Skills
Reusable workflows, knowledge, and prompt templates invoked on demand or auto-loaded when relevant
Extension Name Skills
Vendor Terms agent skills, SKILL.md, slash commands
Scopes
Project / Repo RootUser / Home
Interfaces IDE, CLI
Availability current (explicit)
Trust Model Reusable instruction packages loaded on demand; can include scripts for deterministic tasks but activation is controlled by the agent
Notes Progressive disclosure (name+description at startup, full content on demand); invokable as slash commands with $ARGUMENTS placeholders; IDE supports importing from GitHub repos; workspace takes priority over global
Extension Name Skills
Vendor Terms skills, SKILL.md, commands, slash commands, Agent Skills standard
Scopes
Project / Repo RootUser / HomeOrganization / Enterprise
Interfaces terminal CLI, VS Code, Desktop, web, JetBrains
Availability current (explicit)
Trust Model Reusable knowledge and workflows loaded on demand or invoked via /name; enterprise deployment via managed settings
Notes Reference skills provide knowledge, action skills trigger workflows; follows Agent Skills open standard (agentskills.io); bundled skills include /batch, /debug, /simplify, /loop, /run, /verify, /deep-research; enterprise deployment via managed settings
Extension Name Agent Skills
Vendor Terms agent skills, SKILL.md, .agents/skills, gh skill
Scopes
Project / Repo RootUser / Home
Interfaces GitHub.com, VS Code, JetBrains, CLI, Copilot SDK
Availability current (explicit)
Trust Model Reusable workflows loaded on demand when relevant; allowed-tools frontmatter pre-approves tool usage
Notes Based on open Agent Skills standard (agentskills.io); cross-tool compatible paths (.github/skills, .claude/skills, .agents/skills); gh skill CLI for discovery/install; org/enterprise skills coming soon
Extension Name Skills
Vendor Terms agent skills, SKILL.md, .agents/skills, $skill-creator
Scopes
Subdirectory / FolderProject / Repo RootUser / HomeMachine / Admin
Interfaces CLI, IDE extension, app
Availability current (explicit)
Trust Model Reusable workflows loaded progressively; skills are the authoring format, plugins are the distribution unit
Notes Six scope tiers from repo to system-bundled; explicit ($-mention) and implicit (description matching) invocation; based on open Agent Skills standard (agentskills.io); can declare MCP dependencies for auto-wiring