Add vapi-bootstrap-framework skill#4
Merged
Conversation
Scaffolds a full Bun + TypeScript Vapi voice-agent project from a ROUGH_DRAFT.md spec: scenario registry, per-language voice/transcriber stack, prompt composer, assistant builder, and an idempotent bootstrap script. Registers the skill in the plugin marketplace and adds it to the README/CLAUDE.md skill listings. Co-authored-by: Cursor <cursoragent@cursor.com>
adhamvapi
approved these changes
May 28, 2026
The previous wording singled out Vapi/OpenAI/Deepgram as examples, which biased the skill toward a single project context. Generalizing to "brand and product names" keeps the rule applicable to any project that adopts the framework. Co-authored-by: Cursor <cursoragent@cursor.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
vapi-bootstrap-frameworkskill that scaffolds a complete Bun + TypeScript Vapi voice-agent project from aROUGH_DRAFT.mdspec —package.json,.env.example,.gitignore, the full framework spine (languages.ts,loadPrompt.ts,scenarios/index.ts,buildAssistant.ts, Spanish preamble), per-scenario content files, and an idempotentsrc/bootstrap.tsthat creates/updates one assistant per(scenario × language)tuple via@vapi-ai/server-sdk.license,compatibility,metadata.author,metadata.version)..claude-plugin/marketplace.json, the README's Available Skills table, and theCLAUDE.mdskill list so all three stay in sync.Test plan
ROUGH_DRAFT.mdcontaining 2–3## N. <scenario>sections and confirm it generates the spine + per-scenario files without overwriting existing root files.bun install && bun run bootstrapcreates one assistant per(scenario × language)and prints the env var lines on the first run.VAPI_ASSISTANT_<SCENARIO>_<LANG>=lines into.env.local, re-runbun run bootstrap, and confirm every tuple reports "Updated" (idempotent).Made with Cursor