scienceworld-tool-fetcher

This skill locates and picks up a specified tool or instrument from the environment. It should be triggered when a task requires a specific tool (e.g., thermometer, stopwatch) for measurement or manipulation. The skill identifies the tool's location via observation and executes a pick-up action, moving the tool to inventory.

Quality

79%

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-tool-fetcher/SKILL.md

Quality

Content

75%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, actionable instruction-only skill with a clear sequenced workflow and an explicit pick-up verification step. Main gaps are minor over-explanation and the failure to link the provided reference bundle files from the body.

Suggestions

Link the existing reference files from the body (e.g., 'See environment_actions.md for the full action reference and common tool locations') so progressive disclosure is explicit rather than implicit.

Trim low-value lines such as 'Confirm the exact name of the tool object' and the redundant 'Primary Goal' restatement to tighten token efficiency.

Fold the 'Tool Not Found' retry loop into the main numbered workflow as an explicit feedback step rather than only mentioning it under constraints.

Dimension	Reasoning	Score
Conciseness	Largely lean and action-oriented, using concrete environment commands directly with little padding; not a 5 because a few lines ('Confirm the exact name of the tool object', restating the goal under Primary Goal) could be trimmed without losing clarity.	4 / 5
Actionability	Provides concrete, executable commands (`teleport to [ROOM_NAME]`, `look around`, `look at [CONTAINER]`, `pick up [TOOL_NAME]`) with a worked example (`pick up thermometer`); not a 5 because guidance relies on placeholder templates rather than fully copy-paste-ready coverage of common cases.	4 / 5
Workflow Clarity	Clear four-step sequence with an explicit verification checkpoint ('Verify the action was successful by checking the observation') and a retry feedback loop in 'Tool Not Found'; not a 5 because the recovery loop is described in constraints rather than woven into the main flow as a checklist.	4 / 5
Progressive Disclosure	Well-organized into clearly labeled sections appropriate for a simple under-50-line skill; not a 5 because bundle references (environment_actions.md, trajectory_analysis.md) exist but are never signaled or linked from the body, leaving their relationship to the skill implicit.	4 / 5
	Total	16 / 20 Passed

Description

83%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 concretely states what the skill does and when to trigger it, with good natural trigger terms and concrete tool examples. Minor room to improve keyword breadth and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete actions ('locates and picks up', 'identifies the tool's location via observation', 'executes a pick-up action, moving the tool to inventory'), with only minor coverage gaps; not a 5 because all actions describe a single fetch operation rather than a comprehensive action set.	4 / 5
Completeness	Explicitly answers both what ('locates and picks up a specified tool...executes a pick-up action, moving the tool to inventory') and when ('It should be triggered when a task requires a specific tool (e.g., thermometer, stopwatch)') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keyword coverage with concrete examples users would say ('tool', 'instrument', 'thermometer', 'stopwatch', 'measurement', 'manipulation'); not a 5 because the synonym/variation set is narrow and lacks broader natural phrasings.	4 / 5
Distinctiveness Conflict Risk	Mostly distinct niche (fetching a specified tool from a game environment) with specific triggers; not a 5 because 'tool or instrument for measurement or manipulation' could still overlap with related ScienceWorld skills.	4 / 5
	Total	17 / 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-tool-fetcher/SKILL.md
Commit: 076c6df

Reviewed: 6 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.