CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

65

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/vercel/skills/next-forge/SKILL.md

The canonical home for this skill is next-forge in vercel/vercel-plugin

SKILL.md
Quality
Evals
Security

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.

A well-structured overview with fully executable commands and exemplary progressive disclosure into four real, well-annotated reference files. The main gap is the absence of validation feedback loops — particularly a verification step after database migrations and any post-deploy check — which caps workflow clarity.

Suggestions

Add a validation checkpoint to the migration workflow, e.g. 'After `bun run migrate`, verify the schema with `bun run db:studio` or check that `packages/database/generated` was regenerated before committing', and note how to handle a failed `db push`.

Add a brief verification step to deployment, such as confirming each Vercel project's root directory and that `bun run build` passes locally before creating the three projects.

Tighten the opening paragraph to avoid restating the frontmatter description, and trim the 'Server Components First' section to just the project-specific conventions (all page/layout files are server components; client code goes in separate 'use client' files).

DimensionReasoningScore

Conciseness

The body is dense and token-efficient — a compact app/port table, exact commands, and no library tutorials. Minor over-explanation remains: the opening paragraph partially restates the frontmatter, and 'Server Components First' mixes project convention (valuable) with Next.js knowledge Claude already has. Not anchor 5 due to this slight framing overhead.

4 / 5

Actionability

Every task section gives copy-paste-ready, executable commands (e.g., `npx next-forge@latest init`, `bun run migrate`, `npx shadcn@latest add [component] -c packages/design-system`, `bun dev --filter app`) with exact file paths (`.env` locations, `schema.prisma`). Coverage spans the common cases: setup, dev, migrations, UI components, lint, test, build, and deployment.

5 / 5

Workflow Clarity

The Quick Start is well sequenced (set `DATABASE_URL` → migrate → add keys → dev) and Common Tasks are clearly separated, but no validation or verification checkpoints appear anywhere. The migration workflow (`bun run migrate` → Prisma format/generate/db push) is a database operation with no verify or rollback step, so per the rubric's cap for missing feedback loops in database contexts this cannot score above 3.

3 / 5

Progressive Disclosure

The body is a genuine overview and pushes detail into four clearly signaled, one-level-deep reference files (`references/architecture.md`, `references/setup.md`, `references/packages.md`, `references/customization.md`), each annotated with its scope — and all four exist on disk. No nesting, no buried references, easy navigation.

5 / 5

Total

17

/

20

Passed

Description

78%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 description with an explicit 'Use when...' trigger clause, concrete command-level triggers, and a clearly demarcated niche. Its only weakness is that the 'what' side — the scope of the guidance itself — is left vague as 'expert guidance' rather than naming the domains it helps with.

DimensionReasoningScore

Specificity

Names the domain concretely ('production-grade Turborepo monorepo SaaS starter by Vercel') and lists specific actions including 'scaffolding with `npx next-forge init`' and 'editing @repo/* workspace packages'. Falls short of anchor 5 because the capabilities the guidance covers (auth, database, payments, etc.) are not enumerated, but exceeds anchor 3 with an exact command and concrete editing targets.

4 / 5

Completeness

Both parts are present: what ('next-forge expert guidance — production-grade Turborepo monorepo SaaS starter by Vercel') and an explicit when ('Use when working in a next-forge project, scaffolding with `npx next-forge init`, or editing @repo/* workspace packages'). Not anchor 5 because the 'what' is somewhat thin — 'expert guidance' does not state which kinds of tasks are covered.

4 / 5

Trigger Term Quality

Includes natural phrases users would say in this context: 'next-forge', 'monorepo', 'SaaS starter', 'Turborepo', '@repo/*', and the init command. A few natural variants are missing (e.g., 'Next.js starter', 'pnpm workspace'), keeping it below the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The description is tightly scoped to next-forge projects via the product name, the `@repo/*` import convention, and the init command, giving it a clear niche with distinct triggers and minimal conflict risk with generic Next.js or monorepo skills.

5 / 5

Total

17

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.