agentleFS
lukashouthoofdlukashouthoofd/cenekathon/.agents/skills/team-sync/SKILL.md

team-sync

Skill1 starsChanged 14 days agoMITView on GitHub

Use when 2+ humans or AI agents work in parallel — file ownership, branching, avoiding merge conflicts, and patterns for collaborating with AI tools as a group.

The file

We split this skill into the rules it gives an agent

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

  • 1

    Very specific

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

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

    Contract first: Before splitting front/back, agree the interface (route, JSON shape, function signature) in docs/STACK.md or a shared types …

    line 9
  2. Distinctive:

    Sync beat: every 45 min, 3 minutes: done / doing / blocked.

    line 14
  3. Distinctive:

    Done when: no two people share an unplanned file and main still runs after every merge.

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Team sync (parallel humans + agents)

  1. Ownership map in docs/TEAM.md: person → folders/files → current task. One owner per file. Shared files (dependency manifest, lockfile, router index, docs/PLAN.md) → announce before editing.
  2. Contract first. Before splitting front/back, agree the interface (route, JSON shape, function signature) in docs/STACK.md or a shared types file. Then both sides mock against it.
  3. Branches: <initials>/<task>; start from fresh main; open a PR within 30–45 min; squash-merge. Pull main before every task and every ~30 min.
  4. Conflict rule: whoever merges second resolves. Never force-push main. Never git add -A blindly — stage your own files.
  5. Agent hygiene: one agent session per branch/worktree (git worktree add ../wt-<task> -b <branch>). Give each agent: the task, the files it may touch, the verification command. Tell it to stop and report rather than refactor neighbours.
  6. Shared context lives in files, not chat: decisions → DECISIONS.md, status → issue comments. Agents re-read files; they forget conversations.
  7. Sync beat: every 45 min, 3 minutes: done / doing / blocked. Update the cut line.
  8. Review: skim for secrets, mocks presented as real, and anything that breaks main. Approve fast.

Done when: no two people share an unplanned file and main still runs after every merge.

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.