scaffold-project

Scaffold a new app, API, backend, fullstack project, monorepo, or starter with Better-T-Stack — including new projects built on a specific framework like Hono, Express, Fastify, Elysia, Next.js, TanStack Router/Start, Nuxt, Svelte, Solid, Astro, or React Native (native-bare, native-uniwind, native-unistyles). Use whenever the user wants to start, create, bootstrap, set up, or initialize a new project/app/API, e.g. "create a Hono app", "start a Next.js project", "scaffold a fullstack app with auth and a database". Prefer generating the project through the Better-T-Stack MCP server (plan then create) over hand-writing package.json, config, and folders.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable workflow that leverages the Better-T-Stack MCP with concrete tool names, explicit config fields, and a plan-before-create validation gate. Minor gains are available from trimming schema-duplicating reference content and adding a full example config payload.

Suggestions

Add one complete example `bts_plan_project` config payload (with realistic field values) so Claude has a copy-paste-ready template, boosting actionability.

Trim or shorten the inline option reference since `bts_get_schema` is already designated as the authoritative source; keep only the non-obvious constraints (e.g., mutually exclusive addons, convex data-layer rule).

Make the error-recovery loop explicit in the workflow (e.g., 'If plan output does not match intent, revise the config and re-run `bts_plan_project` before creating').

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no concept explanations), but the inline option reference partly duplicates the authoritative `bts_get_schema` it directs Claude to, a minor redundancy that could be trimmed.	4 / 5
Actionability	Concrete, executable guidance via named MCP tools (`bts_get_schema`, `bts_plan_project`, `bts_create_project`) and exact field/allowed-value lists, but no full example config payload showing how the fields assemble, a minor gap.	4 / 5
Workflow Clarity	A clear, ordered 5-step workflow with an explicit validation checkpoint (plan is a dry run, confirm with user before `bts_create_project`) and an `install: false` timeout guard; the error-recovery feedback loop is implicit rather than spelled out.	4 / 5
Progressive Disclosure	Well-organized into clear sections (When this applies, Workflow, Required config fields, Option reference, Rules) with no nested references and no bundle files needed, though the sizable inline option reference could arguably live in a separate file.	4 / 5
	Total	16 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that concretely names the capability, the supported frameworks, natural trigger terms with examples, and an explicit use-when clause. It also adds useful steering (prefer the MCP server over hand-writing files).

Dimension	Reasoning	Score
Specificity	Lists multiple concrete project types and frameworks ("app, API, backend, fullstack project, monorepo, or starter" plus Hono, Express, Next.js, React Native variants), giving comprehensive coverage of what can be scaffolded.	5 / 5
Completeness	Explicitly answers both what (scaffold a new project with Better-T-Stack, including named frameworks) and when ("Use whenever the user wants to start, create, bootstrap, set up, or initialize a new project/app/API") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms ("start, create, bootstrap, set up, or initialize") with concrete user-voice examples ("create a Hono app", "start a Next.js project", "scaffold a fullstack app with auth and a database").	5 / 5
Distinctiveness Conflict Risk	The Better-T-Stack-specific niche and framework-enumeration give it a clear, distinct trigger surface with minimal overlap risk against generic scaffolding skills.	5 / 5
	Total	20 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: AmanVarshney01/create-better-t-stack
Path: plugin/skills/scaffold-project/SKILL.md
Commit: 9627a7c

Reviewed: ~2 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.