agentleFS
Sign inStart free
aaroncohnaaroncohn/openspec-conductor-powerups/skills/keep-going/SKILL.md

keep-going

Skill1 starsChanged 10 days agoMITView on GitHub

Pick up babysitter where `/babysitter:pause` left off, catching up on what happened and telling the held sessions to carry on. Run it in the Babysitter HQ workspace; anywhere else it changes nothing and says so.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. aewing/skills★ 1same name
    2. CUTEPKQ/radiance-skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Read <this skill's dir>/../hq/SKILL.md (and cloud.md beside it if CONDUCTOR_IS_LOCAL is 0), then state.py show and …

    line 10
  2. Distinctive:

    Start the watcher (step 4), then send each released session, plus any other you held:

    line 12

≈ “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

keep-going

  1. Run python3 <this skill's dir>/../hq/state.py resume from this workspace's root. If it errors, this isn't Babysitter HQ: pass on what it said, change nothing, and stop. If it says not paused, say so and stop. Otherwise it lists the sessions to release, one per line: name, then session.
  2. Read <this skill's dir>/../hq/SKILL.md (and cloud.md beside it if CONDUCTOR_IS_LOCAL is 0), then state.py show and .context/babysitter-notes.md. This may be a new or compacted session, and those rules apply again from here.
  3. Catch up on the pause: update this workspace to the latest main, do the full re-scan from hq's step 4 (all open workspaces, read from their newest messages) into state.py sync-scan, check each held session's PR, and read the queues for answers that came back. Handle those answers (hq step 9), rename what changed stage, and take over every workspace on the ADOPT NOW line and decide each on the CHECK NOW line (step 4).

  4. Start the watcher (step 4), then send each released session, plus any other you held:

    Via Babysitter: resumed. Carry on from where you stopped, with the same rules as before; merging to main is approved, still one at a time: wait for Via Babysitter: your turn to merge.

    Add the answer if it's waiting on one. Tell the merge lock's holder (state.py merge show) it still has its turn; everyone else in line keeps waiting, and the next go comes from the merge lock (hq step 4). A session the user took further by hand during the pause carries on from there. Skip --now.

  5. Set the goal again (hq step 0).
  6. Post a full digest from state.py digest (step 6), opening with "Resumed; paused for about <how long>." and saying which estimates moved because of the pause. Then state.py digest-posted.

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