cursor-skills-system
cursor-skills-system
Cursor follows the Agent Skills spec: drop a folder in .cursor/skills/<name>/ with a SKILL.md and the agent can invoke it on demand. The SDK loads project and user skills when local.settingSources includes the matching scope.
When to use
- Packaging reusable instructions / scripts as a named skill
- Choosing project vs user vs team scope
- Writing spec-compliant
SKILL.mdfrontmatter - Structuring atomic
references/*.mdfor an agent to traverse
Concepts
- [[references/folder-layout]] —
.cursor/skills/<name>/SKILL.md+references/ - [[references/skill-md-frontmatter]] — required and optional fields
- [[references/skill-graph-pattern]] — Map-of-Content + atomic references with
[[wikilinks]] - [[references/scopes]] — project, user, plugins
- [[references/sdk-integration]] — loading via
local.settingSources
More from hktitan/cursor-sdk
cursor-hooks
File-based agent loop hooks via `.cursor/hooks.json` — pre/post commands, governance gates. Use when enforcing policy without modifying agent prompts.
1cursor-runs
Run lifecycle, streaming, follow-ups, and conversation introspection in the Cursor SDK. Use when consuming agent output, handling progress events, or chaining turns.
1cursor-subagents
Define delegated subagents on a Cursor SDK agent via the `agents` field — `AgentDefinition`, MCP scoping, and model inheritance. Use when decomposing work across specialist personas.
1cursor-sdk
Entry point for the Cursor TypeScript SDK — install, auth, and the Agent.create / Agent.resume / Agent.prompt lifecycle. Use when starting any Cursor SDK integration or wiring durable agent IDs.
1cursor-errors
CursorAgentError class hierarchy, isRetryable, and recovery patterns. Use when classifying SDK failures, building retry logic, or surfacing actionable messages.
1cursor-models
Model discovery and selection on Cursor SDK — Cursor.models.list, ModelSelection, parameters (e.g. thinking levels), per-run sticky overrides.
1