All skills
openai avatar

/cloudflare-deploy

@bf9e226 official
by openaiopenai/skills28k stars
1,891

Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.

Use this Skill: https://skilld.dev/gh/openai/skills/cloudflare-deploy

This session only. Nothing lands on disk.

referencesvectorizegotchas.md

≈540 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Vectorize Gotchas

Critical Warnings

Async Mutations

Insert/upsert/delete return immediately but vectors aren't queryable for 5-10 seconds.

Batch Size Limit

Workers API: 500 vectors max per call (undocumented, silently truncates)

// ✅ Chunk into 500
for (let i = 0; i < vectors.length; i += 500) {
  await env.VECTORIZE.upsert(vectors.slice(i, i + 500));
}

Metadata Truncation

returnMetadata: "indexed" returns only first 64 bytes of strings. Use "all" for complete metadata (but max topK drops to 20).

topK Limits

returnMetadata returnValues Max topK
"none" / "indexed" false 100
"all" any 20
any true 20

Metadata Indexes First

Create BEFORE inserting - existing vectors not retroactively indexed.

# ✅ Create index FIRST
wrangler vectorize create-metadata-index my-index --property-name=category --type=string
wrangler vectorize insert my-index --file=data.ndjson

Index Config Immutable

Cannot change dimensions/metric after creation. Must create new index and migrate.

Limits (V2)

Resource Limit
Vectors per index 10,000,000
Max dimensions 1536
Batch upsert (Workers) 500
Indexed string metadata 64 bytes
Metadata indexes 10
Namespaces 50,000 (paid) / 1,000 (free)

Common Mistakes

  1. Wrong embedding shape: Extract result.data[0] from Workers AI
  2. Metadata index after data: Re-upsert all vectors
  3. Insert vs upsert: insert ignores duplicates, upsert overwrites
  4. Not batching: Individual inserts ~1K/min, batched ~200K+/min

Troubleshooting

No results?

  • Wait 5-10s after insert
  • Check namespace spelling (case-sensitive)
  • Verify metadata index exists
  • Check dimension mismatch

Metadata filter not working?

  • Index must exist before data insert
  • Strings >64 bytes truncated
  • Use dot notation for nested: "product.category"

Model Dimensions

  • @cf/baai/bge-small-en-v1.5: 384
  • @cf/baai/bge-base-en-v1.5: 768
  • @cf/baai/bge-large-en-v1.5: 1024

Source: SKILL.md on GitHub

2 warnings17d5 checks · Risk SAFE
  • Gen Agent Trust Hub17d

    This skill provides comprehensive guidance for deploying and managing infrastructure on the Cloudflare platform. It includes extensive educational material on secure development practices, such as preventing SQL injection and managing secrets effectively. No malicious patterns or security risks were identified.

  • Socket17d

    2 alerts: gptAnomaly

  • Snyk17d

    Risk: LOW · No issues

  • Runlayer7mo

    310/310 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at bf9e226. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 months ago.

Activeupdated 8 months ago

README badge

README badge for openai/skills/cloudflare-deploy

Deploys applications and infrastructure to Cloudflare's platform, including Workers, Pages, D1, R2, Durable Objects, KV, and other services. Use decision trees to route to the right Cloudflare product based on compute, storage, AI, networking, security, or media needs.

Generated from the current SKILL.md.

Does this skill cover all Cloudflare products?
The skill is a consolidated index covering compute, storage, AI, networking, security, media, and developer tools on Cloudflare. It uses decision trees to route you to the right product reference, then loads detailed guidance for that product.
What authentication is required before deploying?
Run `npx wrangler whoami` to check if authenticated. For local deployment, use `wrangler login` (one-time OAuth). For CI/CD, set the `CLOUDFLARE_API_TOKEN` environment variable.
What should I do if deployment fails due to network issues?
Rerun the deploy with `sandbox_permissions=require_escalated` to grant elevated network access, which is required for outbound requests to Cloudflare during deployment.
How long does a Cloudflare deployment typically take?
Deployments may take several minutes. Use appropriate timeout values in your configuration or CI/CD environment.

Generated from the current SKILL.md. These answers refresh after source changes.