scienceworld-instruction-reader

Reads a recipe or note from the inventory using the 'read' action and extracts key information. Use this skill when you have acquired a recipe, note, or readable document in your inventory and need to extract explicit instructions, ingredient lists, or procedural steps before executing a task.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%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, actionable instruction skill with a clear workflow, weakened mainly by failing to reference the available action_primer.md bundle file.

Suggestions

Add a one-line pointer to the available action reference, e.g. 'See references/action_primer.md for the full set of available actions.', so the bundle file is discoverable.

Add a checkpoint after 'read OBJ' for when the output is missing or ambiguous (e.g., re-examine the object or try 'look around') to strengthen the workflow.

Tighten the 'Plan Next Actions' step with one concrete example of mapping extracted components to next actions, mirroring the specificity of the earlier steps.

Dimension	Reasoning	Score
Conciseness	Lean and well-organized with no padding or explanation of concepts Claude already knows; every section earns its place and assumes competence.	5 / 5
Actionability	Provides concrete commands ('read OBJ', 'pick up recipe') and a worked example with a sample output string, though the final 'Plan Next Actions' step remains somewhat high-level.	4 / 5
Workflow Clarity	Clear three-step sequence (Read, Extract, Plan) for a non-destructive single read, but lacks any checkpoint for handling missing or ambiguous document output.	4 / 5
Progressive Disclosure	Body sections are well-organized, but the existing references/action_primer.md bundle file is never signaled or linked from the body, leaving an available reference unnavigable.	3 / 5
	Total	16 / 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.

A strong, third-person description that clearly states both capability and trigger conditions with concrete natural-language terms. Minor synonym coverage gaps are the only weakness.

Dimension	Reasoning	Score
Specificity	Names the domain and the concrete 'read' action, and enumerates extraction targets (instructions, ingredient lists, procedural steps), giving several specific actions with only minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what (reads via the 'read' action and extracts key information) and when (a clear 'Use this skill when...' clause with concrete triggers), matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural terms a user would say ('recipe', 'note', 'instructions', 'ingredient lists', 'procedural steps') with good coverage, though some common synonyms (e.g., 'book', 'letter', 'scroll') are absent.	4 / 5
Distinctiveness Conflict Risk	Scoped to inventory reading of recipes/notes via the 'read' action, a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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
Path: experiments/src/skills/scienceworld/scienceworld-instruction-reader/SKILL.md
Commit: 076c6df

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.