soil-extraction

Uses a shovel tool to dig soil from the ground in outdoor environments. Execute this skill when you need to obtain soil for planting tasks and have both the shovel in inventory and access to an appropriate digging location. The skill produces soil that can then be collected and transported.

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/soil-extraction/SKILL.md

Quality

Content

77%

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

The body is actionable and clearly sequenced with concrete game commands and a validation feedback loop, scoring well on actionability and workflow clarity. It is slightly verbose in framing prose and fails to link its one external reference, capping conciseness and progressive disclosure at 2.

Suggestions

Link the trajectory reference explicitly, e.g. 'as demonstrated in the trajectory ([trajectory_excerpt.md](references/trajectory_excerpt.md))', so the provided bundle file is clearly navigable.

Trim the Purpose paragraph to one sentence and drop the out-of-scope disclaimer in Error Handling (soil preparation/planting) unless it resolves a real ambiguity.

If the trajectory excerpt is load-bearing evidence, either summarize the repeatable dig->collect pattern inline or move the 'as demonstrated in the trajectory' note next to the link rather than leaving it unanchored.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept over-explanation, but the Purpose section pads with 'It is a foundational step for planting tasks, transforming a bare outdoor location into a source of usable soil' and the Error Handling section states an out-of-scope disclaimer that adds tokens without aiding execution.	2 / 3
Actionability	Provides fully executable, specific commands ('teleport to outside', 'use shovel in inventory on ground', 'pick up soil') in a copy-paste-ready Core Procedure, matching the executable-guidance anchor.	3 / 3
Workflow Clarity	The Core Procedure is a clear three-step sequence (Navigate -> Execute Dig -> Collect Output) with an Error Handling section that supplies a feedback loop ('If no soil appears after digging, verify your location and that the shovel is correctly in your inventory'), satisfying the explicit-validation anchor for this simple skill.	3 / 3
Progressive Disclosure	Sections are well organized, but the body alludes to 'the trajectory' without linking to the actual bundle file references/trajectory_excerpt.md; a provided reference is referenced in prose yet not clearly signaled with a path, matching 'references present but not clearly signaled'.	2 / 3
	Total	10 / 12 Passed

Description

75%

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 specific, well-triggered description with a clear niche and explicit use-when guidance, but it loses a specificity point for mixing third-person capability statements with second-person ('you need') phrasing. Trigger coverage is adequate but lacks natural variations.

Suggestions

Rewrite in consistent third person to avoid the second-person penalty, e.g. 'Use when the agent needs to obtain soil for planting tasks and holds a shovel with access to a diggable outdoor location.'

Add natural trigger variations a user might actually say, such as 'dig up dirt', 'get soil for planting', or 'fill pots with soil', to broaden trigger-term coverage.

Tighten the trailing clause ('The skill produces soil that can then be collected and transported') since the core action is already stated, reducing redundancy.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('dig soil from the ground', 'produces soil that can then be collected and transported'), which would warrant a 3, but the description slips into second person ('Execute this skill when you need...', 'you have both the shovel'), so per the voice guideline specificity is reduced by 1.	2 / 3
Completeness	Explicitly answers what ('Uses a shovel tool to dig soil from the ground...produces soil that can then be collected and transported') and when ('Execute this skill when you need to obtain soil for planting tasks and have both the shovel in inventory and access to an appropriate digging location') with an explicit trigger clause.	3 / 3
Trigger Term Quality	Includes relevant natural keywords ('soil', 'planting tasks', 'dig', 'shovel', 'outdoor environments') but offers only a single phrasing of the trigger with no common variations, matching 'some relevant keywords but missing common variations' rather than broad coverage.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (shovel-based soil extraction in outdoor environments for planting) with distinct, specific triggers, making it unlikely to fire for an unrelated skill.	3 / 3
	Total	10 / 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/soil-extraction/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.