$ loading_
Semantically search a local skill library and load only relevant skills on demand.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "skill-depot" yet — see the docs or source repo.
Semantically search the local Markdown skill database for skills most relevant to “designing a prompt review workflow for an AI assistant,” and return only high-level summaries first.
Returns concise summaries of the most relevant skills so the user can shortlist before loading details.
First find skills related to “RAG retrieval quality optimization,” then expand only the top two results with detailed steps and cautions.
Provides a candidate skill list first, then loads detailed content for only the top two skills to reduce irrelevant context.
I am building a multi-tool AI workflow. Retrieve the skills most relevant to tool-call planning, context compression, and error recovery from the skill library.
Outputs the skill set most relevant to the current workflow, helping the AI agent fetch needed capabilities dynamically.
Create, refine, validate, and restructure AgentSkills and SKILL.md files.
Compile websites, docs, and repos into SKILL.md packages for coding agents.
Create, refine, and evaluate AI skills for better performance and triggering accuracy.
Generate reusable AI agent skills and draft configs from website documentation.
Search and discover Agent Skills tools and capabilities in the skills.sh registry.
Create, refine, and troubleshoot AI skills, specs, invocation, and compatibility.