Corrects outdated LLM knowledge about the Vercel platform and introduces new products. Injected at session start.
- Costo de contexto al activarse
- 1.8k tok
- Tamaño del paquete
- 1 archivo
- Última actualización
- hace 14 días
Release vercel-plugin — run gates, bump version, generate artifacts, commit, and push. Use when asked to "release", "ship", "bump and push", or "cut a release".
en todo el repo
0–100, la ruta de este skill
último commit aquí
últimos 90 días
41 tok en reposo
2 KB
Funciona con cualquier agente que lea SKILL.md
npx -y skills add vercel/vercel-plugin --skill release --agent claude-codeSe instala solo en este repositorio.
End-to-end release workflow for vercel-plugin.
Run all gates in parallel:
bun run typecheck # tsc --noEmit on hooks/src
bun test # all test files
bun run validate # skill frontmatter + manifest integrity
Stop if any gate fails. Fix issues before proceeding.
Read the current version from .plugin/plugin.json. Ask the user which semver component to bump if not specified:
| Bump | When |
|---|---|
| patch | Bug fixes, test/fixture updates, docs |
| minor | New skills, new hooks, new features |
| major | Breaking changes to hook API or skill map |
Default to patch if the user says "release" without specifying.
Update the version field in .plugin/plugin.json. This is the only version source of truth.
bun run build # hooks (tsup) + manifest
This compiles hooks/src/*.mts → hooks/*.mjs and regenerates generated/skill-manifest.json.
git add -A
git commit -m "<summary>; bump to <new-version>"
git push
Commit message style: match existing convention — descriptive summary followed by ; bump to X.Y.Z (see git log for examples).
The pre-commit hook will re-run typecheck and recompile hooks automatically. If it fails, fix the issue and create a new commit (never amend).
.plugin/plugin.json — the version field. There is no package.json version to sync.
.plugin/plugin.json version bumpedbun run build succeededReproducido de vercel/vercel-plugin bajo licencia NOASSERTION. Leer esta página en markdown.
1 archivo en el paquete. Solo se lee SKILL.md al activarse — las referencias se cargan si el skill decide que las necesita.
Necesita en el PATH:bungit
Este repo incluye 43 skills. Si instalas uno, normalmente ya tienes los demás.
Corrects outdated LLM knowledge about the Vercel platform and introduces new products. Injected at session start.
Vercel Connect expert guidance — securely obtain scoped OAuth tokens for third-party services (Slack, GitHub, MCP servers, OAuth, Snowflake) on behalf of apps or users via Vercel OIDC. Use when wiring up third-party API access, connecting to MCP servers, sending Slack messages, accessing GitHub APIs, receiving webhook events from Slack/Linear/GitHub and forwarding them to your agents and apps, or building eve agent connections.
Debug Vercel CDN caching — cache hit rate, stale content, revalidation behavior, ISR + PPR, per-request cache reasons (cacheReason) and PPR state (ppr_state), and costs.
Vercel Functions expert guidance — Serverless Functions, Edge Functions, Fluid Compute, streaming, Cron Jobs, and runtime configuration. Use when configuring, debugging, or optimizing server-side code running on Vercel.
Backend architecture guidance. Use when planning, building, or migrating an API or backend; choosing between Functions, Services, containers, Workflow, Queues, and Marketplace databases; or selecting a supported backend framework or runtime.
eve framework guidance for durable AI agents and agent-powered applications. Use when creating, editing, or debugging an eve project, when the user explicitly asks for eve, or when the build-agents skill has selected eve as the default framework. Covers eve's filesystem-first runtime, durable sessions, tools, skills, connections, channels, sandboxes, subagents, schedules, evals, frontend clients, and Agent Runs observability. Do not use for incidental agent mentions, generic agent-building prompts, or established non-eve stacks unless the user asks for comparison or migration.
Access and test Vercel deployments protected by Vercel Authentication, SSO, or Deployment Protection. Use when curl, agent-browser, Playwright, or another automated request reaches a Vercel login or protection page; when a protected preview or production URL returns 401 or 403; when TRUSTED_SOURCES_ENVIRONMENT_MISMATCH appears; or when choosing between `vercel curl` and the `x-vercel-trusted-oidc-idp-token` header.
Vercel AI Gateway expert guidance. Use when configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified API.
Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.