CtrlK
BlogDocsLog inGet started
Tessl Logo

scienceworld-object-retriever

Acquires a specified object by moving it from the environment into the agent's inventory using 'pick up OBJ'. Use this skill when a task requires an object to be manipulated, tested, or transported and it is not yet in your inventory. Makes the object available for further actions like testing, measuring, or placing.

68

Quality

85%

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

85%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.

An excellent example of a lean, fully actionable instruction-only skill: exact commands, a complete worked example, an explicit verification step, and error-recovery guidance. The one real defect is that the provided bundle file references/action_primer.md is orphaned — never referenced from the body — leaving its supporting content undiscoverable and partially duplicated inline.

Suggestions

Add an explicit pointer to the bundle file, e.g. under Important Notes: 'For the full action reference (examine, open, look at) and common object locations, see [references/action_primer.md](references/action_primer.md)'.

De-duplicate the inline `examine`/`open OBJ` guidance in Important Notes by summarizing the recovery path in one line and deferring detail to action_primer.md, which already covers those actions plus `look at OBJ` and location patterns.

Trim the redundant first Important Notes bullet ('Ensure you are in the correct room...') since Core Workflow step 1 already states this, tightening conciseness to a 5.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — no concept explanations, no padding, just commands and a worked example. It stops short of anchor 5 because of minor redundancy: the first Important Notes bullet ("Ensure you are in the correct room before attempting pick up. Use teleport to LOC if necessary") restates Core Workflow step 1, and the Purpose section repeats the frontmatter description.

4 / 5

Actionability

Every step is an executable command with exact syntax (`teleport to LOC`, `look around`, `pick up metal fork`, `examine table`, `open OBJ`), and the Example section is a complete copy-paste-ready trace including the expected observation output ("You move the metal fork to the inventory."). This matches anchor 5's 'fully executable; specific examples cover the common cases'.

5 / 5

Workflow Clarity

The four-step sequence (Navigate → Survey → Acquire → Verify) includes an explicit validation checkpoint — "Check the observation feedback confirms 'You move the [object] to the inventory.'" — and the Important Notes provide error-recovery feedback loops for the failure cases (object not visible → `examine` furniture/containers; closed container → `open OBJ` first). This is a simple, non-destructive skill, so the simple-skill exception applies and anchor 5 is the best fit.

5 / 5

Progressive Disclosure

The body itself is well-organized into clean sections (which would merit 5 for an under-50-line skill with no external files), but the bundle provides references/action_primer.md containing supporting actions (`look at OBJ`, common object locations) that the body never mentions or links to — a bundle file with no navigation path from SKILL.md. Additionally, the body partially duplicates the primer's content (the `examine`/`open` guidance) while omitting its other material, matching anchor 3 ('references present but not clearly signaled; content that should be separate is inline') better than anchor 4.

3 / 5

Total

17

/

20

Passed

Description

78%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 that follows best practices: concrete third-party capability statement, an explicit 'Use this skill when...' clause with specific trigger conditions, and exact command syntax. Its only weaknesses are the single-action scope of the capability list and missing natural trigger synonyms like 'retrieve' or 'grab'.

DimensionReasoningScore

Specificity

The description names the domain and one concrete action with exact command syntax ("moving it from the environment into the agent's inventory using 'pick up OBJ'"), but offers only this single action — the downstream mentions ("testing, measuring, or placing") describe outcomes of other skills, not actions this skill performs. It matches anchor 3 ('1-2 concrete actions, but not comprehensive') better than anchor 4, which expects several specific actions listed.

3 / 5

Completeness

It explicitly answers both questions: the 'what' is concrete ("Acquires a specified object by moving it from the environment into the agent's inventory using 'pick up OBJ'") and the 'when' is an explicit 'Use this skill when...' clause with concrete trigger conditions ("requires an object to be manipulated, tested, or transported and it is not yet in your inventory"). This matches the anchor-5 good example pattern of capability sentence plus concrete 'Use when' triggers, and clearly exceeds anchor 4 where the 'when' is generic.

5 / 5

Trigger Term Quality

The 'when' clause supplies good natural keyword coverage — "an object to be manipulated, tested, or transported", "pick up", "inventory" — giving multiple synonymous trigger phrasings a user would naturally say. It falls short of anchor 5 because common variations like 'retrieve', 'get', 'grab', or 'find an object' are absent.

4 / 5

Distinctiveness Conflict Risk

The trigger condition "it is not yet in your inventory" plus the specific 'pick up' mechanics carve out a clear niche distinct from downstream consumers it names (testing, measuring, placing). Minor overlap risk remains with closely related skills in the same suite (e.g., an object-placer or navigation skill), so it fits anchor 4 rather than anchor 5's 'minimal conflict risk'.

4 / 5

Total

16

/

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.