AgentSkillify

Explore

Find agent skills by outcome

139,155 skills indexed with the new KISS metadata standard.

Showing 24 of 139,155Categories: Data & Insights, General, Communication, Data, Coding & Debugging, Creative
Data
PromptBeginner5 minmarkdownQuality: 28

- Sensitive info detection runs **locally in WASM** — no user data is sent to external services. It is only available in route handlers

not in Next.js pages or server actions.

0
Creative
PromptBeginner5 minmarkdownQuality: 28

**Streaming responses**: Call `protect()` before starting the stream. If denied

return the error before opening the stream — don't start streaming and then abort.

0
General
PromptBeginner5 minmarkdownQuality: 28

**Multiple models / providers**: Use the same Arcjet instance regardless of which AI provider you use. Arcjet operates at the HTTP layer

independent of the model provider.

0
Data
PromptBeginner5 minmarkdownQuality: 28

If the user wants a full security review

suggest the `/arcjet:security-analyst` agent which can investigate traffic

0
General
PromptBeginner5 minmarkdownQuality: 24

- `list-requests` — confirm decisions are being recorded

filter by conclusion to see blocks

0
Creative
PromptBeginner5 minmarkdownQuality: 24

Start all rules in `DRY_RUN` mode first. Once verified

promote to `LIVE`.

0
General
PromptBeginner5 minmarkdownQuality: 24

Adapt the response format to your framework (e.g.

`res.status(429).json(...)` for Express).

0
General
PromptBeginner5 minmarkdownQuality: 24

console.warn(Arcjet error:

decision.reason.message);

0
General
PromptBeginner5 minmarkdownQuality: 24

return Response.json({ error: Forbidden }

{ status: 403 });

0
General
PromptBeginner5 minmarkdownQuality: 24

detectPromptInjectionMessage: userMessage

// injection detection

0
General
PromptBeginner5 minmarkdownQuality: 24

requested: 1

// tokens to deduct for rate limiting

0
General
PromptBeginner5 minmarkdownQuality: 24

const decision = await aj.protect(req

{

0
General
PromptBeginner5 minmarkdownQuality: 24

sensitiveInfoValue: userMessage

// PII scanning

0
Coding & Debugging
PromptBeginner5 minmarkdownQuality: 28

Always include `shield()` (WAF) and `detectBot()` as base layers. Bots scraping AI endpoints are a common abuse vector. For endpoints accessed via browsers (e.g. chat interfaces)

consider adding Arcjet advanced signals for client-side bot detection that catches sophisticated headless browsers. See https://docs.arcjet.com/bot-protection/advanced-signals for setup.

0
General
PromptBeginner5 minmarkdownQuality: 32

Pass the `requested` parameter at `protect()` time to deduct tokens proportional to model cost. For example

deduct 1 token per message

0
General
PromptBeginner5 minmarkdownQuality: 24

Set `characteristics` to track per-user: `[userId]` if authenticated

defaults to IP-based.

0
General
PromptBeginner5 minmarkdownQuality: 28

Use `tokenBucket()` / `token_bucket()` for AI endpoints — the `requested` parameter can be set proportional to actual model token usage

directly linking rate limiting to cost. It also allows short bursts while enforcing an average rate

0
Communication
PromptBeginner5 minmarkdownQuality: 24

- JS: `sensitiveInfo({ deny: [EMAIL

CREDIT_CARD_NUMBER

0
Coding & Debugging
PromptBeginner5 minmarkdownQuality: 28

- Python: `detect_sensitive_info(deny=[SensitiveInfoType.EMAIL

SensitiveInfoType.CREDIT_CARD_NUMBER

0
General
PromptBeginner5 minmarkdownQuality: 28

Arcjet rules run **before** the request reaches your AI model — blocking prompt injection

PII leakage

0
General
PromptBeginner5 minmarkdownQuality: 24

Detects jailbreaks

role-play escapes

0
General
PromptBeginner5 minmarkdownQuality: 28

Check for an existing shared Arcjet client (see `/arcjet:protect-route` for full setup). If none exists

set one up first with `shield()` as the base rule. The user will need to register for an Arcjet account at https://app.arcjet.com then use the `ARCJET_KEY` in their environment variables.

0
General
PromptBeginner5 minmarkdownQuality: 28

Read https://docs.arcjet.com/llms.txt for comprehensive SDK documentation covering all frameworks

rule types

0
General
PromptBeginner5 minmarkdownQuality: 24

Secure AI/LLM endpoints with layered protection: prompt injection detection

PII blocking

0