hay-kot/scaffold/scaffold-run
Claude Code and agent skill by hay-kot/scaffold
- community
Checking that the SKILL.md file is still in the repository.
Install
npx vskill@latest install hay-kot/scaffold/scaffold-runSKILL.md
scaffold-run — Use scaffold CLI to generate projects/files
User-invocable: true Auto-triggerable: true
Triggers when: User wants to run a scaffold, generate a project, create files from a template, or use the scaffold CLI.
Workflow
1. Discover available scaffolds
Lists all scaffolds: aliases (from scaffoldrc), local (in .scaffold/), and system (cached remote repos). Use --json for programmatic output.
2. Inspect a scaffold before running
Outputs JSON with questions (name, type, default, options), presets, computed values, features, and messages. Use this to understand what variables a scaffold expects.
3. Run a scaffold interactively
Launches an interactive prompt for project name and all questions. The scaffold argument can be:
- An alias name (defined in scaffoldrc)
- A short reference (
gh:org/repo) - A URL (
https://github.com/org/repo) - An absolute or relative filesystem path
- A bare name (searched in
--scaffold-dirdirectories, default.scaffold/)
4. Run non-interactively
Use --no-prompt to skip all interactive prompts. Provide variables via:
--preset <name>— loads a named preset from the scaffold's config- Positional
key[:type]=valuearguments — override or supplement preset values
CLI arguments take precedence over preset values.
If no Project variable is set in non-interactive mode, a random name scaffold-test-NNNN is auto-generated.
5. Validate with dry-run
Renders the scaffold fully but writes nothing to disk. Outputs JSON:
6. In-memory testing with snapshot
Renders entirely in memory and outputs a full AST with file contents to stdout. Ideal for CI/CD validation and diffing.
7. Passing typed variables
Variables use key[:type]=value syntax. See variable-syntax.md for the full type reference.
Common examples:
Key flags for scaffold new
| Flag | Default | Description | |
|---|---|---|---|
--no-prompt | false | Disable interactive prompts | |
--preset | — | Preset name for variable values | |
--output-dir | . | Output directory (:memory: for in-memory) | |
--dry-run | false | Show what would be created (JSON) | |
--snapshot | — | Output AST to path or stdout | |
--overwrite | false | Overwrite existing files | |
--force | true | Allow dirty git working tree |
Tips
- Always
scaffold inspectfirst to understand a scaffold's variables and presets - Use
--dry-runbefore real runs to verify output paths - Combine
--output-dir :memory:with--snapshot stdoutfor zero-disk testing - When
--no-promptis active, hooks withrun_hooks=promptare skipped - Pre/post messages are suppressed in
--no-promptmode
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingplugins/scaffold/skills/scaffold-run/SKILL.md
Popularity
- Repository stars
- 179
- Repository forks
- 24
- 7-day trend score
- 26
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 19 Mar 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/hay-kot/scaffold/scaffold-run)