CtrlK
BlogDocsLog inGet started
Tessl Logo

scienceworld-substance-preparator

Use when you need to transfer a target substance into an appropriate container for processing (e.g., a pot for heating, a beaker for mixing). Trigger after acquiring the substance and before setting up an apparatus. Selects a suitable empty container and moves the substance into it.

68

Quality

83%

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

88%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 exemplary short, instruction-only skill: lean prose, copy-ready commands, an explicit validate-before-proceeding workflow with error recovery, and a genuinely useful one-level-deep bundle reference. The only real improvement is signaling the reference file by name/path instead of the vague 'consult the bundled reference'.

DimensionReasoningScore

Conciseness

The body is lean (~40 lines), assumes competence, and never explains concepts Claude already knows; every section (trigger, procedure, considerations, example) earns its place. It sits just below the 5 anchor because of minor redundancy — the 'When to Use' section restates the frontmatter description and step 1 ('Confirm the exact name and location') is near-tautological — but it is far from the padded or over-explaining 2-3 anchors.

4 / 5

Actionability

Fully concrete, executable game commands with exact syntax: `move [SUBSTANCE] to [CONTAINER]`, `examine metal pot`, `look around`, plus a worked end-to-end example showing the expected output ('metal pot (containing chocolate)'). This is copy-paste-ready instruction covering the common case, matching the 5 anchor for an instruction-only skill.

5 / 5

Workflow Clarity

A clearly sequenced 5-step procedure with explicit validation checkpoints (step 3 'examine it to confirm it's empty', step 5 'Verify: Briefly check the container's contents'), an error-recovery loop ('If the transfer fails... look around again and consult the bundled reference'), and an explicit gate ('Proceed to the next skill... only after this verification'). This matches the 5 anchor with feedback loops; this is not a destructive or batch operation, so no cap applies.

5 / 5

Progressive Disclosure

The skill is short and well-sectioned, and the bundle has exactly one one-level-deep reference file (references/common_containers.md) that genuinely holds detail (full container lists, unsuitable containers). It falls short of the 5 anchor because the body only says 'consult the bundled reference' generically without naming or linking the file path, and the reference's 'Verification Commands' section duplicates commands already in the body — minor organization gaps characteristic of the 4 anchor.

4 / 5

Total

18

/

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 explicitly covers what the skill does and when to trigger it, with concrete container examples and clear sequencing boundaries. Its main deductions are the second-person phrasing ('Use when you need...'), which violates the third-person voice guideline, and trigger-term coverage that omits some natural synonyms.

Suggestions

Rewrite the trigger clause in third person to avoid the voice penalty, e.g., 'Use when a target substance must be transferred into an appropriate container for processing' or keep the imperative 'Use when transferring...' without 'you'.

Broaden natural trigger terms with synonyms such as 'prepare', 'pour', or 'place into a container' to improve trigger-term coverage toward the 5 anchor.

Consider naming one or two additional concrete actions (e.g., validating the container is empty) to lift specificity once the voice issue is fixed.

DimensionReasoningScore

Specificity

Concrete actions are named ('Selects a suitable empty container and moves the substance into it', 'transfer a target substance into an appropriate container') with concrete examples ('a pot for heating, a beaker for mixing'), which is solidly at the 4 anchor for several specific actions. However, the description uses second person ('Use when you need to transfer...'), and the rubric guideline mandates reducing specificity by 1 for non-third-person voice, bringing it to 3. It is not a 2 because the domain and actions are concrete, not generic.

3 / 5

Completeness

Both 'what' and 'when' are explicitly answered: what — 'Selects a suitable empty container and moves the substance into it'; when — 'Use when you need to transfer a target substance into an appropriate container for processing' plus explicit sequencing triggers ('Trigger after acquiring the substance and before setting up an apparatus'). This matches the 5 anchor with concrete trigger phrases; a 4 would require the 'when' to be less explicit.

5 / 5

Trigger Term Quality

Good natural keyword coverage for this domain: 'transfer', 'substance', 'container', 'pot', 'beaker', 'heating', 'mixing', 'apparatus', 'moves' — terms a user/agent in this environment would naturally say. Not a 5 because common synonyms and variations (e.g., 'pour', 'prepare', 'place into') are not covered; not a 3 because coverage goes well beyond one or two generic keywords.

4 / 5

Distinctiveness Conflict Risk

A clear niche (substance-to-container transfer in a game world) with sequencing boundaries ('after acquiring the substance and before setting up an apparatus') that reduce overlap with related heating/apparatus skills. Minor overlap risk remains with a hypothetical generic 'move objects' or 'heating' skill, so it does not reach the minimal-conflict 5 anchor; it is well above the broad-overlap anchors 2-3.

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.

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.