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.

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

Low

Low-risk findings worth noting

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 body is concise, actionable, and workflow-clear with explicit decision logic and error-recovery feedback loops. The only gap is progressive disclosure: real reference bundles exist but are not linked or signaled in the SKILL.md body.

Suggestions

Add explicit inline links to the bundle files where relevant, e.g. 'See [task_grammar.md](references/task_grammar.md) for parsing patterns' under Step 1 and 'See [verification_examples.md](references/verification_examples.md)' near the decision table.

Consider a short 'References' section listing task_grammar.md and verification_examples.md with one-line descriptions so the supporting material is discoverable from the SKILL.md overview.

DimensionReasoningScore

Conciseness

Lean body with no padded explanations of what ALFWorld is or general concepts; the decision table and examples are tight and every token earns its place.

3 / 3

Actionability

Provides exact output strings, concrete observation patterns to match (e.g. 'Nothing happened'), and a worked example with real Action/Observation lines that is effectively copy-paste ready.

3 / 3

Workflow Clarity

Clear 4-step sequence (Parse → Analyze → Decide → Output) with an explicit decision table and feedback loops for recovery (re-examine on ambiguity, re-count quantities, retry on ineffective action).

3 / 3

Progressive Disclosure

Bundle files task_grammar.md and verification_examples.md exist and are one level deep, but the body never links to or signals them inline, so navigation to the supporting material is implicit rather than clear.

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, specific, and fully answers both 'what' and 'when' with an explicit trigger clause and concrete enumerated actions. It is highly distinct to ALFWorld task verification with little conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'parses the task goal, evaluates the latest environment observation, and outputs a verification decision' with three enumerated outcomes (task complete, incomplete, ineffective).

3 / 3

Completeness

Explicitly answers both what it does (parses, evaluates, outputs a verification decision) and when to use it (the 'Use when the agent needs to check...' clause).

3 / 3

Trigger Term Quality

'Use when the agent needs to check whether an ALFWorld task objective has been met after completing a sub-action' is natural trigger phrasing a user/agent would say; terms like 'check whether...has been met' and 'sub-action' map well to real usage.

3 / 3

Distinctiveness Conflict Risk

Scoped tightly to ALFWorld task-objective verification with specific triggers, making it 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.