The AI tools directory that stays current

The reference collection: document, spreadsheet, and slide skills from the team that defined the format.

Official skill for generating art as code — procedural patterns instead of image prompts.

Official skill for extracting, splitting, merging, and filling PDFs from an agent.

Monthly cost from tokens per request, requests per month, and price per million tokens.

How many tokens a prompt uses, and how much of an 8K–1M window it fills.

The difference between a chatbot, a tool, and an agent — and why the distinction decides what you can delegate.

The config file, the three values that actually matter, and how to know it worked.

A folder with a SKILL.md the agent loads on demand — closer to a training manual than a plugin.

A code tool can be checked by reading the repository. A video model cannot — so media verification leans on dated observation, and says…

WordPress MCP plus a skill library makes an agent a competent publishing assistant. The rule that keeps it safe is simple: drafts, not publishes.…

Meeting recorder that turns calls into structured notes and follow-ups.

Search and drafting inside the wiki you already use.

Meeting notes that write themselves while you talk.

OpenAI's video model: text or image in, short clip out, with storyboard control.

Google DeepMind's video model, available through Gemini and Vertex AI.

Kuaishou's video generator, tuned for motion and image-to-video.

Anthropic's terminal agent: reads the repo, edits files, runs the tests it just broke.

Terminal pair programmer that commits every change it makes to git.

A fast native editor with an agent panel and multiplayer editing built in.

Open-source library that lets an agent drive a real browser through the DOM.

Self-hostable platform for building LLM apps without a backend team.

The self-hostable automation tool for people who can read code.

SEO-oriented writing and research workspace with article and audit workflows.

Writing assistant built for fiction: drafts, rewrites, and story-level continuity.

GTM workflow tool that grew from copy generation into a sales-and-marketing automation layer.

The default general-purpose assistant, now with agents and deep research.

Long-context writing and code work with a strong editing instinct.

Google's assistant, wired into Search, Workspace, and Android.

Black Forest Labs' image models, including open weights you can run yourself.

Adobe's generative image tools, trained on licensed content and wired into Creative Cloud.

A design-first image model: vectors, brand styles, and editable SVG output.

Enterprise search and an assistant that answers from your company's own documents.

An answer engine that cites what it used.

A search assistant that lets you pick the model behind the answer.