2K skills ・ Works with: OpenAI · sorted by popularity
Design autonomous coding agents with patterns inspired by Cline and OpenAI Codex. Explore tool calling interfaces, permission and approval systems, browser automation, and workflows where people review or guide the agent's actions.
Add Application Insights monitoring to browser apps to record page views, clicks, network requests, and errors. Also covers custom measurements and tracing generative AI operations across browser and backend code to investigate behavior and performance.
Search Apple Notes by meaning or exact text, discover related notes and unexpected connections, and synthesize ideas with citations. The skill guides local setup and tool selection, with on-device search and optional local or cloud language models for synthesis.
Design and implement LLM applications, AI agents, and RAG systems that retrieve documents to support answers. Cover model selection, search quality, testing, monitoring, safety measures, and cost controls for applications intended for production use.
Hand a scoped coding task to Aider while the coordinating agent reviews changes, runs project checks, and commits the result. Covers task briefs, execution tracking, and follow-up edits, but the executable helper is not bundled.
Helps design focused AI products built on APIs such as OpenAI and Anthropic. Covers product strategy, prompts, model selection, user experience, usage tracking, and cost management for tools aimed at solving specific customer problems.
Design scheduled AI workflows for document ingestion, batch processing, and model training using Prefect, Airflow, or Dagster. Compare orchestration tools and plan task dependencies, retries, caching, and monitoring through implementation fragments.
Plan structured adversarial tests for AI applications to assess safety bypasses, data leaks, and unauthorized tool use. Organize test prompts, record findings, and prioritize fixes using reporting guidance and an adaptable testing template.
Review GitHub Actions workflows that run AI agents, tracing how external input reaches prompts and tools. Produce findings with evidence, severity, impact, and remediation guidance through static analysis, which examines configuration without running attacks.
Review Git changes with the ocr command-line tool and a configured AI model. Get line-level findings grouped by severity for working changes, commits, or branch comparisons, with code fixes applied when explicitly requested.
Create reusable agent skills, install them from URLs or local files, and update existing packages. Guides the structure of SKILL.md, supporting scripts and templates, naming, and optional format checks so agents can follow clearly defined workflows.
Create images from text descriptions, edit existing pictures, or combine multiple images. The script selects an image service from configured API keys and saves results in the workspace, with options for size, quality, and aspect ratio.
Transfer known function and variable names from an older binary to a newer version. Compare disassembly and pseudocode with an LLM, produce structured mappings, and apply names and comments in IDA.
Choose embedding models, which represent text as numerical vectors, for meaning-based search and RAG applications. Compare options for code, prose, and multilingual content, and plan document splitting, preprocessing, caching, and dimension reduction to improve retrieval quality.
Build AI applications that answer questions using retrieved documents. Covers vector databases, text embeddings that represent meaning as numbers, search strategies, and result reranking to connect language models with external knowledge.
Summarize articles, YouTube videos, podcasts, and local files, or extract available text and transcripts. Choose the summary length to suit the task and use transcript extraction to inspect video content when available.
Investigate LLM application failures with Phoenix CLI by reviewing execution records, recording observations, and grouping mistakes into counted categories. Inspect datasets and experiments to identify which failure types deserve evaluation tests first.
Build, update, explain, or review Microsoft Agent Framework applications in .NET or Python. The skill guides agent and workflow design using current official documentation and supports migration from Semantic Kernel or AutoGen.
Build systems that use Pinecone to find documents for AI answers or retain agent memories across sessions. Guides index setup, data loading, meaning-based and keyword search, memory separation, and end-to-end checks.
Plan how to sell AI products to enterprises, from product messaging and variable pricing to failure accountability. Use practical frameworks to structure demos, address operational concerns, and identify buyers prepared to adopt AI agents.
Generate illustrations, icons, game textures, sprites, and mockups from written descriptions using OpenAI or Google Gemini. The skill selects an available provider, saves the resulting image, and reports its location.
Build applications with GitHub Copilot SDK using Python, TypeScript, Go, or .NET. Add custom tools, display responses as they arrive, preserve conversations across restarts, and connect external tools through MCP, a protocol for connecting agents to tools.
Add controls to AI agents that use APIs, databases, and files. Use Python patterns for tool permissions, approval requirements, call limits, suspicious input checks, audit logs, and trust scores that guide delegation between agents.
Manage the credentials Arize uses to call LLM providers such as OpenAI and Anthropic. Create, inspect, update, or delete connections, configure allowed models and authentication methods, and retrieve connection IDs for use in evaluations.