CtrlK
BlogDocsLog inGet started
Tessl Logo

scienceworld-substance-fetcher

Locates and retrieves a target substance or material from a container in the environment. Use this skill when the task requires processing a specific substance (e.g., chocolate, sodium chloride, a chemical) and you need to find and acquire it. Searches rooms and containers (fridge, cupboard, counter) and retrieves the substance via pick up or move actions.

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.

The body is actionable and well-sequenced with verification and error-recovery steps, but it repeats key constraints across sections and ships an unlinked reference file. Tightening redundancy and signaling the action primer would raise quality.

Suggestions

Consolidate the 'containers are already open' and pick-up-vs-move guidance so each appears once (state in Core Logic, then reference rather than restate in Critical Constraints).

Link `references/action_primer.md` from the body (e.g., 'See [action_primer.md](references/action_primer.md) for the full action and container reference') so the bundle file is clearly signaled and one level deep.

Pull the container-name and room-location tables (currently duplicated in the primer) out of inline prose to reduce token overlap between the two files.

DimensionReasoningScore

Conciseness

Mostly lean and actionable, but the 'All containers are already open' assumption and the pick-up-vs-move guidance are each stated twice (Core Logic then Critical Constraints), so it could be tightened.

2 / 3

Actionability

Provides concrete executable commands — `teleport to [room]`, `look around`, `pick up [substance]`, `move [substance] to [destination container]`, `examine [substance]` — plus a worked example trajectory, matching copy-paste-ready guidance.

3 / 3

Workflow Clarity

Clear Identify → Search → Locate → Retrieve sequence with an explicit verification checkpoint ('use examine [substance] or check your inventory to confirm success') and a feedback loop in Error Handling for failed retrievals.

3 / 3

Progressive Disclosure

Sections are well-organized and the skill is short, but `references/action_primer.md` exists yet is never linked or signaled from the body, leaving a present reference un-navigable rather than cleanly one level deep.

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 states concrete capabilities, includes an explicit 'Use when' trigger with natural keywords, and occupies a distinctive niche. No first/second-person voice or vague fluff present.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'Locates and retrieves', 'Searches rooms and containers', 'retrieves the substance via pick up or move actions' — matching the anchor for listing several specific actions.

3 / 3

Completeness

Explicitly answers what ('Locates and retrieves a target substance...') and when via a clear 'Use this skill when the task requires processing a specific substance' clause, satisfying the highest anchor.

3 / 3

Trigger Term Quality

Includes natural terms a user would say ('substance', 'material', 'chocolate', 'sodium chloride', 'fridge', 'cupboard', 'counter', 'pick up', 'move') with good coverage rather than technical jargon.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche — fetching a substance from named containers in the environment — with distinct triggers unlikely to collide with other 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.