agentleFS
pqmcgillpqmcgill/family/.claude/skills/setup/SKILL.md

setup

Skill0 starsChanged 5 months agoMITView on GitHub

Use when the family wants to establish or amend their domain charter — first-time founding setup, "redo our domains", "amend the charter", or onboarding a fresh household database.

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-atomic-chat-tool, add-dashboard and 10 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.
  • MicrosoftSkill

    add-atomic-chat-tool

    Add Atomic Chat MCP server so the container agent can call local models served by the Atomic Chat desktop app via its OpenAI-compatible API.

    Also in 8 projects that use this

  • MicrosoftSkill

    add-dashboard

    Add a monitoring dashboard to NanoClaw. Installs @nanoco/nanoclaw-dashboard and a pusher that sends periodic JSON snapshots.

    Also in 8 projects that use this

  • +10 more from microsoft

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 169 edited versions we read keep these.

  • 1

    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. Distinctive:

    One topic at a time: Never present a wall of questions.

    line 22
  2. Very specific:

    Read state first: ./bin/fam backup, ./bin/fam person list, ./bin/fam standing list, ./bin/fam --source weekly horizon, read ritual.md.

    line 34

“Common” is measured: kept by at least 6 in 10 of the 169 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

Founding Setup / Charter Amendment

A collaborative session where the adults define (or amend) the domain layer: what areas of life this system manages, what machinery each domain runs on, and what neglect means in each. The goal is setting the stage, NEVER locking anything in — the charter is amendable by re-running this skill anytime.

Same hard rules as the nightly check-in skill: read the "Hard rules" and "Red flags" sections of .claude/skills/checkin/SKILL.md FIRST and apply all of them identically (CLI only; read before you think; full batch then confirm then write; never guess facts; aliases only; every write carries --source weekly).

Conversation discipline (setup-specific)

  • One topic at a time. Never present a wall of questions. This is a conversation between partners that you facilitate — ask, listen, reflect back, move on.
  • Propose, don't impose. You may offer the classic domains (house, to-dos/calendar, personal time, togetherness) as a starting point, clearly labeled as a starting point. Their domains are whatever they say they are.
  • Both voices. This session is for BOTH adults. If only one is present, ask which decisions should wait for the other.

Flow

  1. Read state first: ./bin/fam backup, ./bin/fam person list, ./bin/fam standing list, ./bin/fam --source weekly horizon, read ritual.md.
    • Empty system → founding session (full flow below).
    • Existing system → amendment: present the current charter from ritual.md section by section and ask what's changed. Apply the same flow only to the parts being amended.
  2. Domains — "What are the areas of life we want this system to help carry?" Capture each domain and, in one phrase, why it matters to them.
  3. People — register everyone (aliases + roles + nickname patterns), and record who-is-who as relationships in a "People" section of ritual.md ("P1 — dad", "Grammy — P2's mother"). Real names never enter the system anywhere — aliases by construction.
  4. Machinery per domain — for each domain, what are the moving parts? Recurring chores (with groupings), fixed commitments (day/time, pausable for seasons), backlog one-offs, anything tracked as to-dos. Write as standing items / todos as agreed.
  5. Neglect definitions — for each domain: "how long is too long?"
    • Chore cadences → fam chore cadence <name> <days> (note: a chore enters chore memory after its first completion; declared cadences for not-yet-done chores go in the charter and get set at first completion).
    • Personal/together drought thresholds → these are code constants; record the agreed numbers in the charter and flag any that differ from current code as build-items.
  6. Long-term priorities — "What do we keep meaning to protect or fix?" Each becomes an observation (fam obs add) so it resurfaces at every session.
  7. Ritual shape — when do weeklies happen, what must every check-in cover, any house habits (e.g. nightly reset)?
  8. Write the charter — update ritual.md with structured sections: ## Our domains, ## What neglect means, ## Scheduling context, ## Preferences we've settled on. Show the full diff before applying.
  9. Verification replay — all WROTE echoes against what was agreed; confirm; fix with fam undo if wrong. Close by reminding them the charter amends by re-running /setup.

Red flags (setup-specific, additional to checkin's)

  • Asking more than ~2 related questions in one message
  • Writing standing items for a domain before the couple has agreed the domain exists
  • Treating your proposed defaults as decisions
  • Finishing without the charter written to ritual.md

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.