agentleFS
Sign inStart free
Fanar-labsFanar-labs/just-continue/skills/catch-up/SKILL.md

catch-up

Skill0 starsChanged 13 days agoMITView on GitHub

Pick up a project where it was left, so the user can just continue without re-explaining it. Reads CLAUDE.md, STATE.md and DECISIONS.md, says in a sentence or two what the project is, where it stopped and what comes next, and offers to sort any parked thoughts in INBOX.md. Use at the start of a session or after a break — when the user names a project to go on with ("let's continue the recipe site", "back to the newsletter", "let's work on X"), or asks "where were we?", "catch me up", "what's next on this project?".

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use in-your-own-words, bro and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • drafaelSkill

    in-your-own-words

    Restate the user's goals and the problem they are trying to solve to check understanding. Manual invocation only; use when the user explicitly invokes in-your-own-words or requests this understanding check. Do not solve the task or rewrite the assistant's last answer.

    Also in 3 projects that use this

  • MicrosoftSkill

    bro

    Re-explain the previous assistant message in a much simpler way, for when the reply made you go 'bro what'. Use /bro to get a simpler version of the last answer in Plain Language + Chicago Manual of Style, with diagrams where they help.

    Also in 3 projects that use this

  • MicrosoftSkill

    blast-radius

    Assesses network dependency and shared-infrastructure exposure. Use when the user asks which services, customers, SLA policies, routes, or redundant links are affected by a network fault.

    Also in 3 projects that use this

  • termdockSkill

    recall

    Retrieves cross-session memories about past decisions, lessons, and patterns. Use when user asks about prior work, past decisions, or mentions a feature. Triggers include check memory, what did we decide, how did we solve.

    Also in 3 projects that use this

  • photon-groveSkill

    unslop

    Detects and rewrites generic, overly polished, or AI-sounding prose while preserving meaning. Use when the user asks to "unslop", humanize, de-AI, tighten, or review whether writing sounds generated.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 20 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    No STATE.md anywhere → this project hasn't been started with these files yet.

    line 23
  2. Distinctive:

    If the user already said what to do in this session, don't ask — start on it.

    line 42
  3. Distinctive:

    Never delete a thought. Leave INBOX.md with its header and its line, empty below.

    line 55

“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “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

You are opening a session so that the user doesn't have to re-explain anything. Read only what this needs.

0. Check there is a folder that stays

The project's memory lives in its folder. If you are in a plain chat with no project folder — files written here won't be there in the next conversation — say so in one line and suggest opening the project's folder in Cowork or Claude Code.

1. Find the project

  • The user named the project, and the current folder or a folder inside it matches — by the folder's name or by "What it is" in its CLAUDE.md → that is the project. Go there without asking.
  • The current folder has STATE.md → that is the project.
  • It doesn't, but folders inside it do, and none matches what the user said → list those projects by when their STATE.md last changed, newest first (at most five), and ask which one. Then work in that folder.
  • No STATE.md anywhere → this project hasn't been started with these files yet. Offer new-project; don't invent the files.

2. Read

CLAUDE.md → STATE.md → DECISIONS.md. In DECISIONS.md the latest entries are enough, unless the next step depends on an older one. If INBOX.md exists, count the thoughts below its line.

3. Report

Like a colleague after a break: straight to the point, no welcome.

  • the project in one line, from "What it is" in the charter — so the user sees at once which project this is;
  • where we stopped, in one or two sentences;
  • the next step, as STATE.md states it;
  • the parked thoughts, if there are any: up to five — list them, one short line each; more than five — give the count and the newest three. Then: "Sort them now?"

If the user already said what to do in this session, don't ask — start on it. Otherwise ask: "Continue with <the next step>?"

4. Sort the parked thoughts — only on the user's yes

Take each line in turn and say where it goes:

  • a settled fact or a decision → STATE.md or DECISIONS.md;
  • knowledge that keeps coming back → an extra file (propose it, create it on yes);
  • something to do later → the next steps in STATE.md;
  • nothing worth keeping → nowhere, it is only archived.

Move every sorted line to INBOX-archive.md — append it with today's date and where it went. Never delete a thought. Leave INBOX.md with its header and its line, empty below.

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