CtrlK
BlogDocsLog inGet started
Tessl Logo

scienceworld-object-placer

Moves a specified object from the environment or inventory into a target container based on a classification decision. Use this skill when a task requires sorting or storing an object in a specific location after an assessment (e.g., placing a conductive object in the blue box or a non-conductive object in the orange box).

65

Quality

82%

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

78%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, highly actionable instruction skill: exact environment commands, a worked example with expected output, and an explicit verification step. Its weaknesses are triple repetition of the same commands across three sections, a missing failure-recovery loop after verification, and an unreferenced bundle file (action_primer.md) that the body never points to.

Suggestions

Add a pointer to the bundle reference, e.g. under Key Actions: "For the full set of supporting environment actions (examine, focus on, connect, wait1), see [references/action_primer.md](references/action_primer.md)" — currently the file is orphaned with no navigation from the body.

Consolidate the duplication between Core Workflow, the Key Actions table, and the Example: either drop the Key Actions table (its rows restate the workflow steps verbatim) or keep the table and shorten the Example to the command sequence only.

Add an error-recovery step after verification, e.g. "If `look at` shows the object is not in the container, re-run `move OBJ to OBJ` and verify again" — this would supply the feedback loop the workflow currently lacks.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence with no basic-concept padding, but the same three commands (`pick up OBJ`, `move OBJ to OBJ`, `look at`) appear in both the Core Workflow and the Key Actions table, and then again in the Example — trimmable duplication. Not 5 because that repetition could be consolidated; not 3 because the excess is minor and localized.

4 / 5

Actionability

Commands are exact and executable in the target environment (`pick up metal pot`, `move metal pot to blue box`, `look at <CONTAINER>`), and the worked example includes the expected confirmation output ("In the blue box is: a metal pot"), making it copy-paste ready for the common case. Nothing is pseudocode or left abstract.

5 / 5

Workflow Clarity

The four-step sequence is clear and includes an explicit validation checkpoint ("Verify Placement: `look at <CONTAINER>`" reinforced by "Always verify placement with `look at` — do not assume success"). It is not 5 because there is no error-recovery feedback loop — no guidance on what to do if the move fails or the object is absent from the container after verification.

4 / 5

Progressive Disclosure

The body itself is well-organized with clear sections and is under 50 lines, but the bundle contains `references/action_primer.md` which is never referenced or signaled anywhere in the body — an orphaned reference with no navigation path. Per the bundle-structure guideline this matches anchor 3 ("references present but not clearly signaled"); not 2 because the body structure is good and content is not inlined that belongs elsewhere.

3 / 5

Total

16

/

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 with an explicit what-and-when structure and concrete trigger examples tied to a classification workflow. Its only weaknesses are single-action coverage and a few missing natural synonyms, plus a slight generic-storage overlap risk since the environment is unnamed.

DimensionReasoningScore

Specificity

The description names the domain and one concrete action — "Moves a specified object from the environment or inventory into a target container based on a classification decision" — with concrete mechanics (source, destination, condition). It stays at 3 because it lists only a single action verb rather than several specific actions, and not 2 because the action described is concrete rather than generic.

3 / 5

Completeness

It explicitly answers both questions: the what ("Moves a specified object from the environment or inventory into a target container based on a classification decision") and the when ("Use this skill when a task requires sorting or storing an object in a specific location after an assessment"), with concrete trigger examples (conductive → blue box, non-conductive → orange box). This matches the anchor-5 example structure exactly.

5 / 5

Trigger Term Quality

Natural user phrases are present: "sorting or storing an object in a specific location", "placing a conductive object in the blue box", and "after an assessment". It falls short of 5 because common synonyms like "put" or generic "container" phrasing are missing, and above 3 because multiple natural trigger phrases (not just keywords) are covered.

4 / 5

Distinctiveness Conflict Risk

The classification-conditioned placement niche is mostly distinct — the trigger is tied to acting "after an assessment" with specific container outcomes. It is not 5 because the description never names the target environment and the generic "storing an object in a specific location" phrasing creates minor overlap risk with general sorting/storage skills.

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.