CtrlK
BlogDocsLog inGet started
Tessl Logo

agentsociety-use-dataset

Use when external datasets need to be searched, inspected, or downloaded for experiments or analysis.

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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./extension/skills/agentsociety-use-dataset/v1.0.0/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 content is well-structured and actionable: a command quick-reference, a workflow graph, common mistakes, and pipeline context, with detail correctly offloaded to two real reference files. It is just shy of perfect only because a copy-paste example invocation and an explicit validation checkpoint would push actionability and workflow clarity to the top anchor.

Suggestions

Add one copy-paste example invocation (e.g. `$PYTHON_PATH .agentsociety/bin/ags.py use-dataset search --category surveys`) to make the quick reference immediately runnable.

Make the post-download validation explicit in the workflow (e.g. 'After download, run info <id> to confirm version matches remote') to add a clear checkpoint.

DimensionReasoningScore

Conciseness

The body is lean: a quick-reference command table, a dot-graph workflow, a common-mistakes table, and pipeline position, with no padding explaining what datasets are. Only minor tightening opportunities remain.

4 / 5

Actionability

Provides a concrete command table with real subcommands and flags plus the exact invocation path '.agentsociety/bin/ags.py'; fully actionable, though a single copy-paste example invocation line would make it copy-paste ready.

4 / 5

Workflow Clarity

A clear browse→readme→download→inspect→update sequence is shown via the dot graph, with the Common Mistakes table functioning as implicit checkpoints (read README first, check for updates). No explicit validate→fix→retry loop, but the operations are low-risk so checkpoints are adequate.

4 / 5

Progressive Disclosure

SKILL.md is an overview that clearly signals one-level-deep references to real files (references/listing-guide.md and references/metadata-format.md), keeping detailed material out of the main body with easy navigation.

5 / 5

Total

17

/

20

Passed

Description

75%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 is concise, third-person, and answers both what and when with three concrete actions and an explicit 'Use when' clause. It falls just short of top marks because it lacks the most natural verbatim trigger phrases and could be marginally more comprehensive.

Suggestions

Add the natural verbatim triggers users say, e.g. 'Use when the user says "find data", "download dataset", or "browse datasets"'.

Consider naming file formats or dataset types (e.g. survey data, agent profiles) in the description to boost specificity and distinctiveness.

DimensionReasoningScore

Specificity

Names the dataset domain plus three concrete actions ('searched, inspected, or downloaded'), giving several specific capabilities with only minor gaps versus a fully comprehensive list.

4 / 5

Completeness

Explicitly states what (search/inspect/download datasets) and when ('Use when external datasets need to be...for experiments or analysis'), with the 'when' clause present though it could be slightly more concrete with trigger phrases.

4 / 5

Trigger Term Quality

Includes natural terms ('datasets', 'searched, inspected, or downloaded', 'experiments or analysis') but omits the most common verbatim phrasings like 'find data' or 'download dataset', so a few natural terms are missing.

4 / 5

Distinctiveness Conflict Risk

The 'external datasets' consumption niche is mostly distinct from sibling create/experiment skills, with minimal overlap risk.

4 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
tsinghua-fib-lab/AgentSociety
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.