Agent skills

Reusable instructions for compatible AI agents.

Explore by field

Loading catalog totals…

Field counts come from the latest full-catalog snapshot. A resource can belong to several fields and platforms.

Search results

Sort by

Agent skill

Facilitates running and logging of LightLLM DeepSeek-R1 EP MoE + MTP server variants for accuracy evaluation workflows.

OpenClawDevelopment & Engineering

ModelTC

Agent skill

Facilitates tensor parallel testing for DeepSeek-R1 models using LightLLM API, optimizing GSM8K evaluations on localhost.

ClaudeCodexOpenClawDevelopment & Engineering

ModelTC

Platform labels describe intended use. Read each resource's author credits, requirements and available access methods.