18 Commands You Can Invoke

Every /ork:X command skill in OrchestKit -- grouped by category with descriptions and usage examples.

What Are Command Skills?

Command skills are the 18 skills with user-invocable: true in their frontmatter. You trigger them by typing /ork:skill-name in Claude Code. Each one is a structured workflow that guides Claude through a multi-step process, often spawning parallel agents and pulling in reference skills automatically.

Command skills differ from reference skills in three ways:

You invoke them explicitly with the /ork: prefix.
They define workflows, not just knowledge -- step-by-step processes with decision points.
They compose other skills via the skills: frontmatter field, pulling in reference skills as needed.

Implementation and Development

These commands handle the core development cycle: building features, fixing bugs, and managing code quality.

Command	Description	Complexity	Example
`/ork:implement`	Full-power feature implementation with parallel subagents. Asks for scope (full-stack, backend-only, frontend-only, quick prototype) and constraints before starting.	medium	`/ork:implement user authentication`
`/ork:fix-issue`	Systematic GitHub issue resolution with hypothesis-based root cause analysis, similar issue detection, and prevention recommendations.	medium	`/ork:fix-issue 123`
`/ork:verify`	Comprehensive verification with parallel test agents. Validates implementations across unit tests, integration tests, security, and type safety.	low	`/ork:verify`
`/ork:explore`	Deep codebase exploration with parallel agents. Maps architecture, discovers patterns, generates ASCII diagrams, and produces health assessments.	low	`/ork:explore`
`/ork:brainstorm`	Design exploration with parallel agents. Generates ideas, compares alternatives, and produces structured recommendations.	medium	`/ork:brainstorm real-time notifications`
`/ork:assess`	Rates quality 0-10 with structured pros/cons analysis. Works on code, designs, approaches, or any artifact.	low	`/ork:assess this API design`
`/ork:write-prd`	Product Requirements Documents with structured 8-section templates, user stories, acceptance criteria, and value proposition validation.	medium	`/ork:write-prd payments feature`

Git and GitHub

Commands for version control and pull request workflows.

Command	Description	Complexity	Example
`/ork:commit`	Creates commits with conventional format and validation. Analyzes staged changes, generates a message, and runs pre-commit checks.	low	`/ork:commit`
`/ork:create-pr`	Creates GitHub pull requests with validation. Runs security scanning, code review, and type checking before opening the PR.	low	`/ork:create-pr`
`/ork:review-pr`	PR review with parallel specialized agents. Checks security, test coverage, type safety, and code quality simultaneously.	medium	`/ork:review-pr 456`

Memory and Knowledge

Commands for storing and retrieving decisions, patterns, and context across sessions.

Command	Description	Complexity	Example
`/ork:remember`	Stores decisions and patterns in the knowledge graph. Supports `--success`, `--failed`, and `--agent` flags for categorization.	low	`/ork:remember --success cursor pagination scales well`
`/ork:memory`	Read-side memory operations: search, load, sync, history, and visualization. Subcommands: `search`, `load`, `sync`, `history`, `viz`, `status`.	low	`/ork:memory search "pagination"`

Plugin Management

Commands for managing OrchestKit itself -- health checks, configuration, and help.

Command	Description	Complexity	Example
`/ork:doctor`	OrchestKit health diagnostics. Validates permissions, hooks, skills, agents, and memory system status.	low	`/ork:doctor`
`/ork:configure`	Configures OrchestKit settings. Interactive wizard for MCP servers, plugin options, and preferences.	low	`/ork:configure`
`/ork:help`	OrchestKit skill directory. Lists available skills grouped by category with descriptions.	low	`/ork:help`
`/ork:setup`	Personalized onboarding wizard. Detects your stack, configures MCPs, generates a readiness score and improvement plan.	low	`/ork:setup`

Visualization

Commands for visualizing plans and architecture before implementation.

Command	Description	Complexity	Example
`/ork:visualize-plan`	Visualize planned changes before implementation. Compares before/after architecture, assesses risk, and analyzes execution order and impact.	low	`/ork:visualize-plan`

How Command Skills Compose Reference Skills

Every command skill lists reference skills in its frontmatter skills: field. When you invoke the command, those reference skills are automatically loaded into context. For example, /ork:implement pulls in:

skills:
  - api-design
  - react-server-components-framework
  - testing-unit
  - testing-e2e
  - testing-integration
  - testing-llm
  - testing-perf
  - explore
  - verify
  - memory

This means you do not need to remember which reference skills exist. The command skill knows what knowledge it needs and loads it automatically.

Invocation Patterns

Basic invocation

/ork:implement user authentication with OAuth

With GitHub issue reference

/ork:fix-issue 123

With flags (memory commands)

/ork:remember --success --category database pgvector handles 10M vectors well
/ork:memory search "caching strategy"

Chaining commands in a session

/ork:explore                          # Understand the codebase
/ork:implement search feature         # Build the feature
/ork:verify                           # Validate the implementation
/ork:commit                           # Commit the changes
/ork:create-pr                        # Open a pull request

What's Next

61 Reference Skills -- The knowledge library that command skills pull from.
Composing Skills Into Workflows -- How these commands orchestrate agents and skills together.
How Skills Work -- The fundamentals of the skill system.

18 Commands You Can Invoke

On this page