CtrlK
BlogDocsLog inGet started
Tessl Logo

scienceworld-conditional-box-placer

Moves an object to one of two destination containers based on a numeric threshold check. Trigger after a measurement (e.g., temperature) is taken. Place object in 'green' box if value > threshold, or 'blue' box if value < threshold.

65

Quality

78%

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-conditional-box-placer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 concise and well-structured, but it contains a critical correctness bug in the Decision Logic (both threshold branches route to the green box, contradicting the description and example), which undermines actionability and makes the workflow ambiguous. A relevant bundle file (action_primer.md) also goes unreferenced.

Suggestions

Fix the Decision Logic branch: change 'If measurement_result < threshold: Destination is the green box' to 'blue box' so it matches the description and the example invocation thought.

Add a brief validation/verification checkpoint after the comparison (e.g., confirm the chosen box color against the threshold direction before executing the move) to remove the ambiguity and strengthen workflow clarity.

Link references/action_primer.md from the Core Workflow or Action Template section so Claude can look up the prerequisite environment actions (pick up, teleport to <LOC>) needed to get the object into inventory and reach the destination room.

DimensionReasoningScore

Conciseness

The body is lean (~30 lines), well-sectioned, and does not explain concepts Claude already knows (e.g., what a thermometer is); the only mild redundancy is the Example Invocation Thought restating the comparison, but every section earns its place, matching the 'lean and efficient; assumes Claude's competence' anchor 5.

5 / 5

Actionability

Provides concrete elements — a parameter list, an example invocation thought, and an Action Template 'move <target_object> in inventory to <green/blue> box' — but the Decision Logic section is internally contradictory: it assigns the green box for BOTH 'measurement_result > threshold' and 'measurement_result < threshold', directly conflicting with the description and example, so a key detail is wrong and the guidance cannot be reliably executed, fitting anchor 3 ('concrete guidance but incomplete; missing key details') rather than anchor 4.

3 / 5

Workflow Clarity

The Prerequisites -> Decision Logic -> Execution sequence is present and clearly ordered, but the decision step is ambiguous because both branches resolve to the green box, so the single action is not unambiguous (blocking the simple-skill exception to 5); the sequence has a content error rather than a clean validation gap, placing it at anchor 3 rather than anchor 4.

3 / 5

Progressive Disclosure

The body is well-organized under clear sections (Purpose, Core Workflow, Required Parameters, Example, Action Template) and is short enough to stand alone, but the provided references/action_primer.md — which lists the exact 'move <OBJ> to <OBJ>' action plus prerequisite primitives (pick up, teleport) the workflow depends on — is never linked from the body, a minor organization gap matching anchor 4 rather than the fully-signaled anchor 5.

4 / 5

Total

15

/

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.

The description is strong: it is written in third person, concretely states what the skill does, and provides an explicit trigger ('Trigger after a measurement is taken'). It is specific and distinctive with low conflict risk. Minor room for improvement lies only in slightly broader keyword/synonym coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Moves an object to one of two destination containers', 'numeric threshold check', 'Place object in green box if value > threshold, or blue box if value < threshold' — but they are variations of a single conditional-placement task rather than multiple distinct actions, matching the 'several specific actions; minor gaps' anchor and falling short of the comprehensive multi-action anchor 5.

4 / 5

Completeness

Clearly answers 'what' (conditional placement based on a threshold check) and explicitly answers 'when' via the concrete trigger phrase 'Trigger after a measurement (e.g., temperature) is taken', which is equivalent to a 'Use when...' clause, satisfying the anchor 5 requirement for both what and when with concrete triggers.

5 / 5

Trigger Term Quality

Includes natural domain terms 'measurement (e.g., temperature)', 'threshold', and 'box' with a synonym example provided, giving good keyword coverage though a few natural variations (e.g., 'reading', 'value') are absent — fits anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

Targets a narrow, well-defined niche — conditional object placement into green vs. blue boxes based on a numeric threshold — with distinct triggers and minimal realistic overlap with other skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.

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.