In hooks/skill-map.json: add tailwind.config.*, postcss.config.*, tsconfig.json, and tsconfig.*.json to the nextjs pathPatterns. Add bun/yarn install patterns for @ai-sdk/gateway to ai-gateway bashPatterns. Add bun/yarn install patterns for @vercel/functions to runtime-cache bashPatterns. Add bun/yarn install patterns for @vercel/speed-insights to observability bashPatterns.
In hooks/pretooluse-skill-inject.mjs: refactor the hook script for clarity and robustness.
In tests/pretooluse-skill-inject.test.ts: expand test coverage for the new trigger patterns and refactored hook logic.
Create skills/ai-elements/SKILL.md covering the AI Elements component library — 40+ React components for AI chat UIs (Message, Conversation, Tool, Reasoning, CodeBlock, PromptInput) built as a custom shadcn/ui registry. Document installation via `npx ai-elements`, integration with AI SDK v6 useChat/UIMessage parts, server-side patterns (convertToModelMessages async + toUIMessageStreamResponse), and the DefaultChatTransport client pattern.
Create skills/shadcn/SKILL.md covering shadcn/ui — CLI commands (init, add, build, search, migrate), components.json configuration, namespaced custom registries (@v0, @acme), CSS variable theming with oklch, dark mode setup, the cn() utility, TooltipProvider requirement, RTL support, and framework compatibility (Next.js, Vite, Remix, Astro, Laravel).
Create skills/json-render/SKILL.md covering AI chat response rendering — the UIMessage parts format (text, tool-*, reasoning, step-start), manual rendering patterns for custom chat UIs without AI Elements, ToolResultCard patterns for structured tool output display instead of raw JSON, and the 5 most common v6 rendering mistakes (raw JSON from message.content, tool JSON blobs, convertToModelMessages not awaited, toDataStreamResponse vs toUIMessageStreamResponse, v5 useChat API pattern).
In skills/ai-gateway/SKILL.md, add a full "Authentication (OIDC — Default)" section documenting: VERCEL_OIDC_TOKEN provisioned by `vercel env pull`, @vercel/oidc reading the token automatically, ~24h expiry with re-pull for local dev, auto-refresh on Vercel deployments, AI_GATEWAY_API_KEY as manual alternative, and the auth priority order (API key first, then OIDC fallback).
In skills/ai-sdk/SKILL.md, update the setup section to document OIDC as default auth flow (vercel link → enable gateway → vercel env pull → OIDC token auto-provisioned), rewrite the UI Hooks section with both AI Elements (recommended) and manual rendering patterns showing v6 API changes (DefaultChatTransport, sendMessage, status, message.parts), update Key Patterns to include OIDC, AI Elements, and server-side v6 patterns, and expand the migration section with useChat transport, sendMessage, toUIMessageStreamResponse, and message.parts entries.
In vercel.md ecosystem graph: add AI Elements product entry under AI SDK UI Layer with component list and shadcn dependency, add shadcn/ui product entry under Frameworks with CLI commands and registry system, add OIDC Authentication subsection under AI Gateway with token flow, add AI Elements and custom rendering rows to AI Features decision matrix, update "Build an AI Chatbot" workflow with OIDC steps and AI Elements, add 6 new migration table entries (useChat transport, sendMessage, toUIMessageStreamResponse, message.parts, manual API keys → OIDC), and update AI SDK v6 conventions with OIDC-first auth, AI Elements recommendation, and server/client v6 patterns.
In hooks/skill-map.json, add trigger entries for all 3 new skills: ai-elements (components/ai-elements/**, npx ai-elements, shadcn registry URL patterns), shadcn (components.json, components/ui/**, npx shadcn patterns), json-render (components/chat**, components/message*, chat sidebar patterns).
Run the validator (bun run scripts/validate.ts --coverage skip) to confirm all 8 checks pass with 24 skills, 0 orphans, and all skill-map entries valid.
Addresses a gap where the plugin allowed agents to use direct provider
SDKs (@ai-sdk/anthropic, @ai-sdk/openai) with manual API keys instead
of routing through Vercel AI Gateway, which provides auto-provisioned
credentials, failover, cost tracking, and observability.
Changes:
- PreToolUse hook: add 3 new checks (10-12) for AI Gateway preference,
deprecated generateObject/streamObject, and provider API key env vars
- vercel.md: update AI Features decision matrix to make AI Gateway the
default row, add AI project bootstrap workflow, update Conventions to
lead with gateway-first and vercel-link-first guidance
- ai-sdk SKILL.md: rewrite Installation, add Setup for AI Projects
section, update all code examples to use gateway() instead of direct
provider imports, update Key Patterns to prioritize gateway
The ecosystem graph now lives at vercel.md (root). Remove the redundant
assets/ directory and update all references in the validator, tests, and
README.
generateObject and streamObject are deprecated in AI SDK v6. Replace all
usage and documentation with generateText/streamText + Output.object().
Also:
- Expand migration tables with CoreMessage, Experimental_Agent deprecations
- Simplify validator to check metadata only (components discovered from dirs)
- Add date to vercel.md header
These fields are for path overrides per the open-plugin spec, not
inventory lists. Components are discovered from the filesystem
automatically. Removing them fixes Claude Code validation errors.
Rules (.mdc files) aren't supported by Claude Code's plugin system — they
were silently ignored. Move the ecosystem knowledge graph and all three
convention sets (Next.js 16, AI SDK v6, Vercel platform) into CLAUDE.md
so they're always loaded into context.
Also updates repo references from anthropics/open-plugin to
vercel-labs/vercel-plugin.
Add bun test suite with validate.test.ts, coverage-baseline.ts for
llms.txt gap analysis, orphan-skill detection in validate.ts, structured
JSON output with --format json, and per-check timing metrics.
Add Microfrontends & Multi-App Composition to turborepo skill, OG
Image Generation to nextjs skill, and cache management + MCP server
integration to vercel-cli skill.
Add routing-middleware, runtime-cache, vercel-sandbox, vercel-queues,
vercel-flags, sign-in-with-vercel, and vercel-agent skills to close
coverage gaps identified by llms.txt baseline analysis.
Add verified canonical GitHub repository URLs to the Official Documentation
sections for observability (@vercel/analytics, @vercel/speed-insights),
v0-dev (v0-sdk), and vercel-storage skills.
Added canonical GitHub repository links as the final bullets in the Official Documentation sections for vercel-api, vercel-cli, and vercel-functions.
Each link was added only after validating repository availability.
Verified: node docs section check for expected last bullets (pass)
Verified: curl status checks for vercel/sdk=200, vercel/vercel=200, vercel/firewall=404 (pass)
Swarm-Agent: codex-github-platform
Add canonical GitHub repository URLs to the Official Documentation
sections for Next.js, Turbopack, and Turborepo skills.
Verified: bash scoped check confirms each GitHub link is the final
Official Documentation bullet in the three changed SKILL.md files.
Verified: curl -s -o /dev/null -w '%{http_code}' on each repository URL
returns an allowed status (200).
Swarm-Agent: codex-github-framework
These skill references included 404s and redirected paths that no longer
resolve to canonical docs. This update applies the exact URL mapping
requested across the assigned eight SKILL.md files.
Verified: scoped URL verification via rg patterns (old URLs absent, new URLs present)
Verified: set -euo pipefail; ! rg old-patterns ...; rg required-new-patterns ... (pass)
Swarm-Agent: codex-broken-urls
The skill documented @neondatabase/vercel-postgres-compat, which is not a valid npm package.\nRemoved the install command and migration snippet that imported it while keeping\nall @neondatabase/serverless guidance intact.\n\nVerified: node -e "const fs=require('fs');const vs=fs.readFileSync('skills/vercel-storage/SKILL.md','utf8');const checks=[['compat package removed',!/@neondatabase\/vercel-postgres-compat/.test(vs)],['serverless install present',/npm install @neondatabase\/serverless/.test(vs)],['serverless imports remain',/from '@neondatabase\/serverless'/.test(vs)]];const bad=checks.filter(([,ok])=>!ok);if(bad.length){process.exit(1);}"\nVerified: git diff --check -- skills/vercel-storage/SKILL.md\n\nSwarm-Agent: codex-npm-and-workflow
The workflow skill referenced @workflow/postgres, which is not a real npm package.\nIt now uses @workflow/world-postgres and includes an explicit install command.\nThe AI SDK docs link was also updated from sdk.vercel.ai to ai-sdk.dev.\n\nVerified: node -e "const fs=require('fs');const wf=fs.readFileSync('skills/workflow/SKILL.md','utf8');const checks=[['world-postgres install present',/npm install @workflow\/world-postgres/.test(wf)],['world-postgres import present',/from '@workflow\/world-postgres'/.test(wf)],['old package removed',!/@workflow\/postgres/.test(wf)],['sdk.vercel.ai removed',!/sdk\.vercel\.ai/.test(wf)],['ai-sdk.dev present',/https:\\/\\/ai-sdk\.dev\//.test(wf)]];const bad=checks.filter(([,ok])=>!ok);if(bad.length){process.exit(1);}"\nVerified: git diff --check -- skills/workflow/SKILL.md\n\nSwarm-Agent: codex-npm-and-workflow
John Lindquist