Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Exploit an application's absolute trust in its underlying LLM (Overreliance). Use this skill to induce critical "hallucinations" (confident falsehoods) that cause downstream logical systems or automated agents tracking the LLM's output to make destructive actions or grant unauthorized access.
Supports Pulse Radar knowledge extraction with Pydantic-AI agents. Includes RAG and embeddings.
Provides a playbook for testing direct prompt injection and indirect injection through RAG or browsing. Covers tool abuse, data exfiltration, MCP security risks, and defense bypass techniques.
Exploit AI applications using Indirect Prompt Injection. This skill focuses on hiding malicious instructions within data sources (web pages, documents, emails) that the LLM processes, causing the AI to execute unintended actions or leak data without direct user interaction.
Addresses security for chatbots, AI agents, RAG pipelines, tool-using LLMs, and applications calling LLM APIs. Covers vulnerabilities such as prompt injection using guidance based on the OWASP Top 10 for LLM 2025.
Identify and exploit vulnerabilities in the AI Supply Chain by injecting malicious models, datasets, or dependencies. Use this skill to simulate advanced persistent threats (APTs) compromising Hugging Face repositories, manipulating pre-trained weights (Model Poisoning), and exploiting insecure deserialization during model loading (e.g., Pickle files).
Comprehensive LLM security testing prompts for bias detection, data leakage, alignment testing, and adversarial prompt resistance.
Extract sensitive training data (PII, API keys, intellectual property, or code) directly from a deployed Large Language Model (LLM). This AI Red Teaming skill focuses on forcing models to regurgitate memorized, unredacted data from their massive internet-scraped datasets through repetition attacks, prefix continuation, and context window manipulation.
Explains the knowledge distillation pattern behind an AI-powered Obsidian wiki. Guides setup and organization using a three-layer architecture of raw sources, wiki pages, and schema.
Supports creating and querying an interlinked Markdown knowledge base. Uses Karpathy's LLM Wiki approach.
LLMFit is a terminal tool that detects a system's hardware. It recommends LLM models expected to run well on that system.
Orchestrates external agent reviews of code changes with Codex and Gemini. Processes results as they arrive and uses critical verification and debate to filter suggestions.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name