agentleFS
kuker24kuker24/OpenCodeBestFriend/skills/vercel-ops/SKILL.md

vercel-ops

Skill0 starsChanged 2 months agoMITView on GitHub

Use when the user configures Vercel deploy, project env (names only), Next.js app router hosting, preview URLs, or vercel.json. Not for inventing visual UI, not for frontend-design aesthetics, not for Mongo/Supabase schema.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    NO UI generation: Do not design or style user interfaces, landing pages, or components.

    line 25
  2. Distinctive:

    NO Design Bank access: Do not search, crawl, or load Design Bank assets.

    line 26
  3. Distinctive:

    NO secret exposure: Never print secret tokens, production tokens, or environment variable values.

    line 27
  4. Very specific:

    NO auto-prod deploys: Never run vercel --prod automatically without explicit user command.

    line 28
  5. Very specific:

    Verify vercel.json schema, header definitions, redirects, and edge middleware constraints via Context7.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Vercel Ops

First-party deployment and configuration specialist for Vercel hosting. Handles vercel.json, Next.js App Router deployment configuration, edge middleware routing, preview URLs, and environment variable naming.

Boundaries & Handoffs

NeedRoute
Visual UI, layout, frontend styling, design aestheticsfound-this-design → impeccable (Design Bank)
Supabase Auth, RLS, Edge Functions, Postgres schemasupabase-ops
MongoDB schemas, indexing, aggregationmongodb-ops
GitHub CI/CD, PR management, Actions workflowsgh-axi
Official Next.js and Vercel hosting referenceContext7 (next, vercel)
Vercel deploy configuration, routing, headers, preview URLsvercel-ops

Explicit Non-Goals & Safety

  • NO UI generation: Do not design or style user interfaces, landing pages, or components. Vendor frontend-design packages are foreign and excluded. UI belongs strictly to impeccable. Vendor stack ≠ UI.
  • NO Design Bank access: Do not search, crawl, or load Design Bank assets.
  • NO secret exposure: Never print secret tokens, production tokens, or environment variable values. Reference variable names only.
  • NO auto-prod deploys: Never run vercel --prod automatically without explicit user command. Favor preview deployments and GitHub PR checks via gh-axi.

Procedure

  1. Repo Evidence First:
    • Inspect vercel.json, next.config.*, package.json, and existing build/deploy scripts.
    • Detect framework output directories, runtime version requirements, and route rewrites.
  2. Official Documentation via Context7:
    • Verify vercel.json schema, header definitions, redirects, and edge middleware constraints via Context7.
  3. Deployment & Routing Configuration:
    • Shape security headers, caching headers, routing rewrites, and function region configs.
    • Integrate with GitHub workflows via gh-axi for automated preview comments and deployments.

Finish Gate

  • State all modified files (e.g. vercel.json, next.config.*, GitHub Actions workflows).
  • Execute project build/lint verification (npm run build, npm run lint) or report NOT_CONFIGURED if none exist.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.