vercel-optimize
OfficialUse for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro app…
What it does
- Metrics first. Recommendations start from Vercel production signals, not repo-wide grep.
- Deterministic gates. scripts/gate-investigations.mjs decides what deserves investigation.
- Candidate-bound scope. Read only files named by a candidate or a route-local import chain.
- Version-aware citations. Use only references/docs-library.json; invalid or version-mismatched citations are stripped.
- Customer copy. Read references/voice.md before writing report text or chat output.
- Vercel CLI v53+ with vercel metrics, vercel usage, vercel contract, and vercel api.
- Authenticated CLI session: vercel login.
Requirements & configuration
- Never put auth tokens in shell commands. Do not type VERCELTOKEN=..., --token ..., or Authorization: Bearer ... into commands that may be echoed in chat.
- node -e 'JSON.parse(require("fs").readFileSync(process.argv[1], "utf8"))' "$RUNDIR/vercel-signals.json"
- Traffic-independent examples: middleware matcher, source maps, React Compiler config, build settings. Route-local cache or data-fetch patterns need route-level traffic evidence.
Configuration: VERCEL_PROJECT_IDVERCEL_TOKENRUN_DIRVERCEL_ORG_IDPROJECT_SCOPE_UNRESOLVEDSCOPE_UNRESOLVEDPROJECT_SCOPE_MISMATCHCOLD
Derived from the skill's own SKILL.md documentation · extracted 2026-07-23
Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps. Collect Vercel metrics, usage, project config, and code scan results first; investigate only metric-backed candidates; produce ranked recommendations grounded in verified files and version-aware Vercel/framework docs. Trigger for Vercel bill reduction, slow or expensive routes, caching opportunities, Function Invocations, Build Minutes, Fast Data Transfer, Core Web Vitals, Bot Management, Fluid compute, or cost breakdown requests.
Source
Repository: https://github.com/vercel-labs/agent-skills
vercel-optimize FAQ
What does the vercel-optimize skill do?
Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps. Collect Vercel metrics, usage, project config, and code scan results first; investigate only metric-backed candidates; produce ranked recommendations grounded in verified files and version-aware Vercel/framework docs. Trigger for Vercel bill reduction, slow or expensive routes, caching opportunities, Function Invocations, Build Minutes, Fast Data Transfer, Core Web Vitals, Bot Management, Fluid compute, or cost breakdown requests. Metrics first. Recommendations start from Vercel production signals, not repo-wide grep. Deterministic gates. scripts/gate-investigations.mjs decides what deserves investigation.
What does vercel-optimize require?
Never put auth tokens in shell commands. Do not type VERCELTOKEN=..., --token ..., or Authorization: Bearer ... into commands that may be echoed in chat. node -e 'JSON.parse(require("fs").readFileSync(process.argv[1], "utf8"))' "$RUNDIR/vercel-signals.json" Traffic-independent examples: middleware matcher, source maps, React Compiler config, build settings. Route-local cache or data-fetch patterns need route-level traffic evidence. Configuration keys: VERCEL_PROJECT_ID, VERCEL_TOKEN, RUN_DIR, VERCEL_ORG_ID, PROJECT_SCOPE_UNRESOLVED, SCOPE_UNRESOLVED, PROJECT_SCOPE_MISMATCH, COLD.
How do I install vercel-optimize?
Run: npx -y skills add https://github.com/vercel-labs/agent-skills --skill vercel-optimize --agent claude-code — the source lives at github.com/vercel-labs/agent-skills.
Maintain vercel-optimize?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/skills/vercel-labs-agent-skills-vercel-optimize?ref=badge) npx agentictools info skills/vercel-labs-agent-skills-vercel-optimize The second line is the CLI lookup for this page — handy in READMEs and docs.