Blog
What we are learning while building the directory, plus notes on new AI assets worth your time.
Opus 5.5, GPT-6 Sol, and GPT-6 Luna just got cheaper. The effort setting decides if you notice
Anthropic and OpenAI both cut prices this week. Both companies also published a chart, right next to the discount, that shows effort setting moves your cost far more than either price cut does.
How to Create a Custom AI Skill (Most Guides Skip This Part)
Most SKILL.md files are formatted correctly and still never fire once. The format was never the problem. Three specific habits are, and no checklist about frontmatter fields will catch them.
We open-sourced the full catalog as an awesome-list on GitHub
Every entry from this directory is now also a plain-markdown awesome-list on GitHub, so you can browse it, fork it, or send a PR without leaving GitHub.
Prompt engineering examples: why quality prompting matters more with AI agents
A bad prompt to a chatbot in 2023 meant you asked again. A bad prompt to an agent in 2026 means it already edited the wrong file. Five before-and-after examples show exactly where the gap opens up.
SEO skills for AI agents in 2026, the ones worth actually installing
SEO for agents means two different things now: agents that do the SEO work, and getting found by the agents doing the searching. Both jobs are skills you install, not a checklist someone reads once a month.
GPT-6 Astra vs Claude Fable 5.1: who actually wins?
Astra wins the benchmark table and the price sheet. Fable 5.1 wins the question that matters more once an agent is running unsupervised: does it stay on task.
Claude Fable 5.1 ranked: Opus, Sonnet, and Haiku, and what each one is for
Anthropic only gave a codename to the flagship. That's the tell: reach for Fable 5.1 when a task earns it, and use the plain-named tiers under it for everything else.
Chinese AI labs changed one rule, and it's the one that matters
DeepSeek gets the headlines, but Qwen, GLM, Kimi and MiniMax made the same bet. Open weights aren't charity. They're the strongest move available to a lab that isn't first.
Is a DeepSeek harness the future of coding agents?
DeepSeek didn't just ship a cheap, open model. It made it normal to build your own agent loop instead of renting someone else's. That shift matters more than the model itself.
GPT-6 Astra: what actually changed, past the launch page
OpenAI's new flagship claims record scores everywhere at once. Strip out the marketing and three things hold up: it's cheaper per task, it handles much longer context, and it says no to itself more often.
Is Grok really more powerful than other AIs? Wrong question
xAI keeps claiming the top spot on benchmarks. Maybe it's true this week. It still isn't the question that decides whether Grok is useful to you.
Most agentic AI failures aren't model failures
When an agent goes off the rails, the instinct is to blame the model. Most of the time the real problem is that nobody gave it a skill or a way to reach the right tool.
Why we built a curated directory, not another crawler
Other directories count assets by the hundred thousand. We would rather tell you the license is clean and the install command actually runs, even if that means a shorter list.