---
title: "38 Commands You Can Invoke"
description: "Every /ork: command skill in OrchestKit, grouped by task, with what it does and the arguments it takes."
canonical: "https://orchestkit.yonyon.ai/docs/skills/command-skills"
---

# 38 Commands You Can Invoke

Every /ork: command skill in OrchestKit, grouped by task, with what it does and the arguments it takes.

{/* GENERATED by scripts/_build-docs-generate.py from skill frontmatter. Do not edit by hand. */}

## What Are Command Skills?

Command skills are the **38 skills** with `user-invocable: true` in their frontmatter. You trigger them by typing `/ork:<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:

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

---

## Build and Explore

Plan, build, and fix features, from a plain-English goal to working code.

| Command | What it does | Complexity | Usage |
|---------|--------------|------------|-------|
| [`/ork:auto`](/docs/reference/skills/auto) | Intent-classified router, the front door to OrchestKit and the DEFAULT entry point for any goal-shaped request. | medium | `/ork:auto [plain-english goal]` |
| [`/ork:implement`](/docs/reference/skills/implement) | Full-power feature implementation using parallel subagents for backend, frontend, testing, and security, with worktree isolation and quality verification in one workflow. | medium | `/ork:implement [feature-description]` |
| [`/ork:fix-issue`](/docs/reference/skills/fix-issue) | Fixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. | medium | `/ork:fix-issue [issue-number]` |
| [`/ork:explore`](/docs/reference/skills/explore) | Multi-angle codebase exploration spawning 3-5 parallel agents for code structure, data flow, architecture patterns, and health assessment. | high | `/ork:explore [topic-or-feature] [--render=markdown\|json-render\|both] [--effort=low\|medium\|high]` |
| [`/ork:brainstorm`](/docs/reference/skills/brainstorm) | Design exploration using parallel agents through a 7-phase process: topic analysis, memory context, divergent ideation (10+ ideas), feasibility filtering, evaluation with devil's advocate scoring (0-10 across 7 dimensions), synthesis of top approaches, and trade-off comparison. | medium | `/ork:brainstorm [topic-or-idea]` |
| [`/ork:assess`](/docs/reference/skills/assess) | Assesses and rates quality 0-10 across multiple dimensions (correctness, maintainability, security, performance, testability, simplicity) with pros/cons analysis. | high | `/ork:assess [code-path-or-topic] [--render=markdown\|json-render\|both] [--effort=low\|medium\|high\|xhigh]` |
| [`/ork:write-prd`](/docs/reference/skills/write-prd) | Write PRD, Product Requirements Documents with structured 8-section templates, user stories, acceptance criteria, and value proposition validation. | medium | `/ork:write-prd product name or feature` |
| [`/ork:prd-to-goal`](/docs/reference/skills/prd-to-goal) | Decomposes a PRD, issue, or spec into a copy-pasteable single `/goal until ..., or stop after N turns` line. | low | `/ork:prd-to-goal [prd-text \| issue#N \| path/to/spec.md]` |
| [`/ork:swarm-migrate`](/docs/reference/skills/swarm-migrate) | Cross-repo migration swarm, one coordinator + N parallel subagents (one per target repo) that apply the same transformation, open PRs, wait for CI, and report back to a shared JSON ledger. | high | `/ork:swarm-migrate <spec-file.yaml> [--dry-run] [--max-parallel=N]` |

---

## Test and Verify

Write missing tests, run the suites, and check changes in a real browser.

| Command | What it does | Complexity | Usage |
|---------|--------------|------------|-------|
| [`/ork:cover`](/docs/reference/skills/cover) | Generate tests that do not exist yet. | high | `/ork:cover [scope-or-feature]` |
| [`/ork:verify`](/docs/reference/skills/verify) | Grade work that already exists and decide whether it can merge. | high | `/ork:verify [feature-or-scope]` |
| [`/ork:expect`](/docs/reference/skills/expect) | Diff-aware AI browser testing, reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. | high | `/ork:expect [-m <instruction>] [--target unstaged\|branch\|commit] [--flow <slug>] [-y]` |

---

## Git, GitHub, and CI

Commits, pull requests, reviews, and failing CI runs.

| Command | What it does | Complexity | Usage |
|---------|--------------|------------|-------|
| [`/ork:commit`](/docs/reference/skills/commit) | Creates commits with Conventional Commits format (feat/fix/docs/refactor/test/chore), scope detection, co-author attribution, and pre-commit hook compliance. | low | `/ork:commit [message]` |
| [`/ork:create-pr`](/docs/reference/skills/create-pr) | Creates GitHub pull requests with pre-flight validation, conventional title formatting, and structured summary generation. | medium | `/ork:create-pr [title]` |
| [`/ork:review-pr`](/docs/reference/skills/review-pr) | PR review using parallel specialized agents for code quality, security, testing, architecture, and performance analysis. | medium | `/ork:review-pr [pr-number-or-branch]` |
| [`/ork:ci-debug`](/docs/reference/skills/ci-debug) | Diagnose a failing CI run against an 11-pattern playbook. | medium | `/ork:ci-debug <PR-number \| run-URL \| job-URL>` |
| [`/ork:ci-sentinel`](/docs/reference/skills/ci-sentinel) | Daily autonomous classifier for failing PRs across your repos. | medium | `/ork:ci-sentinel [install\|status\|enable\|disable]` |

---

## Design to Code

Turn mockups, screenshots, and design handoffs into components.

| Command | What it does | Complexity | Usage |
|---------|--------------|------------|-------|
| [`/ork:design-import`](/docs/reference/skills/design-import) | Scaffolds React components from a Claude Design handoff bundle and stops at files on disk: no stories, no tests, no pull request. | medium | `/ork:design-import <handoff-url \| path-to-bundle.json>` |
| [`/ork:design-ship`](/docs/reference/skills/design-ship) | One-shot pipeline turning a claude.ai/design link into a pull request: scaffold via /ork:design-import, stories and specs via /ork:cover, browser verification via /ork:expect, then open the PR. | complex | `/ork:design-ship <handoff-url \| path-to-bundle.json>` |
| [`/ork:design-to-code`](/docs/reference/skills/design-to-code) | Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. | complex | `/ork:design-to-code [screenshot-path \| description \| url]` |
| [`/ork:design-context-extract`](/docs/reference/skills/design-context-extract) | Extract design DNA from app screenshots, live URLs, or screen recordings using Google Stitch, color palettes, typography, spacing tokens, component patterns, and motion specs as design-tokens.json or Tailwind config. | medium | `/ork:design-context-extract [screenshot-path \| video-path \| url \| 'current project']` |
| [`/ork:design-stylecards`](/docs/reference/skills/design-stylecards) | Declarative catalog of named aesthetic recipes, exact shadow stacks, glass surfaces, gradient treatments, and type scales as copy-paste values with Use-When and Avoid rules. | low | `/ork:design-stylecards [list \| <recipe-name> \| apply <recipe> to <file>]` |
| [`/ork:component-search`](/docs/reference/skills/component-search) | Search 21st.dev component registry for production-ready React components. | simple | `/ork:component-search [component description]` |

---

## Memory and Knowledge

Store and recall decisions, patterns, and release knowledge across sessions.

| Command | What it does | Complexity | Usage |
|---------|--------------|------------|-------|
| [`/ork:remember`](/docs/reference/skills/remember) | Write-side memory: stores decisions, patterns, and outcomes in the MCP memory knowledge graph as entities with typed observations and relations. | low | `/ork:remember [decision-or-pattern]` |
| [`/ork:memory`](/docs/reference/skills/memory) | Read-side memory operations on the knowledge graph: search past decisions and patterns, load session context, view decision timelines, render Mermaid graph visualizations. | low | `/ork:memory [subcommand] [query]` |
| [`/ork:dream`](/docs/reference/skills/dream) | Nightly memory consolidation: prunes stale entries, merges duplicates, resolves contradictions, rebuilds the MEMORY.md index. | medium | `/ork:dream [--dry-run]` |
| [`/ork:release-sync`](/docs/reference/skills/release-sync) | Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. | low | `/ork:release-sync [version]` |

---

## Dev Loop and Visuals

Local dev URLs, served pages, and visual answers in chat.

| Command | What it does | Complexity | Usage |
|---------|--------------|------------|-------|
| [`/ork:dev`](/docs/reference/skills/dev) | One-command dev loop boot. | medium | `/ork:dev [start\|stop\|status] [--share\|--funnel\|--live H]` |
| [`/ork:page-serve`](/docs/reference/skills/page-serve) | Hand a human a rendered HTML page at a stable HTTPS URL. | low | `/ork:page-serve [path] [--name slug] [--screenshot\|--no-screenshot] \| stop [name\|--all] \| status [--json]` |
| [`/ork:glyph`](/docs/reference/skills/glyph) | Render an answer as ASCII art plus semantic emojis inline with no setup questions: one render per reply, verdict first. | low | `/ork:glyph [--chat\|--ask\|--page] [--eli5] [--decide] [--signoff] [topic-to-render]` |
| [`/ork:visualize-plan`](/docs/reference/skills/visualize-plan) | Renders planned changes, architecture and before/after comparisons, risk heat maps, execution order, dependency graphs, impact metrics, in your chosen output format (ASCII + emojis, an interactive HTML playground, or a NotebookLM infographic). | medium | `/ork:visualize-plan [plan-or-issue]` |

---

## Plugin Management

Set up, diagnose, and inspect OrchestKit itself.

| Command | What it does | Complexity | Usage |
|---------|--------------|------------|-------|
| [`/ork:setup`](/docs/reference/skills/setup) | Personalized 7-phase onboarding wizard that scans the codebase, detects tech stack, recommends skills and MCP servers, and generates an improvement plan with readiness score. | medium | `/ork:setup [--rescan] [--score-only] [--plan-only] [--channel] [--configure]` |
| [`/ork:doctor`](/docs/reference/skills/doctor) | OrchestKit doctor for health diagnostics across manifest integrity, hook configuration, skill validation, agent frontmatter, MCP server connectivity, CC version compatibility, and permission rules. | low | `/ork:doctor [--verbose]` |
| [`/ork:help`](/docs/reference/skills/help) | OrchestKit help directory with categorized skill listings. | low | `/ork:help [category]` |
| [`/ork:audit-activation`](/docs/reference/skills/audit-activation) | Audits sub-agent activation from explicit consumer telemetry roots. | medium | `/ork:audit-activation [--json]` |
| [`/ork:telemetry-inspect`](/docs/reference/skills/telemetry-inspect) | Inspects the OrchestKit telemetry pipeline for the current project, lists all known telemetry files with write counts, sizes, schema status, growth trend, and orphan detection. | low | `/ork:telemetry-inspect [--session <id>] [--json]` |

---

## More Commands

Commands not yet filed under a task above.

| Command | What it does | Complexity | Usage |
|---------|--------------|------------|-------|
| [`/ork:careful`](/docs/reference/skills/careful) | Blocks destructive shell commands once invoked: a PreToolUse Bash guard denies rm -rf outside temp dirs, force pushes and remote branch deletes, git reset --hard, DROP TABLE / DROP DATABASE / TRUNCATE, kubectl delete and terraform or tofu destroy, including inside ssh remote commands, and makes Claude ask the operator. | low | `/ork:careful` |
| [`/ork:freeze`](/docs/reference/skills/freeze) | Confines file edits to one directory until lifted: an Edit, Write, MultiEdit and NotebookEdit hook refuses any path whose real location, symlinks followed, falls outside the frozen dir. | low | `/ork:freeze <dir> \| off` |

---

## How Command Skills Compose Reference Skills

Every command skill lists the skills it needs in its frontmatter `skills:` field. When you invoke it, those skills load into context. For example, `/ork:implement` pulls in:

```yaml
skills:
  - api-design
  - react-server-components-framework
  - testing-unit
  - testing-e2e
  - testing-integration
  - explore
  - verify
  - memory
  - scope-appropriate-architecture
  - chain-patterns
```

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

---

## 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

- [72 Reference Skills](/docs/skills/reference-skills): the knowledge library that command skills pull from.
- [Composing Skills Into Workflows](/docs/skills/skill-composition): how these commands orchestrate agents and skills together.
- [How Skills Work](/docs/skills/overview): the fundamentals of the skill system.