CtrlK
BlogDocsLog inGet started
Tessl Logo

scienceworld-pot-preparer

Prepares a planting pot by moving soil from inventory into an empty or water-filled pot. Use this when setting up a growth environment for seeds or plants. It performs the 'move soil to flower pot X' action, transforming the container into a viable planting medium. This skill is atomic and can be repeated for multiple pots.

55

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./experiments/src/skills/scienceworld/scienceworld-pot-preparer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

43%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 is well-structured and concise but critically incomplete: the Core Action section promises an action that never appears, the bundled trajectory example is never referenced, and there is no validation step for this repeatable (batch) operation.

Suggestions

Complete the Core Action section by stating the exact command, e.g. `move soil in inventory to flower pot <N>`, instead of leaving "Execute the following action:" dangling.

Add a validation step confirming the pot now contains soil (e.g., check the observation returns "You move the soil to the flower pot N") before declaring the pot prepared, which is important since the skill is repeated for multiple pots.

Link to the bundled example, e.g. "See [trajectory_example.md](references/trajectory_example.md) for a multi-pot execution trace," so the reference is discoverable from the body.

DimensionReasoningScore

Conciseness

The body is lean and avoids over-explaining concepts Claude already knows, with only minor extra phrasing in the soil-acquisition example; however it is lean to the point of being incomplete rather than padded.

4 / 5

Actionability

The Core Action section reads "Execute the following action:" but no action follows, so the body itself never provides the executable command; only the prerequisites offer concrete (but partial) guidance.

2 / 5

Workflow Clarity

Prerequisites are sequenced, but the core action step is missing and there is no validation that soil actually landed in the pot; since the skill is explicitly repeatable across multiple pots (a batch operation), absent validation caps the score and the missing action pulls it further down.

2 / 5

Progressive Disclosure

The body has reasonable section structure (Instructions, Prerequisites, Core Action) and a bundle file references/trajectory_example.md exists, but the body never signals or links to that reference which contains the actual action examples.

3 / 5

Total

11

/

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.

The description is strong: third-person voice, concrete action, explicit trigger guidance, and a clearly distinct niche. It is concise yet specific, with only minor room to expand trigger scenarios.

DimensionReasoningScore

Specificity

Names the concrete action ("moving soil from inventory into an empty or water-filled pot") and even quotes the literal command ("move soil to flower pot X"), with only minor coverage gaps since the skill is intentionally atomic.

4 / 5

Completeness

Clearly states what it does and includes an explicit "Use this when setting up a growth environment for seeds or plants" trigger, but the when-clause could be more specific about concrete scenarios.

4 / 5

Trigger Term Quality

Includes natural terms a user would say ("planting pot", "soil", "growth environment for seeds or plants", "flower pot"), though a few synonyms or variations are missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a very narrow, well-defined niche (preparing a ScienceWorld flower pot with soil) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
zjunlp/SkillNet
Reviewed

Table of Contents

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.