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

81%

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

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise, well-organized, and appropriately uses a single shallow reference file. It is held back by actionability and workflow clarity: the extraction step stays descriptive and there are no validation checkpoints confirming the read or extraction before moving on.

Suggestions

Add a concrete extraction/check step after `read OBJ`, e.g. verify the output contains explicit 'To make...' / 'Required:' style lines before parsing, and re-read or report if it is blank.

Tighten the Example into copy-paste-ready form by showing the exact parse pattern (goal/components/procedure) applied directly to the quoted recipe output rather than restating it as prose.

Reference action_primer.md by name from within the body (e.g. in the 'Plan Next Actions' step) so the one-level-deep navigation is explicitly signaled.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding or explanation of concepts Claude already knows; every section (Purpose, When to Use, Workflow, Example) earns its place and assumes competence.	3 / 3
Actionability	Provides concrete commands such as `read OBJ`, `pick up recipe`, and `read recipe in inventory`, but the extraction guidance is procedural description rather than fully executable, copy-paste-ready instruction.	2 / 3
Workflow Clarity	A clear three-step sequence (read, extract, plan) is present, but there are no validation/verification checkpoints to confirm the read succeeded or that extraction was complete before proceeding.	2 / 3
Progressive Disclosure	As a short, single-purpose skill under 50 lines, it is well-organized into clear sections with one real one-level-deep reference (references/action_primer.md); structure is clean and easy to navigate.	3 / 3
	Total	10 / 12 Passed

Description

90%

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 well-constructed: explicit 'Use when' trigger guidance, natural trigger terms, and a clear narrow niche around inventory document reading. The only mild gap is specificity, where it names the action domain but does not list multiple distinct concrete operations.

Dimension	Reasoning	Score
Specificity	Names a domain (recipe/note/document reading via the 'read' action) and one concrete action (extracts key information), but does not enumerate multiple specific concrete actions like the anchor examples.	2 / 3
Completeness	Clearly answers both 'what' (reads a recipe/note and extracts key information) and 'when' via the explicit 'Use this skill when you have acquired...' trigger clause.	3 / 3
Trigger Term Quality	Covers natural, user-relevant terms — 'recipe', 'note', 'readable document', 'ingredient lists', 'procedural steps' — that a user would actually say, matching the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	It occupies a clear niche tied to the ScienceWorld inventory 'read' action and document-extraction triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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: 7bb9a48

Reviewed: 1 day 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.