CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./experiments/src/skills/alfworld/alfworld-navigation-planner/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 and presents a clear, looped workflow with error handling. Its weaknesses are an unverifiable reference to a missing script and an orphaned reference file that is never pointed to from SKILL.md.

Suggestions

Either add the referenced script under scripts/ and link to it, or remove the 'core logic is handled by the bundled script' claim and inline the concrete navigation logic.

Link to the existing references/action_primer.md (e.g., 'See references/action_primer.md for the full action set') so the bundled reference is discoverable.

Provide a concrete, copy-paste-ready example of constructing the 'go to {recep}' action rather than only describing it abstractly.

DimensionReasoningScore

Conciseness

The body is lean (~24 lines), avoids explaining concepts Claude already knows, and every section earns its place; the only mild redundancy is the example restating the input/output, but it stays efficient.

3 / 3

Actionability

The 'How to Use' steps are procedural but reference 'the bundled script' that does not exist in scripts/, and no executable code or commands are given; guidance is concrete in intent but incomplete and unverifiable.

2 / 3

Workflow Clarity

The four-step 'How to Use' sequence is clear and includes an observe-and-repeat feedback loop with explicit 'Nothing happened' error handling, satisfying the simple-skill workflow bar.

3 / 3

Progressive Disclosure

Sections are well organized, but the actual bundle file references/action_primer.md is never linked from the body, while the body instead references a non-existent 'bundled script'; references are not clearly signaled.

2 / 3

Total

10

/

12

Passed

Description

75%

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 communicates purpose, inputs/outputs, and an explicit use-trigger, with a distinct ALFWorld navigation niche. Its main weakness is the second-person voice ('you need') and limited trigger-term variation.

Suggestions

Rewrite in third person ('Use when the agent must traverse...') to avoid the second-person voice penalty.

Broaden trigger terms with natural variations such as 'navigate to a receptacle', 'move to a location', or 'search rooms for an object'.

DimensionReasoningScore

Specificity

Names concrete actions ('Plans a path to move the agent between receptacles', 'outputs the next go to action'), which would normally score 3, but the second-person phrasing 'Use this when you need to' triggers the voice penalty reducing specificity by 1.

2 / 3

Completeness

Explicitly answers both what ('Plans a path... outputs the next go to action') and when ('Use this when you need to traverse the environment...'), with a clear 'Use this when' trigger clause.

3 / 3

Trigger Term Quality

Includes relevant triggers ('traverse the environment to reach a specific location', 'systematically explore multiple areas') but offers a narrow set of variations rather than broad coverage of natural phrasings a user would say.

2 / 3

Distinctiveness Conflict Risk

The receptacle-to-receptacle 'go to' navigation framing is a distinct niche unlikely to trigger for unrelated skills, despite the slightly generic 'explore multiple areas' phrasing.

3 / 3

Total

10

/

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.