Rendered at 16:13:29 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
gbrindisi 2 days ago [-]
Shameless plug: in case someone finds this requiring too many tokens, we shared the recipe on how we built our own in house audit skill so that it can easily be replicated and tuned to different environments https://www.synthesia.io/post/automating-code-security-revie...
gyanchawdhary 2 days ago [-]
This is awesome. Thanks for sharing
prodigycorp 2 days ago [-]
Hi Cloudflare people, if you are reading this. Please clean up your Cloudflare. Skills. There are way too many skills for the platform. You should consolidate all of your skills into a single skill and route everything thru that skill. The way it is right now pollutes our context window.
14 skills with short descriptions doesn't seem like an issue to me.
riffic 2 days ago [-]
a skill issue.
prodigycorp 2 days ago [-]
The descriptions are shorter now, but they used to read like ads. The skill split still feels arbitrary. You turn on what you think you need, then hit some Cloudflare task that needs another skill and have to go fetch it.
I don’t get why these need to be separate. One skill with progressive disclosure already handles this. That’s kind of the point.
mooktakim 2 days ago [-]
I really don't understand why they didn't create an "app store" style skills library where it could be approved and scanned for security issues
m00dy 2 days ago [-]
I'm sure they read here.
kentonv 2 days ago [-]
We actually do.
I forwarded this to the right person, and it sounds like it's being worked on. Thanks!
prodigycorp 1 days ago [-]
I complain because I like using CF. Thank you.
tomrod 2 days ago [-]
Once again, proving my growing trust in Cloudflare is well placed. Thanks!
Tip for security professionals using LLMs: audit skills that explicitly frame the task as security research sometimes trigger refusals from the top OpenAI and Anthropic models because they guard against misuse. What works for me: separate skills for bug classes (and bugs in general) without the security framing, plus another skill that combines their findings to spot security bugs.
viraptor 2 days ago [-]
If you're a security professional, go through their validation. You won't get the security refusals anymore. Well... you'll still get the occasional downgrade from Fable, but not the "oh no, I can't do exploits for you" breaks.
xur17 2 days ago [-]
Except their validation doesn't seem to work. I've gone through both (both personally and for my company), and.. no response for weeks.
viraptor 1 days ago [-]
Weird. I have minimal publicly visible record of security work and got the approval almost immediately.
acedTrex 2 days ago [-]
Incredible, a post and repo dedicated to a markdown file, the downfall of this field has been swift.
vntok 2 days ago [-]
Did you open the repo? There's a subdirectory with two dozens of files, around 300Kb of text.
Storing/visualizing small text changes over time as revisions is exactly what Git is excellent at, how else would you keep track of updates to the prompts?
acedTrex 2 days ago [-]
> how else would you keep track of updates to the prompts
I dont? because prompts are not a thing that are ever needed to be tracked lol.
decidu0us9034 2 days ago [-]
but they're very huge markdown files. look how much junk they're polluting the conext window with.
drchaim 2 days ago [-]
I threw 1M tokens for nothing in a medium codebase.
SkyPuncher 2 days ago [-]
These work best on a targeted section of the code, like a PR.
TZubiri 2 days ago [-]
how much is medium codebase, like 50kloc including docs?
drchaim 2 days ago [-]
in this case medium is relative to the projects I've worked. Bad expression anyway.
throwup238 2 days ago [-]
500kloc plus at least ten million lines of gastown logs.
For a todo cli. That doesn’t work.
this_user 2 days ago [-]
Welcome to agentic coding in 2026.
TrustScoreAgent 2 days ago [-]
[dead]
hyperionultra 2 days ago [-]
Uf, how much tokens?
jesse_dot_id 2 days ago [-]
At least 150k on my relatively small FastAPI project, but hit my session limit. Continuing in a few hours.
chrisweekly 2 days ago [-]
Oof. YAGNI. 150k tokens is where you start hitting the "dumb zone" (model attention issues and inconsistent adherence to instructions).
qsbuilder 2 days ago [-]
Dumping 14 full schemas into the prompt is just lazy design. You burn tokens, spike latency for no reason
tonymet 2 days ago [-]
What’s the difference between a skill and a prompt? Separate files? Aren’t tokens, tokens?
fassssst 2 days ago [-]
Skills can have scripts packaged with them
9el 2 days ago [-]
Any clues why "an OS-enforced sandbox" is in requirements?
nicce 2 days ago [-]
Probably to save their skin if agent starts to do some unexpected things and bringing havoc. But I doubt that OpenAI models with normal subscription, for example, wont even work with this skill.
donk8r 2 days ago [-]
Runs target builds, tests, fuzzers. No sandbox: workflow won't execute them. Lead stays needs_validation.
https://github.com/cloudflare/skills/tree/main/skills
I don’t get why these need to be separate. One skill with progressive disclosure already handles this. That’s kind of the point.
I forwarded this to the right person, and it sounds like it's being worked on. Thanks!
Storing/visualizing small text changes over time as revisions is exactly what Git is excellent at, how else would you keep track of updates to the prompts?
I dont? because prompts are not a thing that are ever needed to be tracked lol.
For a todo cli. That doesn’t work.