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.

65

Quality

82%

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

77%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 concise, highly actionable single-purpose skill with a clear sequenced workflow and a concrete worked example. Its weaknesses are repetition of the same two pieces of advice across sections and an orphaned bundle file (references/trajectory_analysis.md) that is never referenced from the body.

Suggestions

State the "in <CONTAINER>" disambiguation rule once (e.g., in Core Instruction) and drop the duplicate mentions in Key Considerations and the closing Note.

Either add a one-level-deep, clearly signaled link to references/trajectory_analysis.md (e.g., a "## Background" section: "See [trajectory_analysis.md](references/trajectory_analysis.md) for the derivation trajectory") or remove the file from the bundle.

Trim the Quick Reference section or the Key Considerations bullets that restate the wait/patience point already covered in Core Instruction.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete, unpadded instruction, but the "in <CONTAINER>" disambiguation advice is repeated three times (Core Instruction, Key Considerations, the closing Note) and the wait/patience guidance plus the Quick Reference section restate earlier content — matching anchor 3 ("could be tightened") rather than anchor 4's "minor instances".

3 / 5

Actionability

Guidance is fully executable: the exact action syntax ("focus on <PLANT_OBJECT> [in <CONTAINER>]"), a copy-paste ready worked example ("focus on avocado seed in flower pot 1"), expected outputs ("You focus on the avocado seed.", "avocado sprout"), and the alternating focus/wait loop cover the common case — a direct match to anchor 5.

5 / 5

Workflow Clarity

The steps are clearly sequenced (Identify Target → Execute Focus → Confirm & Wait) with an explicit confirmation checkpoint and an observe-the-output feedback loop in the example; as a simple single-action skill with unambiguous guidance it meets the simple-skill exception for a 5, and the operation is neither destructive nor batch so no validation cap applies.

5 / 5

Progressive Disclosure

Sections are well organized for a short skill, but the actual bundle contains references/trajectory_analysis.md which the body never mentions or links, leaving a provided reference buried and unsignaled — matching anchor 3 ("references present but not clearly signaled") rather than the well-signaled references of anchor 4/5.

3 / 5

Total

16

/

20

Passed

Description

77%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 well-constructed description with explicit what/when structure, strong trigger phrasing, and a clearly bounded niche in the ScienceWorld domain. Its main deductions are the second-person voice ("you have planted", "you need"), which the rubric penalizes, and coverage limited to essentially one action with a few missing natural synonyms.

Suggestions

Rewrite the description in third person (e.g., "Applies the 'focus on' action... Use after planting a seed or when tracking a plant's growth stage") to avoid the second-person specificity penalty.

Broaden trigger-term coverage with natural synonyms such as "grow", "growing", "germinate", or "bloom" so users' phrasing variants match.

Consider mentioning companion actions the skill coordinates with (e.g., the follow-up `wait` pattern) to lift specificity from one action toward more comprehensive coverage.

DimensionReasoningScore

Specificity

The description names the domain and one concrete action ("Applies the 'focus on' action to a specific plant or biological entity to signal intent and monitor its development") with enumerated growth stages, matching anchor 3 — but the explicit second-person phrasing ("Use when you have planted a seed", "when you need to observe") triggers the rubric's -1 specificity penalty, reducing it to 2.

2 / 5

Completeness

It clearly answers both what ("Applies the 'focus on' action to a specific plant or biological entity to signal intent and monitor its development") and when with concrete trigger phrases ("Use when you have planted a seed or need to track a plant's growth stage... Trigger after planting"), matching anchor 5; it does not fit anchor 4 since the 'when' is already explicit and specific.

5 / 5

Trigger Term Quality

Good natural keyword coverage ("planted a seed", "growth stage", "sprouting, flowering, reproduction", "planting", "life cycle progression") that a user would plausibly say, though common variations like "grow", "germinate", or "bloom" are missing, matching anchor 4 rather than the comprehensive coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche by naming the specific action ('focus on'), the biological-entity domain, and the "ScienceWorld environment" explicitly, giving it distinct triggers with minimal conflict risk — a direct match to anchor 5.

5 / 5

Total

16

/

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.

Validation — 16 / 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.