A real boost on standard / older models (+25); today's top models already have this built in.
Today's top models
This tier already does it — no lift to add · e.g. Claude 4 · GPT-4-class · DeepSeek-V3
100% without → 100% with · measured on deepseek-chat (4×3)
Standard / older models
Clearly better with it (+25 pts) · e.g. MiniMax-Text-01 · smaller open models
75% without → 100% with · measured on MiniMax-Text-01 (4×3)
How: we install the skill into a real model, run the same tasks with it vs without, and compare — labeled with the exact model + sample size above.
What it claims to do
Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct synt…
What we found · 7
Description doesn’t say WHEN to use itmediumA good description names the trigger (e.g. "when reviewing a PR"). Without it the skill mis-fires or never fires.
Bloated: high token costmedium~4,589 tokens on every single call. Compress instructions and trim examples.
References API keys / env configmediumReads an API key or env var — normal for API clients. Ensure keys come from the runtime (not hardcoded); a leak risk only if sent to an untrusted endpoint.
Embedded shell script blockmediumShips runnable command-line scripts. Not necessarily bad, but must be sandboxed and reviewed.
Contains curl / wget network commandmediumAccesses the network from the shell. If the target is untrusted it can pull malware or exfiltrate data.
Reads credentials and makes network calls — verify the destinationmediumThe normal shape of an API client (your key → the API). Static analysis sees the capability, not the intent — confirm the endpoint is one you trust; it is a data-leak risk only if it is not.
Repeated contentlow~7 duplicate lines detected; de-duping is free token savings.
What its scripts can do
high
Reads secrets
medium
Installs packages
medium
Network egress
Conflicts with · 7
cloudflare-email-service
shadow
cloudflare, worker
verification-before-completion
shadow
runn, command
turnstile-spin
overlap
cloudflare, deploy, manag, worker, load
agents-sdk
overlap
cloudflare, worker, load, workflow
workers-best-practices
overlap
cloudflare, worker, load, wrangler
cloudflare
overlap
cloudflare, worker, vectorize
sandbox-sdk
overlap
load, command
If you have both installed, they compete for the same triggers — the top cause of an agent picking the wrong skill.
Have you installed wrangler? Scan everything you run.
One command grades every skill in your Claude Code / Codex — safety, token bloat, and conflicts, 100% locally.
Does this rating match your experience with wrangler?
Anonymous & aggregate. We watch these as a trend and re-check flagged skills — a single click never moves a grade on its own.
Independent static analysis by SkillMOO — the Consumer Reports for agent skills. Safety, token, and conflict grades are computed, not opinions. Efficacy is only ever claimed when measured. We rate & link to the source; we do not rehost skill content.