CtrlK
BlogDocsLog inGet started
Tessl Logo

scienceworld-task-parser

Analyzes user instructions in ScienceWorld environments to extract specific task requirements and constraints. Use when receiving a new task to identify required objects, target locations, and action sequences before taking any environment actions.

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

Low

Low-risk findings worth noting

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 concise, highly actionable instruction skill with a clear workflow and worked example. The main gap is that the existing reference file task_patterns.md is not referenced from SKILL.md.

Suggestions

Link references/task_patterns.md from the body (e.g., under a 'Common task patterns' section: See [task_patterns.md](references/task_patterns.md)) so the bundled reference is discoverable.

Promote the 'Verification' key principle into an explicit checkpoint in the Execute workflow (e.g., 'Confirm object state with a second look around before the core action').

Tighten a few descriptive sentences (e.g., the Target Object bullet) to reduce token overhead without losing the concrete examples.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, with concrete commands and minimal over-explanation; a few descriptive sentences could be trimmed slightly.

4 / 5

Actionability

Provides fully executable commands throughout ('look around', 'teleport to LOC', 'focus on OBJ', 'move OBJ to OBJ') plus a complete worked example with the exact command sequence.

5 / 5

Workflow Clarity

A clear Parse→Survey→Identify→Execute sequence with numbered substeps and a Verification principle, but the verification is a principle rather than an explicit validate→fix→retry checkpoint in the workflow.

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections under 50 lines, but the bundled references/task_patterns.md exists yet is never linked or signaled 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.

The description is strong: third-person, with both a clear capability statement and an explicit 'Use when' trigger, scoped tightly to ScienceWorld. Minor room to add more action synonyms for broader trigger coverage.

DimensionReasoningScore

Specificity

Names the ScienceWorld domain and several concrete actions ('extract specific task requirements and constraints', 'identify required objects, target locations, and action sequences'), with only minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what ('Analyzes user instructions...to extract specific task requirements and constraints') and when ('Use when receiving a new task...') with concrete trigger phrasing.

5 / 5

Trigger Term Quality

Includes natural trigger terms ('ScienceWorld', 'new task', 'objects', 'target locations') that a user would say, though a few synonyms or variations are missing.

4 / 5

Distinctiveness Conflict Risk

Scoped narrowly to ScienceWorld task parsing, giving it a clear niche with minimal risk of triggering for unrelated skills.

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.