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.

60

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./experiments/src/skills/alfworld/alfworld-object-disposer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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 tight, well-structured single-purpose skill body with real supporting reference files and a sensible verify-execute-complete sequence. Main gaps are the missing explicit success-validation checkpoint and the body not linking/signaling the available reference files.

Suggestions

Add an explicit validation checkpoint in Execution—e.g., 'Confirm the action returned success (object now in receptacle) before marking complete; if "Nothing happened", re-check identifiers per the error handling in alfworld_actions.md'.

Signal the reference files inline, e.g., under Notes add 'Action syntax and error handling: references/alfworld_actions.md; trajectory example: references/trajectory_pattern.md', so progressive disclosure is fully navigable.

Inline the exact action template `put {obj} in/on {recep}` in the Execution step so the guidance is copy-paste ready (lifts actionability toward 5).

DimensionReasoningScore

Conciseness

Lean body that assumes Claude's competence—no padding, no explanation of basic concepts, every section earns its place, matching the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

Gives the concrete action ('Perform the put action with the object and receptacle') and points to the put {obj} in/on {recep} template via the skill's own framing, but does not inline the exact command syntax or a copy-paste example, leaving minor gaps versus 'fully executable'.

4 / 5

Workflow Clarity

Steps are sequenced (verify prerequisites, execute put, completion), and there is a failure-handling note ('re-evaluate identifiers'), but there is no explicit validation checkpoint confirming the put succeeded before declaring completion; the disposal action is atomic so the sequence is clear, yet validation is only implicit.

3 / 5

Progressive Disclosure

Well-organized short sections with two real one-level-deep reference files (alfworld_actions.md, trajectory_pattern.md) that exist and are topically relevant; however the body never explicitly signals or links to these references, so navigation is good but not fully signaled.

4 / 5

Total

16

/

20

Passed

Description

66%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 clearly conveys a narrow, well-bounded disposal subtask with explicit what/when guidance and natural trigger phrases. It is slightly limited in action breadth (single put action) and could add a couple of common disposal synonyms.

Suggestions

Add a couple of natural trigger synonyms (e.g., 'discard', 'dispose of') to broaden trigger_term_quality toward comprehensive coverage.

Tighten the 'when' clause—'triggered when the task requires discarding an object (e.g. ...)' and the precondition can be stated more concisely to lift completeness to 5.

DimensionReasoningScore

Specificity

Names the domain (disposal via receptacle) and one concrete action ('put' to place object in/on receptacle), but coverage is narrow—only the final put action is described, mirroring the 'domain + 1-2 actions but not comprehensive' anchor.

3 / 5

Completeness

Explicitly answers both what ('disposes of an object by placing it into a disposal receptacle...executes the put action') and when ('triggered when the task requires discarding an object...and the agent is at the disposal location with the object in hand'); the when could be slightly more concise but is concrete, matching 'has both what and when; when could be more explicit/specific'.

4 / 5

Trigger Term Quality

Includes natural trigger phrases a user would say ('put it in garbagecan', 'throw away the X') plus the receptacle term; a few common synonyms or alternative disposal phrasings are missing, fitting 'good keyword coverage; a few natural terms missing'.

4 / 5

Distinctiveness Conflict Risk

Scoped to a narrow disposal niche with explicit precondition (object in hand, at receptacle) and explicit boundary that acquisition/navigation are separate skills, leaving only minor overlap risk with closely related put/place skills.

4 / 5

Total

15

/

20

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.