$npx -y skills add Rune-kit/rune --skill scaffoldAutonomous project bootstrapper. Generates complete project from a description — structure, code, tests, docs, config. Orchestrates ba → plan → design → fix → test → docs → git in one pipeline. The \"0 to production-ready\" skill.
| 1 | # scaffold |
| 2 | |
| 3 | ## Purpose |
| 4 | |
| 5 | The "zero to production-ready" orchestrator. Takes a project description and autonomously generates a complete, working project — directory structure, code, tests, documentation, git setup, and verification. Orchestrates 8+ skills in sequence to produce output that builds, passes tests, and is ready for development. |
| 6 | |
| 7 | <HARD-GATE> |
| 8 | Generated projects MUST build and pass tests. A scaffold that produces broken code is WORSE than no scaffold. Phase 9 (VERIFY) is mandatory — if verification fails, fix before presenting to user. |
| 9 | </HARD-GATE> |
| 10 | |
| 11 | ## Triggers |
| 12 | |
| 13 | - `/rune scaffold <description>` — Interactive mode (asks questions) |
| 14 | - `/rune scaffold express <detailed-description>` — Express mode (autonomous) |
| 15 | - Called by `team` when task is greenfield project creation |
| 16 | - Auto-trigger: when user says "new project", "start from scratch", "bootstrap", "create a new [app/api/lib]" |
| 17 | |
| 18 | ## Calls (outbound) |
| 19 | |
| 20 | - `ba` (L2): Phase 1 — requirement elicitation (always, even in Express mode) |
| 21 | - `sentinel-env` (L3): Phase 1.5 — environment pre-flight (validate runtime versions, ports, required tools before generating code) |
| 22 | - `research` (L3): Phase 2 — best practices, starter templates, library comparison |
| 23 | - `plan` (L2): Phase 3 — architecture and implementation plan |
| 24 | - `design` (L2): Phase 4 — design system (frontend projects only) |
| 25 | - `skill-forge` (L2): when scaffolded project includes custom skills or plugin structure |
| 26 | - `fix` (L2): Phase 5 — code generation (implements the plan) |
| 27 | - `team` (L1): Phase 5 — parallel implementation when 3+ independent modules |
| 28 | - `test` (L2): Phase 6 — test suite generation |
| 29 | - `docs` (L2): Phase 7 — README, API docs, architecture doc |
| 30 | - `git` (L3): Phase 8 — initial commit with semantic message |
| 31 | - `verification` (L3): Phase 9 — lint + types + tests + build |
| 32 | - `sentinel` (L2): Phase 9 — security scan on generated code |
| 33 | |
| 34 | ## Called By (inbound) |
| 35 | |
| 36 | - User: `/rune scaffold` direct invocation |
| 37 | - `team` (L1): when decomposed task is a new project |
| 38 | - `cook` (L1): when task is classified as greenfield (rare — cook usually handles features, not projects) |
| 39 | |
| 40 | ## Modes |
| 41 | |
| 42 | ### Interactive Mode (default) |
| 43 | |
| 44 | Full phase-gate workflow. User reviews and approves at each major phase: |
| 45 | 1. BA asks 5 questions → user answers |
| 46 | 2. Plan presented → user approves |
| 47 | 3. Design system presented → user approves (if frontend) |
| 48 | 4. Implementation proceeds |
| 49 | 5. Results presented with full report |
| 50 | |
| 51 | ### Express Mode |
| 52 | |
| 53 | Autonomous mode for detailed descriptions. User provides enough context upfront: |
| 54 | 1. BA extracts requirements from description (no questions asked) |
| 55 | 2. Plan auto-approved (user gave enough detail) |
| 56 | 3. Implementation proceeds autonomously |
| 57 | 4. User reviews only the final output |
| 58 | |
| 59 | <HARD-GATE> |
| 60 | Express mode MUST still validate. Auto-approve doesn't mean skip quality checks. |
| 61 | BA still extracts requirements — it just doesn't ask questions. |
| 62 | Verification (Phase 9) is NEVER skipped in any mode. |
| 63 | </HARD-GATE> |
| 64 | |
| 65 | ## Project Templates |
| 66 | |
| 67 | Auto-detected from BA output. Template selection informs Phase 3 (Plan) architecture decisions. |
| 68 | |
| 69 | | Template | Stack | Key Generation Targets | |
| 70 | |----------|-------|----------------------| |
| 71 | | REST API | Node.js/Python + DB + Auth | Routes, models, middleware, migrations, Docker, CI | |
| 72 | | Web App (Full-stack) | Next.js/SvelteKit + DB | Pages, components, API routes, auth, DB setup | |
| 73 | | CLI Tool | Node.js/Python/Rust | Commands, arg parsing, config, tests | |
| 74 | | Library/Package | TypeScript/Python | Src, tests, build config, npm/pypi publish setup | |
| 75 | | MCP Server | TypeScript/Python | Tools, resources, handlers, tests (delegates to mcp-builder) | |
| 76 | | Chrome Extension | React/Vanilla | Manifest, popup, content script, background, tests | |
| 77 | | Mobile App | React Native/Expo | Screens, navigation, auth, API client | |
| 78 | |
| 79 | ## Executable Steps |
| 80 | |
| 81 | ### Phase 1 — BA (Requirement Elicitation) |
| 82 | |
| 83 | Invoke `rune:ba` with the user's project description. |
| 84 | |
| 85 | **Interactive Mode**: BA asks 5 questions, discovers hidden requirements, produces Requirements Document. |
| 86 | |
| 87 | **Express Mode**: BA extracts requirements from the detailed description without asking questions. Still produces Requirements Document with scope, user stories, and acceptance criteria. |
| 88 | |
| 89 | Output: `.rune/features/<project-name>/requirements.md` |
| 90 | |
| 91 | Gate: In Interactive mode, user must approve requirements before proceeding. |
| 92 | |
| 93 | ### Phase 2 — RESEARCH (Best Practices & Templates) |
| 94 | |
| 95 | Invoke `rune:research` to find: |
| 96 | - Best practices for the detected project type |
| 97 | - Recommended libraries (compare 2-3 options for each concern) |
| 98 | - Starter templates or skeleton projects to reference |
| 99 | - Common pitfalls for th |