CtrlK
BlogDocsLog inGet started
Tessl Logo

scienceworld-conditional-focus-executor

Executes a 'focus on OBJ' action on a specific object based on the outcome of a prior conditional evaluation. Use when you have a measurement result and task instructions specify focusing on different objects (e.g., colored boxes) depending on whether the result meets a threshold.

70

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

92%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, single-purpose skill: lean, fully executable, with an explicit verification step and an error-recovery loop. Its only real defect is navigation — the bundled references/action_primer.md exists but is never referenced from SKILL.md, so the action reference is undiscoverable through the skill's entry point.

Suggestions

Add a one-level-deep reference to the primer, e.g., a line under a '## References' or in When to Use: "For the full action vocabulary, see [action_primer.md](references/action_primer.md)."

Clarify what the primer adds beyond SKILL.md (e.g., measurement actions like `use thermometer on chocolate`) so the reference is clearly signaled rather than merely linked.

DimensionReasoningScore

Conciseness

The body is ~20 lean lines with no padding and no explanation of concepts Claude already knows; every section (When to Use, Procedure, failure note, Example) earns its place, matching 'Lean and efficient; assumes Claude's competence'. It is clearly above anchor 4, which allows minor over-explanation — there is none.

5 / 5

Actionability

Concrete, copy-paste-ready commands are given (`focus on <TARGET_OBJECT>`, `look around`) plus a fully worked example with real values ("63 > 50 is true → target is red box", "Execute: `focus on red box`"), matching 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases'.

5 / 5

Workflow Clarity

The 4-step procedure has an explicit validation step ("Verify: Confirm the focus action succeeded before proceeding") and a feedback loop for error recovery ("If the focus action fails (e.g., object not found), use `look around` to verify the target object name"), matching the anchor 5 example's structure. The operation is not destructive or batch, so no cap applies.

5 / 5

Progressive Disclosure

The body itself is well organized, but the bundle contains references/action_primer.md — a relevant action reference — that is never mentioned or linked anywhere in SKILL.md, matching 'Some structure but could be better organized; references present but not clearly signaled'. It is not anchor 4 because an existing bundle file is completely orphaned from the entry point; it is above anchor 2 because the inline content is short, structured, and nothing is improperly inlined.

3 / 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 well-constructed description that clearly states a concrete action and an explicit, condition-rich 'Use when' clause in third person. Its main gaps are narrow action coverage (only the focus action) and the absence of the target environment name and common measurement-type terms, which slightly limit specificity, trigger coverage, and distinctiveness.

Suggestions

Mention the ScienceWorld environment explicitly in the description to sharpen distinctiveness and reduce conflict risk with generic measurement/conditional skills.

Include the concrete measurement types from the body (temperature, pH, mass) as trigger terms to broaden natural keyword coverage.

If the skill also covers verifying or recovering from failed focus actions, state that capability to lift action coverage beyond a single action.

DimensionReasoningScore

Specificity

The description names the domain (conditional evaluation of measurements) and one concrete action ("Executes a 'focus on OBJ' action on a specific object"), matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'. It stays at a single action rather than listing several specific capabilities, so it does not reach anchor 4, and it is far more concrete than the generic anchor 2.

3 / 5

Completeness

It explicitly answers both: what ("Executes a 'focus on OBJ' action on a specific object based on the outcome of a prior conditional evaluation") and when ("Use when you have a measurement result and task instructions specify focusing on different objects (e.g., colored boxes) depending on whether the result meets a threshold"), with concrete trigger conditions — the anchor 5 pattern. Not anchor 4 because the 'when' clause is already explicit and specific.

5 / 5

Trigger Term Quality

Phrases like "measurement result", "threshold", "focus on", and "colored boxes" give good natural keyword coverage, matching 'Good keyword coverage; a few natural terms missing'. It misses common variations users would say (e.g., temperature, pH, mass, 'if/otherwise'), keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

The niche is distinct (conditional focus-on-object after a measurement) with low overlap risk, matching 'Mostly distinct; minor overlap risk with closely related skills'. It is not a 5 because the description alone never names the ScienceWorld environment, so it could overlap with other measurement/threshold-conditional 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.