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.

64

Quality

77%

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 ./skills/next-forge/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 excellent progressive disclosure and largely copy-paste-ready commands. The weak spot is workflow clarity: setup and especially database migration workflows lack validation/verification checkpoints, which the rubric explicitly caps for database operations.

Suggestions

Add a verification step after "bun run migrate" (e.g. "then run `bun run db:studio` or `prisma studio` to confirm the schema applied"), which is required to lift workflow_clarity above 3 for a database operation.

Add a validation checkpoint to Quick Start (e.g. "run `bun run dev` and confirm the app boots on :3000 before adding optional integrations").

Flesh out "Adding a New Package" and "Deployment" with a minimal concrete example (a sample package.json or the exact Vercel project-root settings) instead of prose-only description.

DimensionReasoningScore

Conciseness

The body is mostly tables, commands, and file paths with little padding; a few lines explain things Claude already knows ("Apps are deployable applications. Packages are shared libraries imported as @repo/<package-name>", the server-components recap). Fits anchor 4 — efficient with minor trimmable over-explanation — rather than 3, where unnecessary explanation would be more than incidental.

4 / 5

Actionability

Most tasks are copy-paste ready ("npx next-forge@latest init", "bun run migrate", "npx shadcn@latest add [component] -c packages/design-system", "bun dev --filter app"), but "Adding a New Package" ("Create a new directory in /packages/ with a package.json...") and "Deployment" remain at the hint/prose level without concrete steps or examples. Anchor 4, not 5, due to those gaps.

4 / 5

Workflow Clarity

The Quick Start is a clearly numbered sequence (set DATABASE_URL → migrate → add keys → dev) and per-task commands are unambiguous, but there are no validation or verification checkpoints anywhere — notably the database migration workflow ("bun run migrate. This runs Prisma format, generate, and db push in sequence") modifies schema with no step to verify success. Per the rubric's cap, a database operation without validation cannot score above 3; not 4 because checkpoints are absent rather than merely minor.

3 / 5

Progressive Disclosure

The body is a genuine overview — an apps table, a package name-list, and command snippets — that delegates detail to four clearly annotated, one-level-deep references ("references/setup.md — Installation, prerequisites, environment variables...", and similarly architecture/packages/customization), all of which exist and are substantive. Anchor 5, not 4, because navigation is easy and nothing that belongs in a reference is inlined.

5 / 5

Total

16

/

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.

A strong description: explicit what-and-when structure with concrete, distinctive triggers tied to a uniquely named product. The main weakness is that the capability side relies on the vague phrase "expert guidance" rather than enumerating what the skill actually helps with.

Suggestions

Replace or augment the vague "expert guidance" phrase with 2-3 concrete capabilities, e.g. "scaffolds new projects, configures integrations (auth, database, payments), and maintains @repo/* workspace packages".

Add common natural variations users might say — e.g. "next forge", "monorepo starter kit", or "Turborepo template" — to broaden trigger coverage.

DimensionReasoningScore

Specificity

"production-grade Turborepo monorepo SaaS starter" names the domain clearly and "scaffolding with `npx next-forge init`" / "editing @repo/* workspace packages" give a couple of concrete actions, but the skill's capabilities are implied ("expert guidance") rather than enumerated. Matches anchor 3 — not 4, since it doesn't list several specific actions the skill performs.

3 / 5

Completeness

Both parts are explicitly answered: the what is "next-forge expert guidance — production-grade Turborepo monorepo SaaS starter by Vercel" and the when is a concrete trigger clause — "Use when working in a next-forge project, scaffolding with `npx next-forge init`, or editing @repo/* workspace packages." Not 4, because the when-clause is fully explicit with specific triggers rather than merely adequate.

5 / 5

Trigger Term Quality

Good natural keyword coverage: "next-forge", "Turborepo", "monorepo", "SaaS starter", "@repo/*", and the "next-forge init" command. A few natural terms are missing (e.g. "next forge" spelled out, "starter kit"/"template", "pnpm-workspace"), so it fits anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

"next-forge" is a uniquely named product, and triggers like `@repo/*` workspace packages and `npx next-forge init` are distinct to it — a clear niche with minimal conflict risk with other Next.js or monorepo skills.

5 / 5

Total

17

/

20

Passed

Validation

81%

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

Validation — 13 / 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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
vercel/vercel-plugin
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.