From spark
Scaffold a new project's runtime with config options — choose frontend/backend and framework, run the canonical scaffolder with Bun (TypeScript) or uv (Python) defaults, and wire it into the Spark lifecycle. Use when starting a new project, scaffolding a runtime, or setting up a frontend/backend stack. Not for wiring services or secrets (`connect`), nor framing/planning the work (`ideate`/`plan`).
How this skill is triggered — by the user, by Claude, or both
Slash command
/spark:bootstrapThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
`bootstrap` stands up a project's runtime by running the stack's **official
bootstrap stands up a project's runtime by running the stack's official
scaffolder with the right flags — it does not hand-roll a directory tree. The
runtime/package-manager defaults are fixed; only the framework on top is a choice.
Concrete per-framework commands and quality-gate defaults live in references/profiles.md.
ideate exists, infer from it; otherwise ask.bun init (lib/CLI).uv init (lib/CLI).bun run build /
uv run …) and confirm it works before moving on. If it fails, report the
output plainly; don't paper over it.bun.lock, uv.lock) so the runtime is reproducible.codify, after planning.bootstrap and connect are the two project-setup skills:
runtime + connectivity. Run them first, then enter
Ideate → Plan → Generate → Solve → Ship.
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub jwogrady/spark --plugin spark