next-forge

next-forge expert guidance — production-grade Turborepo monorepo SaaS starter by Vercel. Use when working in a next-forge project, scaffolding with `npx next-forge init`, or editing @repo/* workspace packages.

Quality

81%

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

80%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.

The content is a well-organized, actionable overview that defers detail to four real reference files. Its main weakness is workflow clarity: destructive database operations lack explicit validation/verification steps, which caps that dimension.

Suggestions

Add an explicit validation/verification step to the database migration workflow (e.g., run `bun run dev` / Prisma Studio or check migration status after `bun run migrate`) and a retry-on-error loop, which would lift workflow_clarity above the destructive-operation cap of 3.

Trim basic-concept asides (e.g., defining what apps vs packages are in a monorepo) that Claude already knows to push conciseness toward 5.

Reference the four `references/*.md` files inline at their relevant sections rather than only in the closing list, so navigation is signposted where each topic is introduced.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tables and concrete commands, but includes minor over-explanation of concepts Claude already knows (e.g., "Apps are deployable applications. Packages are shared libraries imported as `@repo/<package-name>`."). It is not a 5 because of those padded asides, and not a 3 because the bulk is lean rather than noticeably verbose.	4 / 5
Actionability	Provides copy-paste-ready commands throughout (`npx next-forge@latest init`, `bun run migrate`, `npx shadcn@latest add [component] -c packages/design-system`), a ports table, and concrete env-var paths covering the common cases. It is not a 4 because the guidance is fully executable, not merely mostly executable.	5 / 5
Workflow Clarity	Quick Start is a numbered sequence and migrations are ordered, but neither includes an explicit validation/verification checkpoint for the potentially destructive `db push`, which caps the score. It is not a 4 because validation checkpoints are absent, and not a 2 because a clear sequence does exist.	3 / 5
Progressive Disclosure	The body is a concise overview with well-signaled one-level-deep references to four verified files (architecture.md, setup.md, packages.md, customization.md), each annotated with its contents and one referenced inline. It is not a 4 because navigation and content split are clean with no nesting.	5 / 5
	Total	17 / 20 Passed

Description

82%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.

The description is strong: it states a clear purpose and gives an explicit, concrete "Use when" trigger clause tied to project-specific signals. It is comprehensive on completeness and distinctiveness, with only minor gaps in action coverage and trigger synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain (next-forge, Turborepo monorepo SaaS starter) and two concrete actions — "scaffolding with `npx next-forge init`" and "editing @repo/* workspace packages" — but coverage is not comprehensive. It is not a 4 because only two actions are listed, and not a 2 because the actions are specific rather than generic.	3 / 5
Completeness	Explicitly answers both what ("next-forge expert guidance — production-grade Turborepo monorepo SaaS starter") and when ("Use when working in a next-forge project, scaffolding with `npx next-forge init`, or editing @repo/* workspace packages") with concrete trigger phrases. It is not a 4 because the when clause is fully explicit rather than merely adequate.	5 / 5
Trigger Term Quality	Includes natural terms users would say ("next-forge", "npx next-forge init", "@repo/*", "monorepo SaaS starter") with good coverage. It is not a 5 because a few natural synonyms/extensions are missing, and not a 3 because the keyword set is clearly strong rather than partial.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (the next-forge project) with project-specific triggers (`next-forge`, `@repo/*`) that are unlikely to fire for unrelated skills. It is not a 4 because overlap risk is minimal, not merely reduced.	5 / 5
	Total	17 / 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: openai/plugins
Path: plugins/vercel/skills/next-forge/SKILL.md
Commit: 1e28582

Reviewed: 8 days 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.