CtrlK
BlogDocsLog inGet started
Tessl Logo

alfworld-object-state-inspector

Inspects a receptacle's contents by navigating to it and reading the observation. Use when you need to check what is on or inside a receptacle (e.g., "what's on the shelf", "is the holder empty", "check the table for items"). Executes `go to {receptacle}`, parses the observation listing items present, and decides whether to take an item, search elsewhere, or proceed.

73

Quality

92%

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

88%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, actionable, well-sequenced skill body: exact commands, exact observation strings to parse, outcome-branched decisions, and an error-recovery loop, all within ~40 lines. The only weaknesses are mild duplication of observation patterns between the workflow and examples, and an orphaned references/ file that the body never links and that duplicates body content (and is truncated).

Suggestions

Reference `references/alfworld_actions_ref.md` explicitly from SKILL.md (e.g., under an 'Advanced' or 'Reference' heading) or remove it — it currently duplicates the body's observation patterns and action list and is unreachable, so a reader cannot discover it.

Fix or complete `references/alfworld_actions_ref.md`, whose 'Skill Integration in Task Flow' section ends mid-sentence with no task sequence shown.

Trim the duplication between the 'Parse contents' pattern list and the two Example scenarios (e.g., keep one canonical pattern table and let a single scenario illustrate the decision flow) to push conciseness to a 5.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — 'The environment automatically reports what is on/in the receptacle -- no additional inspection action is needed' conveys a non-obvious fact in one line, and the Error Recovery section is terse. It falls at anchor 4 rather than 5 because the observation patterns in 'Parse contents' ("On the {receptacle}, you see nothing." / "you see a {item1}, and a {item2}.") are repeated nearly verbatim in the two Example scenarios, a minor duplication that could be trimmed.

4 / 5

Actionability

Fully executable for the target environment: exact commands (`go to {target_receptacle}`, `take {item} from {receptacle}`), exact observation strings to match against, and two complete Action/Observation/Decision walkthroughs covering the empty and populated cases. This matches the anchor-5 'copy-paste ready, examples cover the common cases' standard; it is not anchor 4 because no key execution detail is missing.

5 / 5

Workflow Clarity

A clearly sequenced 4-step workflow (Navigate → Read observation → Parse contents → Decide next action) with explicit decision branches for each outcome (empty / item found / wrong items) and an Error Recovery feedback loop ('Nothing happened': the `go to` target name is invalid -- verify the receptacle name from your environment scan). This is a simple single-purpose skill, so the simple-skill exception applies and the explicit error-recovery loop satisfies the anchor-5 pattern; it is not anchor 4 because checkpoints for both success and failure outcomes are present.

5 / 5

Progressive Disclosure

The body is under 50 lines with clean sections (Workflow, Error Recovery, Example) that would merit a 5 under the simple-skill exception. However, the bundle contains `references/alfworld_actions_ref.md` which is never referenced or linked from SKILL.md, and it largely duplicates body content (observation patterns, `go to` description) and even ends mid-sentence in 'Skill Integration in Task Flow'. Scoring against the actual bundle structure, this unsignaled, partially truncated reference file is a minor organization gap, placing it at anchor 4 rather than 5.

4 / 5

Total

18

/

20

Passed

Description

91%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.

A strong description: it states concrete actions in third person, includes an explicit 'Use when' clause with natural example trigger phrases, and scopes itself to a distinct niche. The only deductions are the second-person 'you' in the trigger clause (voice penalty) and minor overlap risk with adjacent navigation/search skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Inspects a receptacle's contents by navigating to it and reading the observation', 'Executes `go to {receptacle}`', 'parses the observation', 'decides whether to take an item, search elsewhere, or proceed' — which is near the comprehensive anchor 5. However, the trigger clause 'Use when you need to check...' uses second person, which the judging guidelines penalize by reducing specificity by 1; it fits anchor 4 (several specific actions, minor gaps) after the penalty rather than 5.

4 / 5

Completeness

Explicitly answers both questions: 'what' ('Inspects a receptacle's contents by navigating to it and reading the observation... Executes `go to {receptacle}`, parses the observation') and 'when' with concrete trigger phrases ('Use when you need to check what is on or inside a receptacle (e.g., "what's on the shelf"...)'). This mirrors the anchor-5 good example structure; it is not anchor 4 because the 'when' clause is fully explicit with example queries rather than merely stated.

5 / 5

Trigger Term Quality

Provides comprehensive natural trigger phrasing users would actually say: "what's on the shelf", "is the holder empty", "check the table for items", plus the synonym pair 'on or inside a receptacle'. This matches the anchor-5 pattern of covering natural terms and synonyms (file extensions are not applicable in this domain); it is clearly above anchor 4 since no obvious common variations are missing.

5 / 5

Distinctiveness Conflict Risk

The receptacle-inspection niche is well scoped ('check what is on or inside a receptacle') with distinct observation-parsing triggers, but 'check the table for items' and generic `go to` navigation could overlap with a sibling AlfWorld search/navigation skill — minor overlap with closely related skills, matching anchor 4. It is not anchor 5 because the phrasing does not fully disambiguate from a general 'find object' or 'navigate' skill, and not anchor 3 because the core trigger is receptacle-content checking, not broadly generic.

4 / 5

Total

18

/

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.

Validation — 16 / 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.