agentleFS
DeepusleepyDeepusleepy/t3-tots/skills/t3-digest/SKILL.md

t3-digest

Skill110 starsChanged 18 days agoMITView on GitHub

Daily or weekly digest across all the user's projects (T3 threads, git, TODOs, trackers) with suggestions. Use for "daily digest", "weekly digest", "what did I do this week", "where do my projects stand", "what happened today", or the Daily digest and Weekly wrap-up routines.

The file

Files
SKILL.md

Follow the t3-tots-rules skill (skills/t3-tots-rules/SKILL.md). Steps that use the box, ListMachines, routines, cards or SendToUser are Grok Bot only; other agents follow t3-tots-rules "Grok Bot only". Read-only. Leave out usage and cost figures; those belong to t3-usage, on request only.

1. Collect from every connected computer

  • T3: node survey.js for activity and stale threads, and node export.js --project all --days <1|7> --out out/digest.json, then CopyToBox the export. t3q.py waiting lists what needs the user.
  • Active project folders are the T3 projects active in the window, plus folders under the user's projects folder that changed in it. The projects folder comes from memory; ask once if it's unknown. For each one, collect:
    • git -C <root> log --since=<window> --oneline | head -20
    • git -C <root> status -s | wc -l and the current branch
    • the first 40 lines of TODO*, ROADMAP*, plans/ and state.md
  • Goals: <tools folder>/trackers/*.md (t3-project-tracker).

2. Write

For each project, cover what happened, where it stands, what's next (from trackers, TODOs and the last agent messages), and 1 or 2 concrete suggestions, such as "1 uncommitted file" or "idle 5 days: settle or continue?". Then list what's waiting on the user and what's running now. Add stale threads only in the weekly digest, and only if the user turned on the stale-thread list.

  • Daily: 15 lines or fewer in chat.
  • Weekly: the same, plus an HTML page at /workspace/t3-out/digest-<date>.html in the t3-project-report style, sent with SendToUser.

3. Routines

The Daily digest and Weekly wrap-up routines run this skill (t3-getting-started section 6). In a routine run, skip quiet projects, and send nothing if nothing happened and nothing is waiting.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.