alfworld-tool-user

Use when the agent needs to apply a tool to a target object in ALFWorld to accomplish an interaction such as cleaning, heating, cooling, or examining. This skill handles locating both the tool and target object, then executing the correct environment action (e.g., `clean`, `heat`, `cool`, `use`) to progress the task.

Quality

88%

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

92%

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, fully actionable, and has a clear validated workflow for a single-purpose skill. Its only gap is progressive disclosure: existing reference bundle files are not signaled from the body.

Suggestions

Link the existing bundle files from the body (e.g., 'See [action_reference.md](references/action_reference.md) for the full verb list' and 'See [trajectory_example.md](references/trajectory_example.md) for a longer trace') so they are discoverable rather than orphaned.

Consider moving the inline command table and example trace into those reference files to keep SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is lean and ALFWorld-specific (command table, example trace, error handling) with no explanation of concepts Claude already knows; every section earns its place.	3 / 3
Actionability	Provides exact executable command syntax ('clean knife 1 with sinkbasin 1') and a full copy-paste-ready example trace, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Clear four-step sequence (Identify → Locate → Execute → Verify) with an explicit verification checkpoint ('Nothing happened' = invalid) and an error-recovery feedback loop in Error Handling.	3 / 3
Progressive Disclosure	Sections are well organized, but the provided bundle files (references/action_reference.md, references/trajectory_example.md) are never referenced or linked from the body, leaving them orphaned and content that could be split out inline.	2 / 3
	Total	11 / 12 Passed

Description

85%

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 specific, complete, and clearly scoped to an ALFWorld niche with an explicit 'Use when' trigger. Its main weakness is trigger phrasing aimed at the agent rather than natural user language.

Suggestions

Reframe the trigger in terms a user would naturally say (e.g., 'Use when the user asks to clean, heat, cool, or examine an object in ALFWorld') to lift trigger_term_quality.

Add a few common user variations of the verbs (e.g., 'wash', 'warm up') to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('clean', 'heat', 'cool', 'use', 'examine') plus the locating of both tool and target object, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (locating tool/target and executing the environment action) and when ('Use when the agent needs to apply a tool...') with an explicit trigger clause.	3 / 3
Trigger Term Quality	Contains relevant domain verbs and a 'Use when' clause, but the phrasing ('apply a tool to a target object in ALFWorld') is agent-oriented rather than natural user speech, so it has some relevant keywords but misses common user variations.	2 / 3
Distinctiveness Conflict Risk	Scoped to ALFWorld tool-on-object interactions with distinct verbs, giving it a clear niche unlikely to trigger 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/alfworld/alfworld-tool-user/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.