CtrlK
BlogDocsLog inGet started
Tessl Logo

scienceworld-growth-focuser

Use when you have planted a seed or need to track a plant's growth stage (sprouting, flowering, reproduction). Applies the 'focus on' action to a specific plant or biological entity to signal intent and monitor its development. Trigger after planting or when you need to observe life cycle progression in the ScienceWorld environment.

70

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tight, actionable skill body with concrete syntax and a complete worked example for the 'focus on' action. The main gap is the absence of an explicit validation/error-recovery step and no in-body pointer to the bundled reference file.

Suggestions

Add a validation checkpoint after the 'focus on' action (e.g., check the confirmation output and handle disambiguation prompts by retrying with the explicit container clause).

Link the bundled reference (trajectory_analysis.md) from the body so the rationale/reference is discoverable, or note that it is supplementary.

Trim the 'Patience is Required' and 'Prerequisites' asides into a single concise note to reduce remaining over-explanation.

DimensionReasoningScore

Conciseness

Largely lean with no padding about basic plant/seed concepts; minor explanatory asides in 'Key Considerations' ('Patience is Required', 'Prerequisites') could be trimmed.

4 / 5

Actionability

Provides the exact executable action syntax `focus on <PLANT_OBJECT> [in <CONTAINER>]`, a worked example (`focus on avocado seed in flower pot 1`), and a complete end-to-end scenario covering the common cases.

5 / 5

Workflow Clarity

Steps are clearly sequenced (Identify → Execute → Confirm & Wait) with an alternating focus/wait example, but there is no explicit validation checkpoint or error-recovery loop for handling disambiguation prompts.

4 / 5

Progressive Disclosure

Compact (~44 lines), single-purpose, and well-organized into clear sections, but the bundled reference file (trajectory_analysis.md) is not signaled or linked from the body.

4 / 5

Total

17

/

20

Passed

Description

87%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 focused, well-triggered description that clearly states both the action and when to use it for a distinct ScienceWorld mechanic. Slightly concentrated on a single action, which keeps specificity from reaching the top anchor.

DimensionReasoningScore

Specificity

Names a concrete action ("Applies the 'focus on' action to a specific plant or biological entity to signal intent and monitor its development") rather than vague language, but centers on a single core action so coverage is not fully comprehensive.

4 / 5

Completeness

Explicitly answers both what (apply the 'focus on' action to signal intent and monitor development) and when ("Use when you have planted a seed...", "Trigger after planting") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural trigger phrases ("Use when you have planted a seed", "need to track a plant's growth stage (sprouting, flowering, reproduction)", "Trigger after planting") with good synonym coverage, though a few natural variations are absent.

4 / 5

Distinctiveness Conflict Risk

Tied to a narrow ScienceWorld mechanic ('focus on' for biological growth tracking) with distinct post-planting triggers, giving it a clear niche with minimal conflict risk.

5 / 5

Total

18

/

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.