CtrlK
BlogDocsLog inGet started
Tessl Logo

scienceworld-conductivity-tester

Determines if an object is electrically conductive by integrating it into a circuit and observing a light bulb. Triggered when classifying an object based on conductivity.

67

Quality

84%

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, highly actionable instruction skill whose wiring sequence and classification procedure are fully specified. Its main weaknesses are the absence of any error-recovery path around the observation step and an orphaned, incomplete references/circuit_diagram.md that the body never points to.

Suggestions

Add a brief error-recovery note to the Observe & Classify step covering ambiguous bulb state or a failed connection (e.g., re-verify the wiring sequence and re-run wait1/look around).

Either link references/circuit_diagram.md from the body (e.g., under Core Procedure step 4) and complete its dangling 'Connection Map' section, or remove the file since the body already inlines the full wiring sequence.

Trim the redundant Key Notes lines ('The observation... is critical', 'The circuit is fragile') that restate steps 4-5.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — no re-teaching of conductivity or circuits — but the Key Notes section has minor trimmable redundancy: "The observation (`look around`) after waiting is critical" restates step 5, and "The circuit is fragile; connect components in the order specified" restates the "exact sequence" instruction. This matches the 4 anchor (efficient with minor instances that could be trimmed) rather than 5's every-token-earns-its-place.

4 / 5

Actionability

Fully concrete, executable guidance for the environment's action set: an exact terminal-to-terminal wiring sequence (battery anode → orange wire terminal 1, etc.), exact commands (`focus`, `wait1` twice, `look around`), and concrete outcome routing (blue box for conductive, orange box for non-conductive). As an instruction-only skill with copy-ready specificity, it meets the 5 anchor.

5 / 5

Workflow Clarity

A clearly sequenced 5-step procedure with an explicit observation checkpoint (wait, look around, branch on bulb state) — but there is no error-recovery guidance for ambiguous bulb state, failed wiring, or an object without two terminals, which keeps it below the 5 anchor's feedback loops. The operation is neither destructive nor batch, so the cap of 3 does not apply.

4 / 5

Progressive Disclosure

Sections are well organized and the content is appropriately inlined for a sub-50-line skill, but the actual bundle structure reveals a gap: references/circuit_diagram.md is never referenced from the body and is itself incomplete (a dangling "## Connection Map" heading with no content), leaving an orphaned, partially duplicated reference file. This is the 4 anchor's "minor organization gaps" rather than the 5 anchor's well-signaled, easy navigation.

4 / 5

Total

17

/

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.

A concise, concrete, third-person description that clearly states both capability and trigger. Trigger keyword coverage is good but lacks common synonyms, and the trigger clause could enumerate more concrete phrases to reach the top anchor.

DimensionReasoningScore

Specificity

Lists several concrete actions — "determines if an object is electrically conductive", "integrating it into a circuit", "observing a light bulb" — with minor gaps (no mention of the battery or sorting outcomes). It exceeds the 3 anchor (domain plus only 1-2 actions) but is not comprehensive enough for the 5 anchor.

4 / 5

Completeness

Both what ("Determines if an object is electrically conductive by integrating it into a circuit and observing a light bulb") and when ("Triggered when classifying an object based on conductivity") are explicitly stated in third-person voice. The single trigger clause could be more specific with additional concrete phrases, so it falls short of the 5 anchor.

4 / 5

Trigger Term Quality

Natural keywords are present ("classifying", "conductivity", "electrically conductive", "circuit"), giving good coverage of what a user would say, but common synonyms like "insulator", "non-conductive", or "does it conduct" are missing, matching the 4 anchor rather than the 5 anchor's comprehensive synonym list.

4 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche — electrical conductivity classification via a circuit-and-bulb test — with distinct trigger terms, making accidental activation by unrelated skills very unlikely.

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.

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.