CtrlK
BlogDocsLog inGet started
Tessl Logo

scienceworld-living-entity-identifier

Analyzes room observations to identify potential living things (e.g., eggs, plants, animals) among listed objects. Use this skill when a task involves finding, focusing on, or interacting with a living thing, biological entity, or organism. Processes observation text, flags candidate living items based on domain knowledge, and outputs a focused target for subsequent actions like focus on or pick up.

73

Quality

90%

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

80%

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

The body is lean and highly actionable with concrete commands and a worked example, but it underuses its own bundle: the references are never linked from SKILL.md and one is essentially empty, and the identify step lacks an explicit verification checkpoint before focusing.

Suggestions

Link the bundle references from the body — e.g., under Core Workflow add 'See [living_indicators.md](references/living_indicators.md) for the full indicator list' — so progressive disclosure is one level deep and clearly signaled.

Fill out references/action_sequences.md (currently just a heading) or remove it if unused, so every referenced file delivers on its promise.

Add an explicit verification checkpoint in the workflow, e.g., 'Confirm the candidate matches a high-confidence indicator before focus on' to lift workflow clarity to a full feedback loop.

DimensionReasoningScore

Conciseness

The body is lean and well-sectioned (Purpose, Core Workflow, Key Actions table, Example, Important Notes) with no padding or explanation of concepts Claude already knows; every section earns its place, matching the level-3 'lean and efficient' anchor.

3 / 3

Actionability

Concrete, executable game commands ('look around', 'focus on [IDENTIFIED_OBJECT]', 'teleport to LOC', 'pick up [OBJECT] then move [OBJECT] to [CONTAINER]') plus a fully worked example make the guidance copy-paste ready, fitting the level-3 anchor; placeholders are appropriate since the object is runtime-determined.

3 / 3

Workflow Clarity

The four-step sequence (Survey, Identify, Focus, Transport) is clearly numbered, but there is no explicit verification checkpoint confirming a flagged candidate is actually living before 'focus on', so checkpoints are implicit rather than explicit — matching the level-2 anchor; not level 3 because the validate/confirm feedback loop is absent.

2 / 3

Progressive Disclosure

Bundle files references/living_indicators.md and references/action_sequences.md exist but are never signaled or linked from the body, while candidate indicator lists that belong in the reference are kept inline — matching the level-2 'references present but not clearly signaled' anchor; not level 1 because the body itself is well-organized into sections rather than a monolithic wall, and not level 3 because navigation to the references is missing and action_sequences.md is near-empty.

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.

The description is concise, third-person, and cleanly answers both what the skill does and when to use it, with concrete actions and natural trigger terms. It is among the stronger reference examples in the rubric.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Analyzes room observations to identify potential living things', 'Processes observation text, flags candidate living items', 'outputs a focused target for subsequent actions like focus on or pick up' — matching the anchor for several specific concrete actions rather than the level-2 single-domain example.

3 / 3

Completeness

Explicitly answers both what (analyzes observations, flags candidates, outputs a target) and when via a clear 'Use this skill when a task involves…' clause, matching the level-3 anchor; not level 2 because the when-trigger is explicit rather than merely implied.

3 / 3

Trigger Term Quality

Natural trigger phrasing a user/task would actually say — 'finding, focusing on, or interacting with a living thing, biological entity, or organism' — gives good coverage of common variations, not just jargon; it is not the sparse level-2 'Works with PDF files' style.

3 / 3

Distinctiveness Conflict Risk

The game-interaction action context ('room observations', 'focus on', 'pick up', 'teleport to') carves a clear niche unlikely to conflict with general skills, fitting the level-3 distinct-triggers anchor.

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.