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

weekly

Skill0 starsChanged 5 months agoMITView on GitHub

Use when the user starts a weekly review or planning session, says "weekly", "plan the week", or wants the full sweep — every open item, neglect, fairness, trends — before building next week's plan.

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use inbox, decide and 1 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.
  • lamb92009Skill

    inbox

    Use when the user runs /inbox or asks to process the inbox folder in the RDL vault. Reads unprocessed files, routes content to correct vault locations, creates or updates notes with wikilinks, and deletes processed originals.

    Also in 3 projects that use this

  • dirienSkill

    decide

    Three-agent adversarial debate protocol for strategic decisions. Two advocates steelman opposing positions while a moderator identifies risks and synthesizes a binding consensus. Use when choosing between alternatives, evaluating tradeoffs, or making high-stakes decisions.

    Also in 3 projects that use this

  • SentrySkill

    onboard

    Onboard a service to sentry-options. Use when integrating a new service, creating schemas, or setting up the multi-repo sentry-options workflow.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 17 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run, before interpreting any user input:

    line 17

“Common” is measured: kept by at least 6 in 10 of the 17 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

Weekly Review & Planning

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; facts vs. inference; every write carries --source weekly or --source transcript). Differences are in scope and flow.

Flow

  1. Run, before interpreting any user input:
    • ./bin/fam backup
    • ./bin/fam check (event-log integrity — investigate any drift before writing anything new)
    • ./bin/fam --source weekly horizon (EVERY open item, however far out)
    • ./bin/fam --source weekly chore list
    • ./bin/fam --source weekly fair --weeks 4
    • read ritual.md
  2. Review phase — walk through, conversationally:
    • Last week's pending entries: fam week new REFUSES to draft while any earlier week has pending entries, so disposition each now — fam week done <id> (it happened) or fam week skip <id> (let it go, on the record). Items to carry forward: skip now, re-add to the new week in the planning phase (with --day, and --todo if it mirrors a todo).
    • Far-out dated items: anything that needs action to start now?
    • Parked todos: still parked, or revive (fam todo defer <id> --to <date>) or drop?
    • Unresolved calendar (date passed): done, or cancelled?
    • Neglect flags: name them plainly ("bedding is at 24 days, usually ~14").
    • Fairness: present the numbers; if lopsided, ask — never accuse.
    • Pulse trends: facts first, then any "I notice ..." inference (not saved unless asked).
    • Observations: do NOT revalidate the list — that's homework, not review. Raise one only if (a) this session's facts contradict it, or (b) it's the oldest and unconfirmed for 30+ days — at most 2 per session. Archive (fam obs archive <id>) only on agreement.
  3. Planning phase — only after review:
    • ./bin/fam --source weekly week new drafts the week from standing chores. Run it AFTER the user agrees planning is starting (it writes). CAUTION: week new defaults to the week CONTAINING today. On the Sunday planning day that's the week that's ending — pass --start <upcoming Monday> to draft the week ahead. Verify the "week of <date>" echo before continuing; undo + redo if wrong.
    • Adjust the draft through conversation: skip entries (fam week skip <id>), add one-offs (fam week add ... --kind oneoff). A one-off that mirrors an open todo gets --todo <id> (or fam week link <eid> <tid> after the fact) so marking the entry done resolves the todo too — never track the same work twice unlinked.
    • Plan personal time blocks for BOTH adults — ask each (fam week add "<block>" --kind personal --who <alias>).
    • Assign days: once the family agrees which day each entry lands on, set it — fam week day <id> <mon..sun> (validated; works on standing-drafted entries too). fam today and the checkin report compute TODAY'S TARGETS and BEHIND PLAN from this field; an entry left unassigned shows under NO DAY ASSIGNED so it can't hide. fam week note remains for free-text context ("before the trip").
    • Assign owners where the family knows who's doing what (--who on add) — the fairness report can only measure owned work.
    • Standing items themselves: add, pause, resume, or retire?
  4. Save the session journal (--session weekly --kind summary, plus any pasted transcript as --kind transcript). Also write a terse one-line day-plan (--session weekly --kind summary, prefix WEEKPLAN, kept under 200 chars) capturing each day's targets — laundry loads, room resets, key events. This is a human-readable summary; the entry notes set in step 3 are the structured copy. If the two would ever disagree, fix the notes — they win.
  5. Verification replay — same as nightly: list all WROTE echoes against what was agreed, confirm, fix with fam undo if wrong.

Order matters

Review BEFORE planning. The whole point of the weekly is that next week's plan is informed by the full horizon, neglect, and fairness facts — a plan made before the review silently repeats last week's blind spots.

Self-adjustment

Same mechanism as the checkin skill: ritual.md for preferences (no commit), this SKILL.md for behavior (commit after confirming diff).

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.