Creation pipeline for Claude Code products — research, create, validate, and publish skills, agents, squads, minds, and 9 more product types with 10 validation stages and 20 structural quality patterns.
Scaffold a new product with MCS-1 valid structure and WHY comments. Supports all 13 types. Use when the creator says 'new skill', 'create', 'scaffold', 'start building', or wants to start a new product.
Search the marketplace, analyze competition, discover gaps, and find inspiration. Use when: 'explore', 'search marketplace', 'what exists for', 'competitors', 'market gap', 'trending', or before browsing the marketplace. For domain research with build recommendations, use /scout instead.
Guide content filling for scaffolded products. Walks sections, asks domain questions, writes expertise into files. Use after /create in 'scaffold' state, or when the creator says 'fill', 'add content', or 'help me complete this'.
Show all available Studio Engine commands with descriptions. Displays command list organized by category, current edition features, and quick start guide. Use when the creator asks "help", "commands", "what can I do", or "how does this work".
Import existing skills from .claude/skills/ into the Engine workspace for validation, packaging, and publishing. Auto-detects type, creates .meta.yaml, runs MCS-1 check. Use when: 'import', 'bring in', 'add existing skill', or to scan inventory.
Extract and structure domain knowledge into domain-map.md for product creation. Asks targeted questions, maps expertise for /create and /fill. Use when the creator says 'map', 'map my knowledge', 'extract expertise', or before complex products.
Set up or update your myClaude creator profile. Builds creator.yaml with expertise, goals, technical level, and preferences. Use on first run, 'set up profile', 'who am I', 'my profile', 'get started', or 'configure'.
Package a product for distribution across 33+ platforms. Strips WHY comments, generates triple manifests (vault.yaml + plugin.json + agentskills.yaml), stages .publish/. Use when: 'package', 'prepare for publish', or 'bundle it'.
Publish a packaged product to myclaude.sh via the CLI. Shows summary, requires confirmation, runs myclaude validate + myclaude publish. Use when the creator says "publish", "ship it", "go live", or after /package.
Research a domain before building products. Tests Claude's baseline knowledge, identifies gaps, scans the marketplace, runs deep research, and recommends the optimal product setup. Use when: 'scout', 'research domain', 'what should I build for', 'analyze domain', or before /create for any non-trivial product.
Display Studio Engine status dashboard. Shows version, edition, creator profile, products with scores, and stale warnings. Use when: 'status', 'dashboard', 'show my products', or at session start.
Sandbox test a product in an isolated worktree. Runs 3 scenarios (happy path, edge case, adversarial), verifies activation protocol, reports results. Use when the creator says 'test', 'try it', 'does it work', or before publishing.
Brainstorm, evaluate, or decide during product creation. Pause the pipeline to think through a problem, compare approaches, or explore ideas before committing. Use when: 'think about', 'brainstorm', 'evaluate', 'compare', 'should I', 'help me decide', 'what if', 'not sure about', or any hesitation during /fill.
Run MCS quality validation on products in workspace/. Three-tier system: MCS-1 structure, MCS-2 quality + anti-commodity, MCS-3 deep review. Returns scored reports with fix instructions. Use when: 'validate', 'check quality', or before publishing.
Run a comprehensive codebase health analysis covering dead code, dependency freshness, test coverage gaps, security surface, and complexity hotspots. Produces a scored report with prioritized remediation. Use when the user asks to "check health", "audit the codebase", "code quality", or "technical debt".
Architecture specialist for code review. Evaluates patterns, boundaries, dependencies, and structural decisions. Use when reviewing config, routing, or schemas.
Performance specialist for code review. Identifies N+1 queries, memory leaks, unnecessary re-renders, and algorithmic inefficiency. Use for perf-sensitive code.
Security specialist for code review. Finds vulnerabilities, injection risks, auth gaps, and data exposure. Use when code-review-team routes security-related files.