CtrlK
BlogDocsLog inGet started
Tessl Logo

alfworld-object-disposer

This skill disposes of an object by placing it into a disposal receptacle like a garbage can. It should be triggered when the task requires discarding an object (e.g., 'put it in garbagecan') and the agent is at the disposal location with the object in hand. The skill executes the 'put' action to place the object in/on the target receptacle, completing the disposal subtask.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

A lean, well-sequenced body with clear validation and error-recovery steps, but its guidance stops short of the exact executable action syntax and leaves the provided reference files unlinked. Tightening actionability and signaling the bundle would raise it further.

Suggestions

Include the exact executable action form inline — e.g. `put {obj} in/on {recep}` — so the execution step is copy-paste ready rather than just naming the 'put' action.

Link the existing reference files in the body (e.g., 'See alfworld_actions.md for the action template and common disposal receptacles') so the provided bundle is discoverable instead of orphaned.

DimensionReasoningScore

Conciseness

Roughly 20 lines with no padding and no explanation of concepts Claude already knows; every line earns its place (trigger conditions, execution steps, failure handling).

3 / 3

Actionability

It instructs to 'Perform the `put` action with the object and receptacle' but never gives the exact executable syntax (e.g., `put {obj} in/on {recep}`), which only appears in the unreferenced bundle file, leaving the guidance short of copy-paste ready.

2 / 3

Workflow Clarity

Sequences Verify Prerequisites -> Execute Disposal -> Completion with an explicit prerequisite check and a failure feedback loop ('If the disposal fails...re-evaluate the object and receptacle identifiers').

3 / 3

Progressive Disclosure

The body is cleanly sectioned, but the provided bundle files (alfworld_actions.md, trajectory_pattern.md) are never linked or signaled, orphaning useful detail such as the exact action template and receptacle list.

2 / 3

Total

10

/

12

Passed

Description

100%

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 concretely states the action, gives an explicit natural trigger phrase, and clearly answers both what the skill does and when to use it. No verbosity or over-claims.

DimensionReasoningScore

Specificity

Names the concrete action precisely — 'placing it into a disposal receptacle' and 'executes the "put" action to place the object in/on the target receptacle' — rather than vague language.

3 / 3

Completeness

Explicitly answers what ('disposes of an object...executes the put action') and when ('should be triggered when the task requires discarding an object...and the agent is at the disposal location with the object in hand') with explicit triggers.

3 / 3

Trigger Term Quality

Quotes the exact natural task phrase 'put it in garbagecan' alongside 'discarding an object', terms a user would actually say when needing this skill.

3 / 3

Distinctiveness Conflict Risk

Scoped to a clear disposal niche (garbage can / disposal receptacle) with distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.