2K skills ・ Works with: OpenAI · sorted by popularity
Review AI vendor contracts against your organization's policies. Identify gaps in data training rights, liability, model changes, and other terms, then prepare targeted contract edits and escalation options for issues outside agreed limits.
Build reusable Convex backend components with their own database tables and a small API, the functions an app calls. It guides component structure, app integration, authentication boundaries, and checks for generated code and type errors.
Turn a Bifrost PR or GitHub issue into API regression tests that catch recurring bugs. Review existing coverage, add cases to the Postman collection, and validate collection processing and provider filtering.
Investigate Bifrost GitHub issues by examining reports, related code, and library documentation. Produce an implementation plan with impact analysis and regression tests, including a demonstrated failing test for bugs before requesting approval to fix them.
Compare Bifrost HTTP API code with OpenAPI, its API specification, to find missing routes and mismatched methods, authentication, parameters, and responses. Get an audit report with code references and recommended fixes.
Run OpenClaw tests and reproduce bugs on remote machines through Crabbox. Choose a suitable execution provider, verify realistic user workflows, and report the actual provider, environment ID, logs, and timing.
Analyze webpage screenshots to extract colors, typography, and component styles. Generate structured JSON describing reusable design rules and an AI coding prompt, or convert the results into brand styling for a presentation video.
Extract still frames from videos at chosen intervals, then use an AI model that understands images to analyze scenes, people, and composition. Get structured descriptions and creative prompts for video planning and storyboard reference.
Review how an AI agent loads, retains, summarizes, and shares working information. This historical guide helps examine forgotten constraints, repeated actions, tool selection, and handoffs using context engineering practices published in 2024–2025.
Diagnose why an AI agent skips tools, passes incorrect arguments, or repeats calls. Get guidance on tool descriptions, schemas that define accepted inputs, execution flow, and mock tests before connecting to a real model.
Audits GitHub Actions workflows that run AI coding agents. Traces how attacker-controlled content reaches prompts, checks permissions and sandbox settings, and reports evidence, severity, and fixes for prompt injection and related configuration risks.
Choose a small validation experiment based on your hypothesis, risks, time, and resources. Compare five methods, from technical checks to user interaction tests, and define pass, fail, and learning criteria before investing in a larger build.
Add, extend, or review OpenAI Ads conversion tracking for purchases, signups, and other confirmed outcomes. The skill covers browser Pixel events, server-side Conversions API events, duplicate-event prevention, secret handling, and local verification with a setup report.
Turn an idea, existing code, or a previous Codex conversation into a runnable OpenAI Agents SDK app. Supports local verification, focused evaluations of agent behavior, and local deployment through the Deployment Manager.
Diagnose failed OpenAI API requests by separating network problems, authentication errors, exhausted credits, rate limits, and access restrictions. Use concrete error messages to explain the likely cause and direct users to the appropriate next action.
Build, refactor, and troubleshoot ChatGPT apps with an MCP server, which exposes tools to the assistant, and an interactive widget. Use official documentation and examples to plan tools, scaffold code, configure security settings, and validate local operation.
Set up NemoClaw, create an isolated sandbox for OpenClaw, and start the first agent conversation in a browser or terminal. Follow onboarding for model connections, optional search and messaging, and network policy settings.
Handles credentials before Codex builds or runs tools that use the OpenAI API. Checks for an existing key without revealing it, asks whether to reuse or create one, and saves credentials only to a confirmed local destination.
Add burned-in captions to a finished video using Whisper timings from its own audio. Choose paper, bold, or clean styling, and optionally use narration text to preserve intended spelling. Outputs include the captioned video and an SRT file.
Produce a finished faceless video with multiple scenes, a consistent illustrated style, and narrator voiceover. Supports explainers, history, stories, and children's content, assembling scenes and optional embedded subtitles into one video file.
Create server endpoints in Expo Router and deploy them with EAS Hosting. Use them to keep API keys off the client, validate incoming data, access databases, proxy external services, and receive webhook notifications.
Build isolated code execution environments on Cloudflare Workers for AI-generated code, scripts, and build pipelines. Covers running commands, managing files, preserving interpreter state, exposing service previews, and cleaning up sandbox resources.
Build and debug Python agents with Swarms, a framework for coordinating multiple AI agents. Covers tool connections, saved memory, autonomous execution, and workflow choices such as sequential steps, parallel work, specialist delegation, and combined answers.
Turn articles, reports, papers, notes, or outlines into a visually consistent PowerPoint deck. Each slide is a generated image, with an approval workflow for the outline, style, and sample, plus quality checks and speaker notes.