Skills Reference

Skills are specialized instruction files that the agent loads on demand when a task matches their domain. They provide conventions, patterns, and guardrails for specific task types. Each skill is a SKILL.md file that gets injected into the agent's context when relevant.

Available Skills

SkillDomainWhen Loaded
cleaveTask decomposition & assessmentUsing /cleave, /assess, or cleave_assess
gitGit conventionsCommitting, branching, tagging, releases
ociContainer & OCI artifactsContainerfile authoring, registry work, multi-arch builds
openspecSpec-driven developmentUsing OpenSpec commands (/opsx:*)
extensionsExtension APICreating or modifying Omegon extensions
tuiTUI component patternsBuilding extension UIs
pythonPython developmentWorking with Python projects (pyproject.toml, pytest, ruff)
rustRust developmentWorking with Rust projects (Cargo, clippy, Zellij plugins)
securitySecurity checklistUser-facing code, template rendering, process spawning
styleVisual style guideCreating visual output (diagrams, themes, images)
typescriptTypeScript conventionsWorking with TypeScript (strict typing, node:test)
vaultObsidian markdownGenerating interlinked documentation

How Skills Work

  1. The agent detects that a task matches a skill's domain
  2. It reads the skill's SKILL.md file using the read tool
  3. The skill's instructions are incorporated into the agent's reasoning
  4. The agent follows the skill's conventions for the duration of the task

Skills are loaded lazily — they only consume context when actually needed. The agent manages skill loading autonomously; operators don't need to specify which skills to use.