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.Interactive, source-grounded learning for the Agentic PM Lab. Lessons, quizzes, failure scenarios, and a cross-topic assessment. Say 'agentexpert' to start.
Summarize the current git diff against main into a horizontally sliced task with acceptance criteria. Creates the task through gh and links it as a sub-issue of a parent Feature in SmoothAiStockAnalysis.
Supports applying best practices in agricultural insurance.
Test AI agent systems for tool abuse, unauthorized actions, privilege escalation through tool chaining, and safety bypass via agentic workflows. Use this skill when assessing autonomous AI agents that use tool-calling (function calling, plugins, actions) to interact with external systems. Covers multi-step attack chains, implicit trust exploitation, and capability boundary testing for AI agents.
Provides production-grade AI agent patterns with MCP integration and agentic RAG. Covers handoff orchestration, multilayer guardrails, and observability.
Guides the architecture and implementation of autonomous AI agents. Covers tool use, function calling, memory systems, planning strategies, and multi-agent orchestration.
Start and run a listen-first braindump session for tickets, issues, ADRs, worktasks, PR descriptions, requirements, designs, or implementation plans. Use when the user says they want to braindump, think out loud, capture rough requirements, or provide context incrementally before asking the agent to synthesize, update a ticket, create docs, or perform implementation work.
Read Simon's latest AI Champions weekly task from
Exploit AI assistants equipped with web-browsing capabilities or internal API plugins to perform Server-Side Request Forgery (SSRF). This skill details injecting prompts that force the LLM to request sensitive internal endpoints, such as underlying cloud metadata services or internal networks.
Execute and analyze AI Data Poisoning attacks. By subtly injecting malicious or targeted misinformation into an LLM's training or fine-tuning dataset, an attacker can covertly manipulate the model's future outputs, implant backdoors, or enforce biases without altering the model architecture.
Identify and simulate Data Poisoning attacks aimed at degrading or skewing an AI model's accuracy. This skill focuses on Adversarial Machine Learning concepts where attackers inject malicious or mislabelled data points into training or fine-tuning datasets (e.g., feedback loops) to bias the AI.
AI governance, EU AI Act compliance, OWASP LLM security, responsible AI practices for GitHub Copilot agents
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