scienceworld-result-archiver

Places an object into a designated container (like a colored box) based on a test outcome. It should be triggered when the agent needs to finalize a task by storing an object according to a rule (e.g., conductive → blue box, non-conductive → orange box). The input is the object and the rule, and the output is the object moved to the correct container.

Quality

79%

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/scienceworld/scienceworld-result-archiver/SKILL.md

Quality

Content

75%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 concise, well-organized, and gives a concrete worked example with the exact command syntax, but it lacks an explicit post-move validation checkpoint for an irreversible action and points to a bundled script (scripts/conductivity_test.py) that is not present in the bundle.

Suggestions

Add an explicit validation step after `move OBJ to CONTAINER` (e.g., `look at <container>` or check inventory) to confirm the object was archived correctly before declaring the task finalized.

Either provide the referenced `scripts/conductivity_test.py` bundle file or remove the 'Bundled Logic' section reference, so the skill does not point to a non-existent resource.

For non-conductivity test types, include at least one concrete example command beyond the general procedure so the guidance is executable for those cases too.

Dimension	Reasoning	Score
Conciseness	Lean and efficient at ~30 lines; assumes Claude's competence (no explanations of what conductivity or containers are) and every section earns its place, with the example and procedure all directly actionable.	5 / 5
Actionability	Provides the concrete command form (`move OBJ to CONTAINER`, `move metal pot to blue box`) and a worked example, but the general test types rely on 'use the general instructions above' rather than copy-paste-ready commands for each case.	4 / 5
Workflow Clarity	The four-step Core Procedure is clearly sequenced, but the move-to-container operation is effectively irreversible and lacks an explicit validation checkpoint (e.g., confirm the object landed in the correct container or that the rule mapping was applied correctly), which caps workflow clarity per the destructive-operation guideline.	3 / 5
Progressive Disclosure	Content is well sectioned and references a bundled script (scripts/conductivity_test.py) for the error-prone case, but that referenced file does not exist in the bundle, so the reference is not actually navigable; the broken reference keeps this below a 4.	3 / 5
	Total	15 / 20 Passed

Description

83%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 what the skill does and when to trigger it, with concrete input/output and a worked mapping example. It is mostly specific and distinct, with only minor gaps in trigger-term synonyms and a small overlap risk with generic container-placement skills.

Dimension	Reasoning	Score
Specificity	Names the domain (archiving a test object into a container) and concrete actions (place into a designated container, map an outcome to a container via a rule), plus explicit input/output; coverage of multiple test types is implied rather than enumerated, leaving minor gaps.	4 / 5
Completeness	Explicitly answers both 'what' (places an object into a designated container based on a test outcome) and 'when' ('It should be triggered when the agent needs to finalize a task by storing an object according to a rule') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrasing ('finalize a task by storing an object according to a rule', 'test outcome') and concrete examples ('conductive → blue box'), but lacks synonyms or extension-like variations a user might say; a few natural terms are missing.	4 / 5
Distinctiveness Conflict Risk	The niche (archiving a science-test result into a rule-mapped container) is fairly distinct with concrete examples, but the phrasing is generic enough that it could overlap with general 'put object in container' skills; minor overlap risk.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: zjunlp/SkillNet
Path: experiments/src/skills/scienceworld/scienceworld-result-archiver/SKILL.md
Commit: 076c6df

Reviewed: 6 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.