alfworld-goal-interpreter

Parses the natural language task goal to extract actionable sub-objectives and required objects. Trigger this skill whenever a new task is assigned to break down complex instructions into clear, sequential targets. It interprets phrases like 'look at X under Y' to identify target objects (pillow), reference objects (desklamp), and spatial relationships (under).

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./experiments/src/skills/alfworld/alfworld-goal-interpreter/SKILL.md

Quality

Content

67%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.

The body is well-structured, concise, and clearly sequenced with a fallback reference. Its main weakness is actionability: it directs the agent to a `parse_goal.py` script that does not exist in the bundle, breaking the primary executable path.

Suggestions

Either ship `parse_goal.py` under a `scripts/` directory or replace the reference with inline, self-contained parsing guidance so the primary step is executable.

Add an explicit validation/feedback checkpoint (e.g., verify parsed objects against the current observation and re-parse or fall back on mismatch) to close the workflow-clarity gap.

Ensure every referenced bundle path (`parse_goal.py`, `search_patterns.md`) resolves to a real file so navigation is unbroken.

Dimension	Reasoning	Score
Conciseness	The body is efficient and free of padding about concepts Claude already knows, with only minor gloss lines like 'The main object to interact with', fitting the 'efficient; minor instances of over-explanation that could be trimmed' anchor rather than the fully lean 5.	4 / 5
Actionability	It gives structured output fields, IF/THEN logic, and action mappings, but instructs use of `parse_goal.py` which is not present in the bundle (no scripts/ directory), leaving a key executable step unfulfilled — matching the 'some concrete guidance but incomplete; missing key details' anchor.	3 / 5
Workflow Clarity	Four numbered sections give a clear parse → plan → map → execute sequence with a 'Critical Check' and a fallback pointer, but there is no explicit validate-then-fix feedback loop, fitting the 'clear sequence with most checkpoints present; minor validation gaps' anchor.	4 / 5
Progressive Disclosure	The overview points one level deep to a bundled reference (`search_patterns.md`, which exists) with clearly signaled inline mentions, giving good structure; the missing `parse_goal.py` is a minor organization gap rather than a structural one, keeping it at 4.	4 / 5
	Total	15 / 20 Passed

Description

72%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.

The description clearly states its purpose and trigger and occupies a distinct niche, scoring well on completeness and distinctiveness. Its main weakness is trigger-term quality: the activation language is workflow jargon rather than the natural phrases a user would actually say.

Suggestions

Add concrete natural-language trigger terms a user might say, such as 'task', 'goal', 'instructions', or 'find/look at object' phrases, plus ALFWorld-specific cues.

Consider including synonyms or extension-like markers (e.g., 'task goal', 'objective', 'instruction parsing') to broaden natural keyword coverage.

Tighten the trigger clause from 'whenever a new task is assigned' to also reference the user-facing signal (e.g., 'Use when given an ALFWorld task instruction to break into ordered sub-goals').

Dimension	Reasoning	Score
Specificity	Names the domain (ALFWorld task goals) and several concrete actions — 'Parses the natural language task goal to extract actionable sub-objectives and required objects' and 'identify target objects (pillow), reference objects (desklamp), and spatial relationships (under)' — with only minor coverage gaps, fitting the 'lists several specific actions; minor gaps' anchor rather than the comprehensive 5.	4 / 5
Completeness	Explicitly answers both what ('Parses the natural language task goal to extract actionable sub-objectives and required objects') and when ('Trigger this skill whenever a new task is assigned') with concrete trigger guidance, matching the top anchor.	5 / 5
Trigger Term Quality	Trigger phrases ('whenever a new task is assigned', 'complex instructions') are workflow jargon rather than natural terms a user would say, with no synonyms or file extensions, matching the 'one or two generic keywords; missing the natural phrases users say' anchor.	2 / 5
Distinctiveness Conflict Risk	The niche language ('task goal', 'sub-objectives', 'target/reference objects', 'spatial relationships') and ALFWorld-specific examples give it distinct triggers with minimal conflict risk, matching the 'clear niche with distinct triggers' anchor.	5 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

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
Path: experiments/src/skills/alfworld/alfworld-goal-interpreter/SKILL.md
Commit: cce11c3

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.