Explore

Find agent skills by outcome

115,787 skills indexed with the new KISS metadata standard.

Showing 24 of 115,787Categories: Research & Learning, Openclaw, General, Coding & Debugging

General

PromptBeginner5 minmarkdown

Detects jailbreaks

role-play escapes

Apr 15, 2026

General

PromptBeginner5 minmarkdown

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.

Find agent skills by outcome

Detects jailbreaks

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

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

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

description: Protect AI chat and completion endpoints from abuse — detect prompt injection and jailbreak attempts

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

Best practices — legend-first

Add AI protection

Visual symbol table — per ELV system (CCTV

pdfcount

$analysis_of_ai_characteristics (Identify areas that sound robotic

mc

The result should look like a refined typographic portrait where shadows are created purely through text density

- Focus density on eyes

Arrange text with slight variations in rotation and spacing

minimal

- No lines

- The image must be composed ONLY of text (e.g.

​Player Goal: [e.g.

​Inputs: > - Genre: [e.g.

6. Have you avoided filler

2. Have you covered product

Before producing the final answer

5. Have you provided sufficiently specific frontend

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

Player Goal: [e.g.

Inputs: > - Genre: [e.g.