CtrlK
BlogDocsLog inGet started
Tessl Logo

scienceworld-liquid-source-finder

This skill searches rooms for a liquid source (e.g., sink, toilet, jug) by sequentially surveying different locations. It should be triggered when the task requires obtaining a liquid (like water) and the agent does not have immediate access to it. The skill involves teleporting to candidate rooms, looking around, and identifying potential sources, guiding the agent toward the nearest available liquid.

77

Quality

96%

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

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill body is a tight, actionable, well-sequenced search procedure with concrete commands and a clear success checkpoint. Its main weakness is progressive disclosure: the provided reference files are orphaned from the body and partly duplicated inline.

Suggestions

Link the bundle files from the body so they are clearly signaled, e.g. under Core Procedure add 'For the full command syntax, see [action_glossary.md](references/action_glossary.md)' and 'For ranked room likelihoods, see [room_priority.md](references/room_priority.md)'.

De-duplicate the inline room-priority list by trimming it to a brief note ('Teleport to candidate rooms by likelihood — see room_priority.md') and letting the reference file carry the full ranking, keeping the body as an overview.

Consider moving the detailed command descriptions (e.g. `move OBJ to OBJ`, `activate OBJ`) entirely to action_glossary.md and keeping the body focused on the procedure, so the SKILL.md serves as a true entry point.

DimensionReasoningScore

Conciseness

The body is lean and procedural, assuming Claude's competence without explaining basic concepts; the Quick Reference section is a legitimate compact summary rather than padding. Not a level-2 case because there is no unnecessary explanatory fluff.

3 / 3

Actionability

Provides concrete, copy-paste-ready game commands throughout — `look around`, `examine`, `pick up`, `move ... to ...`, `activate`, `deactivate` — with specific sub-steps for filling containers from fixed sources. As an instruction-only skill, its actionable guidance earns the top anchor.

3 / 3

Workflow Clarity

Clear five-step sequence (Initiate → Prioritize → Survey → Obtain → Terminate) with an explicit success checkpoint ('Once the required liquid is successfully obtained and in your inventory, conclude the skill'). This is a search procedure, not a destructive/batch operation, so no validation cap applies.

3 / 3

Progressive Disclosure

The body is well-organized, but the two bundle files (references/action_glossary.md, references/room_priority.md) are never linked or signaled in the body, and room-priority content is duplicated inline — matching 'references present but not clearly signaled; content that should be separate is inline.' It is not a 1 (not a monolithic wall, no nested references) and not a 3 (references are unsignaled).

2 / 3

Total

11

/

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.

The description is concise, third-person, and explicitly covers both capability and trigger conditions with concrete actions and natural keywords. It is a strong, well-scoped description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'searches rooms for a liquid source', 'sequentially surveying different locations', 'teleporting to candidate rooms, looking around, and identifying potential sources' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what ('searches rooms... by sequentially surveying... teleporting... looking around, and identifying potential sources') and when ('It should be triggered when the task requires obtaining a liquid... and the agent does not have immediate access to it').

3 / 3

Trigger Term Quality

Uses natural terms a user would say when needing the skill — 'liquid source (e.g., sink, toilet, jug)', 'obtaining a liquid (like water)', 'does not have immediate access to it' — giving good coverage of common phrasings.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche — locating a liquid source via room teleport-and-survey in ScienceWorld — with distinct triggers unlikely to fire for unrelated 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.