CtrlK
BlogDocsLog inGet started
Tessl Logo

alfworld-task-verifier

Use when the agent needs to check whether an ALFWorld task objective has been met after completing a sub-action (e.g., placing an object). This skill parses the task goal, evaluates the latest environment observation, and outputs a verification decision — task complete, task incomplete, or action ineffective — to guide the next step.

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A well-structured, concise instruction skill with a clear workflow and concrete decision table, weakened only by orphaned reference files that the body never points to.

Suggestions

Add explicit links to references/task_grammar.md and references/verification_examples.md (e.g., 'See [task_grammar.md](references/task_grammar.md) for goal-parsing patterns') so the bundled material is discoverable.

Consider a brief one-line validation checkpoint in the workflow (e.g., 'Re-examine the receptacle when the count is uncertain') as an explicit step rather than only in Error Handling.

DimensionReasoningScore

Conciseness

Lean and efficient across short sections, a compact decision table, and tight examples with no padding or over-explanation of concepts Claude already knows.

5 / 5

Actionability

The decision table maps concrete observation conditions to exact output strings and examples are copy-paste-style, but it is instruction-only with no executable code; guidance is actionable though not fully executable.

4 / 5

Workflow Clarity

Clear four-step sequence (Parse, Analyze, Decide, Output) with feedback loops for ambiguous observations and uncertain quantity tracking, though validation is observational re-checking rather than a hard checkpoint gate.

4 / 5

Progressive Disclosure

The body is well-organized with clear sections, but the bundled reference files (references/task_grammar.md, references/verification_examples.md) are never linked or signaled in SKILL.md, leaving them orphaned.

3 / 5

Total

16

/

20

Passed

Description

92%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, specific description that clearly conveys both what the skill does and when to use it, with concrete actions and outcomes. The only minor gap is slightly narrow trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain and three concrete actions (parses the task goal, evaluates the latest environment observation, outputs a verification decision) with enumerated outcomes, giving comprehensive coverage of its scope.

5 / 5

Completeness

Explicitly answers both 'what' (parses goal, evaluates observation, outputs verification decision) and 'when' (after completing a sub-action) with concrete trigger phrases.

5 / 5

Trigger Term Quality

Uses natural trigger phrasing ('check whether an ALFWorld task objective has been met', 'placing an object') but is anchored to one scenario, missing common variations like 'verify task' or 'is the task done'.

4 / 5

Distinctiveness Conflict Risk

Tied to a clear niche (ALFWorld task verification after sub-actions) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

19

/

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.