agentsclimarketplace
Sign in

Whats up

Skill autographical/claude-code-plugins/plugins/autographical/skills/whats-up

Fetch recent activity from Autographical — what the user and their AI agents have been working on. Use when starting a session, when the user mentions recent activity, when the user alludes to what they were doing or looking at, or picking up where they left off. Also use when the conversation feels like a topic change or you could use more background context on the ask.From its SKILL.md

Install
npx -y skills add autographical/claude-code-plugins --skill whats-up

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.6 KB, 262 tokens by cl100k_base, as published. Nobody here has run it

What's Up

Fetch recent activity from Autographical and present what's been happening. The activity stream includes everything the user has been doing — browsing, reading, saving, researching — as well as activity from AI sessions the user has been collaborating with. It's the full picture of human + AI work.

Data

  1. Call the recent_activity MCP tool to fetch recent sessions and top resources.

  2. If the user provided arguments via $ARGUMENTS, also call the search MCP tool with those arguments to narrow focus.

  3. If a session or resource looks particularly relevant, use get_session or get_resource to get more detail.

Synthesis

Lead with what you find interesting or notable. You have full latitude in how you read and present the data — don't follow a rigid template. Some things to surface:

  • Active threads and topics — what has the user been engaged with, and what have their AI collaborators been working on?
  • Momentum — where is attention concentrated? What's in-progress?
  • Recency and intensity — what's hot right now vs background threads?

Keep it concise. A few sentences per thread, not an exhaustive list of URLs. The goal is to transfer context to you so the session can build from shared awareness.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,758. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.