alfworld-navigation-planner

Plans a path to move the agent between receptacles to search for target objects. Use this when you need to traverse the environment to reach a specific location or systematically explore multiple areas. It takes the current location and destination receptacle as input, and outputs the next 'go to' action to approach the target.

Quality

67%

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-navigation-planner/SKILL.md

Quality

Content

56%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 with a clear workflow and feedback loop, but its actionability and progressive disclosure are undermined by a broken reference to a missing bundled script and an orphaned reference file that is never linked. The Key Principles section adds mild padding.

Suggestions

Fix the broken bundle reference: either add the referenced script to scripts/ or replace 'the bundled script' wording with the actual mechanism (and link references/action_primer.md, which contains the action set the skill relies on).

Link references/action_primer.md from the body so the action vocabulary and receptacle associations are discoverable one level deep.

Trim the 'Key Principles' section or merge it into the workflow steps to remove restatement of obvious guidance.

Dimension	Reasoning	Score
Conciseness	The body is short and mostly efficient, but the 'Key Principles' section (Systematic Search, Adaptive Planning, Context Preservation) restates fairly obvious guidance that could be trimmed, keeping it from the efficient end of the scale.	3 / 5
Actionability	It gives a clear input/output format and a concrete example trace, but the actual execution mechanism — 'The core logic is handled by the bundled script' — refers to a script that does not exist in the bundle, leaving a key gap in how to invoke the skill.	3 / 5
Workflow Clarity	The 'How to Use' steps give a clear sequence (identify goal → call skill → execute → observe and repeat) with an explicit feedback loop for unfound targets and failed actions, with only minor validation gaps.	4 / 5
Progressive Disclosure	Sections are well-organized, but reference signaling is broken: the body points to a non-existent 'bundled script' and never links the actual reference file (references/action_primer.md), so the real bundle material is orphaned.	3 / 5
	Total	13 / 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, well-structured description that clearly states both what the skill does and when to use it, with concrete domain-specific triggers. Its main weakness is narrow capability coverage — it describes essentially one action rather than a comprehensive set.

Suggestions

Broaden the specificity by listing the concrete actions the planner supports (e.g. planning multi-hop paths, choosing fallback receptacles) rather than only 'output the next go to action'.

Add a few more natural trigger synonyms (e.g. 'navigate', 'find objects', 'move to') to round out trigger-term coverage toward the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ('move the agent between receptacles to search for target objects') and the concrete output ('outputs the next "go to" action'), but coverage is narrow — really one core action rather than a comprehensive list of capabilities.	3 / 5
Completeness	Explicitly answers both 'what' ('Plans a path to move the agent between receptacles... outputs the next go to action') and 'when' with a concrete 'Use this when...' trigger clause, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural trigger phrases a user would say — 'traverse the environment to reach a specific location', 'systematically explore multiple areas', 'search for target objects' — with good coverage, though a few synonyms (e.g. 'navigate', 'find') are absent.	4 / 5
Distinctiveness Conflict Risk	Domain-specific terms ('receptacles', 'go to action') give it a clear niche with minimal conflict risk, though 'traverse the environment' and 'explore multiple areas' are somewhat generic and could overlap with general navigation/exploration skills.	4 / 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-navigation-planner/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.