scienceworld-measurement-taker

Use when the agent needs to measure a quantitative property (temperature, weight, pH) of a target object or substance using a measurement tool. This skill covers acquiring the tool, preparing both tool and target with focus actions, executing the measurement via "use [TOOL] on [TARGET]", and interpreting the resulting value for conditional decisions such as classification or placement.

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

78%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.

A well-structured, highly actionable body with concrete commands and complete worked examples. Its main gap is progressive disclosure: the bundled reference files are orphaned rather than linked, which also hides their error-recovery and verification content that would have strengthened the workflow's validation checkpoints.

Suggestions

Link the bundle files from the body (e.g., a 'References' section pointing to references/action_glossary.md and references/decision_workflow.md) so their content is discoverable rather than orphaned.

Add an explicit validation checkpoint after 'use [TOOL] on [TARGET]' — confirm the observation contains a parseable number and, if not, follow the recovery steps already documented in references/decision_workflow.md.

Trim Example 1 by dropping the echoed environment responses and keeping only the command sequence plus the key measurement observation to cut redundant tokens.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence, but Example 1's transcript echoes every environment response ('You pick up the thermometer.') and restates the entire workflow, and 'to confirm readiness' is repeated — minor padding that could be trimmed rather than the severe verbosity of lower anchors.	4 / 5
Actionability	Every step carries a concrete command ('pick up', 'focus on [TOOL] in inventory', 'teleport to', 'use [TOOL] on [TARGET]') and the two worked examples show real observations ('The thermometer measures a temperature of 56 degrees celsius.'), covering the common classify-and-place and compare cases copy-paste ready.	5 / 5
Workflow Clarity	The 7-step sequence is clear and coherent with semi-checkpoints via the focus steps, but validation is implicit — there is no explicit check that the measurement returned a parseable value and no error-recovery loop, so it sits at 'most checkpoints present; minor validation gaps'.	4 / 5
Progressive Disclosure	Two bundle files exist (references/action_glossary.md, references/decision_workflow.md) with directly relevant material — an action glossary and an error-recovery/verification workflow — but the body never references or links either, so the references are present yet completely unsignaled and partially duplicated inline.	3 / 5
	Total	16 / 20 Passed

Description

88%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 strong description that explicitly covers both what the skill does and when to use it, with concrete environment-specific action language. Its only weaknesses are incomplete synonym coverage in trigger terms and the absence of any naming that would fully disambiguate it from generic measurement skills.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete actions covering the full task lifecycle — 'acquiring the tool, preparing both tool and target with focus actions, executing the measurement via "use [TOOL] on [TARGET]", and interpreting the resulting value for conditional decisions such as classification or placement' — matching the comprehensive-coverage anchor rather than the 'minor gaps' anchor.	5 / 5
Completeness	It opens with an explicit trigger clause ('Use when the agent needs to measure a quantitative property (temperature, weight, pH) of a target object or substance') and then clearly states what the skill does, explicitly answering both what and when with concrete trigger phrases in third-person voice.	5 / 5
Trigger Term Quality	'measure a quantitative property (temperature, weight, pH)' supplies the natural terms users would say, but common synonyms and tool names (reading, thermometer, scale, how hot/heavy) are missing, placing it at good-but-not-comprehensive keyword coverage.	4 / 5
Distinctiveness Conflict Risk	The environment-specific action patterns ('use [TOOL] on [TARGET]', 'focus actions') carve a mostly distinct niche, but the environment itself is never named, so generic measurement requests carry minor overlap risk with other skills.	4 / 5
	Total	18 / 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-measurement-taker/SKILL.md
Commit: c490239

Reviewed: 2 hours 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.