CtrlK
BlogDocsLog inGet started
Tessl Logo

scienceworld-material-classifier

This skill makes a determination about a material's property (e.g., conductivity) based on environmental cues or domain knowledge when direct testing fails. Trigger it when experimental actions are invalid or unavailable, requiring a logical inference. It uses observed object properties and common-sense reasoning to classify the material and decide its final disposition.

60

Quality

68%

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-material-classifier/SKILL.md
SKILL.md
Quality
Evals
Security

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.

The content is a tight, actionable overview with concrete commands, a worked example, and a verification step, supported by a well-signaled one-level reference. It falls just short of top marks due to a missing error-recovery loop and an unreferenced bundled file.

DimensionReasoningScore

Conciseness

The body is lean (~30 lines) and assumes Claude's competence; minor redundancy comes from the worked example re-walking the procedure and the "When to Use" section overlapping the frontmatter description.

4 / 5

Actionability

Provides concrete executable ScienceWorld commands (`focus on`, `connect ... terminal`, `move ... to`, `look at`) plus a fully worked example; the inference step is described rather than given as a discrete command, leaving a minor gap.

4 / 5

Workflow Clarity

A clear 5-step sequence includes an explicit verify step (step 5) demonstrated in the example; no error-recovery feedback loop is present, but the operation is single-object and non-destructive so the destructive-batch cap does not apply.

4 / 5

Progressive Disclosure

The overview points one level deep to `references/material_properties.md`, clearly signaled in step 3, with the lookup content appropriately split out; the bundled `material_properties.json` is never referenced in the body, a minor organization gap.

4 / 5

Total

16

/

20

Passed

Description

62%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 clearly conveys both the skill's purpose and its trigger condition in third person, with a distinct niche. It is held back by jargon-leaning trigger terms and only moderate action specificity rather than comprehensive coverage.

Suggestions

Add a broader set of concrete actions and example properties beyond conductivity (e.g., magnetism, thermal conductivity) to lift specificity.

Include more natural user-facing trigger phrases and synonyms (e.g., "when a circuit test fails", "classify a material without testing equipment") alongside the technical wording.

Tighten the when clause with a short list of explicit triggering situations to push completeness toward a 5.

DimensionReasoningScore

Specificity

Names the domain (material property/conductivity) and a few concrete actions ("makes a determination", "classify the material", "decide its final disposition"), but coverage is not comprehensive and only conductivity is exemplified.

3 / 5

Completeness

Explicitly answers both what (determine/classify/decide disposition) and when ("Trigger it when experimental actions are invalid or unavailable"), but the when clause could be more granular with multiple concrete trigger phrases to reach 5.

4 / 5

Trigger Term Quality

Contains relevant trigger-condition language ("when direct testing fails", "when experimental actions are invalid or unavailable") but leans on specialized jargon and misses common synonyms or variations a user might naturally say.

3 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (inference-based material classification when direct testing fails) with distinct triggers; mostly distinct with only minor overlap risk against closely related skills.

4 / 5

Total

14

/

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.