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

90%

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%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 excellent on conciseness, actionability, and workflow clarity, with executable commands and a clear validated workflow. The main gap is progressive disclosure: two bundle reference files are present but never linked from the body, while their content is inlined.

Suggestions

Replace the inlined interaction table with a pointer to references/action_reference.md (e.g., "See [action_reference.md](references/action_reference.md) for the full command matrix") and keep only a brief inline summary.

Move or cross-link the worked trajectory to references/trajectory_example.md so the body stays a concise overview and the bundle file is actually reachable.

Add a short 'References' section at the bottom of the body listing each bundle file with a one-line description so navigation is explicitly signaled.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient — a compact command-syntax table, short error-handling bullets, and one minimal trajectory example — with no padding or explanation of concepts Claude already knows, matching the score-5 anchor; it does not drift down to 4 because there are no meaningful instances of over-explanation to trim.	5 / 5
Actionability	Provides fully executable, copy-paste-ready commands (`clean {obj} with {tool}`, `take {object} from {receptacle}`) and a complete worked trajectory covering the common case, matching the score-5 anchor.	5 / 5
Workflow Clarity	Presents a clear four-step sequence (Identify Requirements → Locate and Acquire → Execute Interaction → Verify Outcome) with an explicit validation checkpoint ("Check the environment observation"; "Nothing happened" means invalid) and error-recovery feedback loops, matching the score-5 anchor.	5 / 5
Progressive Disclosure	The body is well-sectioned for a simple skill, but bundle files exist (references/action_reference.md, references/trajectory_example.md) that are never referenced or linked from the body while overlapping content is inlined (the action table and example trajectory), matching the score-3 anchor ("references present but not clearly signaled; content that should be separate is inline"); not a 4 because the duplicate inlined content has a natural home in the bundle files, and not a 2 because the in-body structure is genuinely organized.	3 / 5
	Total	18 / 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, explicit what-and-when, and scoped to a clear ALFWorld niche with concrete interaction verbs. Minor improvements would come from more comprehensive action enumeration and a few more synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ("locating both the tool and target object, then executing the correct environment action (e.g., `clean`, `heat`, `cool`, `use`)"), with only minor coverage gaps, matching the score-4 anchor; not a 5 because it does not comprehensively enumerate all interaction types in the description itself.	4 / 5
Completeness	Explicitly answers both what ("handles locating both the tool and target object, then executing the correct environment action") and when ("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") with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Includes natural interaction terms users would say ("cleaning, heating, cooling, or examining" plus "clean, heat, cool, use") giving good keyword coverage, but misses some common synonyms/variations, so it sits at the score-4 anchor rather than 5.	4 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche ("apply a tool to a target object in ALFWorld") with distinct interaction triggers, giving minimal conflict risk with other skills, matching the score-5 anchor.	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/alfworld/alfworld-tool-user/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.