82

Reviewed: 8 days 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.