Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
496 skills found
Architect production-grade LLM applications using LangChain 1.x and LangGraph. Implement stateful AI agents, multi-step workflows, and custom memory systems for complex conversational and automation tasks.
Detects indirect prompt injection and goal hijacking in AI agents by evaluating how they process external content like RAG, documents, and web data.
Build AI agents with tool calling and multi-step reasoning. Generate, manage, and orchestrate custom skill files for Claude Code, Cursor, Cline, and other AI assistants to standardize your development workflows.
Cascading goal tracking system connecting 3-year vision to daily tasks. Automates progress calculation, stalled goal detection, and project-to-goal alignment for Obsidian vaults.
P9 Tech Lead mode: Manages P8 agent teams via Task Prompts (six-element) without direct coding. Orchestrates 3+ parallel agents for project management, task decomposition, and architecture.
A color-coded, real-time context usage progress bar for the Claude Code statusline and manual on-demand checks.
Intelligent pattern selection for Fabric CLI, automatically choosing from 242+ specialized prompts for threat modeling, data analysis, summarization, and content creation.
Search, analyze, and audit GeminiClaw session logs and memory. Use to investigate past interactions, track token usage, debug tool calls, and monitor agent performance.
Multi-perspective AI consultation for technical architecture, complex refactoring, and structured debugging.
Enforce high-quality Java 17+ coding standards, Spring Boot conventions, and maintainable project structures.
Architect multi-agent systems to overcome context limits, using patterns like supervisor, swarm, and hierarchical models to manage complex workflows.
Automate the creation and maintenance of Rsbuild E2E tests, ensuring feature coverage and regression prevention through Playwright.