RESOURCE2SKILL: Executable Agent Skills from Multimodal Resources

A Microsoft dataset release for the RESOURCE2SKILL system, which distills human-created multimodal resources into reusable executable skills for software agents. The dataset was last updated on 2026-07-17 and includes structured skill entries for discovery and inspection. The project page, paper, and code are available via the provided links.

Use Cases

• Training software agents to perform tasks based on structured skill entries.
• Discovering and inspecting reusable agent skills based on multimodal resources.
• Benchmarking skill distillation systems for AI agents.
• Developing agent skill libraries for multimodal task execution.

Strengths

• Created and released by Microsoft, a major research institution.
• Based on a system described in a paper on arXiv (2606.29538).
• Includes structured skill entries for discovery and inspection.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and license are unknown, which may limit suitability assessment.

Provenance

Source

Microsoft

Collection Method

Distilled from human-created multimodal resources by the RESOURCE2SKILL system.

Freshness

Last updated 2026-07-17 03:43:38; freshness should be verified.