scienceworld-process-monitor

This skill observes the state of an active apparatus and its contents to track progress. Use when you need to periodically check for state changes (e.g., solid to liquid) during a heating or reaction process. The skill uses 'look at' or 'examine' actions on the apparatus and substance.

Quality

96%

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.

The body is concise, actionable, and presents a clear monitored workflow with a feedback loop. Its main gap is that the bundled reference file is not surfaced from the overview, weakening progressive disclosure.

Suggestions

Add a one-line link to the bundled reference, e.g. under Procedure: 'See [state transitions](references/state_transitions.md) for common observable state changes.'

Reference the state-transition table when interpreting examine output (step 3) so the reference is integrated into the workflow rather than orphaned.

Dimension	Reasoning	Score
Conciseness	The ~25-line body is lean with no padding and no explanation of concepts Claude already knows; every line (procedure, example, scope note) earns its place.	3 / 3
Actionability	Gives concrete executable game actions ('look at <APPARATUS>', 'examine <SUBSTANCE>', 'activate <APPARATUS>', 'wait') and an example with real observed outputs, not pseudocode.	3 / 3
Workflow Clarity	A clear numbered sequence with conditional branches and a feedback loop (step 4: 'If no change, use wait then repeat from step 1') plus a state-comparison checkpoint; the read-only monitoring task is non-destructive so no destructive-ops cap applies.	3 / 3
Progressive Disclosure	The body is well organized into sections, but references/state_transitions.md exists yet is never linked or signaled from SKILL.md, leaving a one-level-deep reference without clear navigation.	2 / 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.

The description is concise, third-person, and explicitly states both what the skill does and when to use it with natural trigger terms. Concrete actions and a distinct niche keep it well above the anchors for vague or generic descriptions.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'observes the state of an active apparatus and its contents to track progress' and 'uses 'look at' or 'examine' actions' — going beyond a single domain action to specific commands.	3 / 3
Completeness	Explicitly answers both what ('observes the state of an active apparatus and its contents to track progress') and when ('Use when you need to periodically check for state changes during a heating or reaction process') with an explicit trigger clause.	3 / 3
Trigger Term Quality	Includes natural trigger phrasing a user would say — 'periodically check for state changes (e.g., solid to liquid)' and 'during a heating or reaction process' — covering the common variations of process monitoring.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — monitoring apparatus state changes in a ScienceWorld-style environment — with triggers tied to heating/reaction processes that are unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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-process-monitor/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.