agentleFS
Sign inStart free
DeepusleepyDeepusleepy/t3-tots/skills/t3-project-tracker/SKILL.md

t3-project-tracker

Skill110 starsChanged 17 days agoMITView on GitHub

Living tracker for one project or launch (goal, milestones, todo, decisions, next steps). Use for "help me launch <project>", "track <project>", "update the <project> tracker", "what's next for <project>", "how close is <project> to done".

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Follow the t3-tots-rules skill (skills/t3-tots-rules/SKILL.md).

    line 8
  2. Very specific:

    Read the README, docs, plans and TODOs, git log --oneline -30, git status -s, tags and releases, and the project's T3 threads (node …

    line 14
  3. Distinctive:

    If nothing states the goal and the date, ask for them.

    line 15
  4. Distinctive:

    Read git and the threads since the last Log entry.

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Follow the t3-tots-rules skill (skills/t3-tots-rules/SKILL.md). Write only the tracker file, never project files.

The tracker is <tools folder>/trackers/<project>.md on the computer where the project lives. It has these sections: Goal, Milestones (checkbox and target date), Todo (now, next, later), Decisions (dated), Open questions, Risks, Links, and Log (dated one-liners).

Create

  1. Find the project with t3ctl projects or <projects folder>/<name> from memory. Find related folders with mdfind on macOS, Get-ChildItem on Windows or find on Linux.
  2. Read the README, docs, plans and TODOs, git log --oneline -30, git status -s, tags and releases, and the project's T3 threads (node export.js --project '<P>' --days 30 --out out/<P>-tracker.json).
  3. If nothing states the goal and the date, ask for them.
  4. Show the goal and the top 5 next steps. Write the file after the user confirms.

Update

Read git and the threads since the last Log entry. Tick milestones, add decisions (including "we decided X" from chat) and open questions, and add a Log line. Tell the user what changed and the next 3 steps.

Suggest

Suggest next steps from the gap between the goal and the current state. For a release, check signing, notarizing, the installer, a landing page, the README, the changelog and a demo post. Add bugs from threads and open questions. Offer to start one with t3-new-thread, t3-pm-thread or t3-handoff.

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.

Check your setup, free