agentleFS
byun-alexbyun-alex/claude-session-continuity/skills/catchup-all/SKILL.md

catchup-all

Skill0 starsChanged 5 months agoMITView on GitHub

Cross-project briefing — orient the user across ALL their projects at once, newest activity first, in a warm assistant voice. Use when they say "catch me up on everything", "what was I doing across projects", "global catchup", "/catchup-all", "where did I leave off overall", or want a bird's-eye view spanning every project rather than just the one folder they're sitting in. Reads the single rollup timeline (_Overall.md) that /wrapup maintains in the central Session Diary and hands back a unified briefing + a suggested focus. Companion to /catchup (which is scoped to the current project only).

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    All session logs live in one central folder — Session Diary/ at the projects root — one file per project.

    line 17
  2. Very specific:

    Read $OVERALL. If it's missing or has no timeline lines yet, tell them warmly there's no cross-project history yet and that it fills in as …

    line 29
  3. Distinctive:

    Read the timeline, newest first.

    line 30
  4. Very specific:

    If an argument names a project, still give the full timeline but bias the Suggested for today toward that project (and you may open that …

    line 38
  5. Very specific:

    Read-only — reports and converses, never writes a log (that's /wrapup).

    line 40

≈ “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

/catchup-all — orient me across everything

The user works across many projects in different terminals and forgets the big picture. /catchup briefs them on the current project only; this one zooms out to all projects so they can see, in one place, what they've touched most recently and what's still hanging — then decide where to spend today.

Voice (this run only): speak as the user's personal AI assistant — warm, composed, smooth, lightly witty, professional first. Address them by name if you know it. Chat voice for the briefing only; it doesn't change how files are written.

Where the data lives (the rollup file)

All session logs live in one central folder — Session Diary/ at the projects root — one file per project. On top of those, /wrapup maintains a single rollup file that this skill reads:

ROOT="${CLAUDE_PROJECTS_ROOT:-$HOME/projects}"
DIARY="$ROOT/Session Diary"
OVERALL="$DIARY/_Overall.md"

_Overall.md holds one condensed line per session across every project, newest first, under a ## Timeline heading. You read only this file — do not scan the per-project logs.

What to do

  1. Read $OVERALL. If it's missing or has no timeline lines yet, tell them warmly there's no cross-project history yet and that it fills in as they run /wrapup — then stop. (You may ls "$DIARY" to mention which projects already have their own per-project logs.)
  2. Read the timeline, newest first. Note how long ago each line is so you can say "yesterday" / "Monday" / "three days ago".
  3. Brief them in warm, full sentences (not terse dots):
    • Greeting with today's date + weekday.
    • The timeline — walk the most recent lines, grouped sensibly (e.g. by day or by project), leading with the latest. One sentence each: which project, what got done / where it stands.
    • Hottest thread — the single most recent session is most likely where they were last; call out where that project stands and the natural next move. If you need a sharper detail, you may open that project's own <Project>.md for its logged "Next step" / "Open threads".
    • Suggested for today — 2–3 concrete options across projects, framed as a plan. Recommend one.
    • Any new ideas? — ask if they've had sparks since last time; feeds the journal at next /wrapup.
    • Close by asking which project they want to dive into.
  4. If an argument names a project, still give the full timeline but bias the Suggested for today toward that project (and you may open that project's <Project>.md for extra detail).

Read-only — reports and converses, never writes a log (that's /wrapup). Don't dump the whole file; synthesize the recent timeline into a fast orientation.

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.