agentleFS
emiljuchnikowskiemiljuchnikowski/ai-os-template/.claude/skills/brief/SKILL.md

brief

Skill0 starsChanged 3 months agoMITView on GitHub

Morning brief — calendar, tasks, deadlines, inbox + a suggested day plan. Use in the morning or on "what's today?" / "brief".

81 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use capture, strategy and 9 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.
  • toneron2Skill

    capture

    Capture thoughts to inbox with automatic classification

    Also in 6 projects that use this

  • EpistatesSkill

    strategy

    Plan weekly or monthly X content strategy. Use when the user wants to plan their content calendar, set growth goals, build a content pipeline, or think strategically about their X presence.

    Also in 4 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 5 projects that use this

  • JaimeGBASkill

    ingest

    Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base

    Also in 7 projects that use this

  • howellsSkill

    reconcile

    Audit a project against current plugin conventions and offer to update structure.

    Also in 3 projects that use this

  • HermeticOrmusSkill

    close

    End-of-session ritual. Captures session state, updates auto-memory, writes a session summary, then exits the session cleanly.

    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 74 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:

    Every piece of owner feedback ("don't plan X on Fridays", "this label means an external blocker") gets written into THIS file immediately — …

    line 24

“Common” is measured: kept by at least 6 in 10 of the 74 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

Brief — morning review + suggested plan

Read-only. The brief SUGGESTS a plan; the owner decides. If you later automate delivery (posting the brief somewhere on a schedule), record that write target as an explicit exception in CLAUDE.md Safety rules first.

Gather (in parallel; skip unavailable connections with a note)

  1. Day of week FIRST: run date '+%Y-%m-%d %A' — the day drives the rules (e.g. which topics apply Mon–Wed, what belongs to Friday). NEVER assume the day from memory or from a previous brief; a brief signed with the wrong weekday applies the wrong rules and no one notices.
  2. Calendar: today + tomorrow. Only the calendars that matter (list them here once connected); recurring series that are long dead are noise, not plan — don't report them.
  3. Tasks (task manager / project tool, once connected): assigned items — overdue and high-priority go to "Needs attention". Only REPORT state; don't reorder the owner's queue unless asked. Watch tool defaults that resurface archived/deleted items — filter them out explicitly.
  4. Context deadlines: dates from context/ (e.g. the 90-day priorities in north-star.md), open decisions from the latest handoff in archives/handoffs/ (no files = skip silently).
  5. Inbox: open items in context/inbox.md ("## Open") — candidates for the plan; an entry older than 3 days → escalate. READ-ONLY — checking items off belongs to supervised sessions.

Output format (concise)

  • Today: events with times (+ tomorrow in one sentence).
  • Needs attention: overdue/priority tasks, calendar collisions, data gaps, external blockers ("waiting on X" — the only action for those is a nudge).
  • Focus of the day: 1–3 items closest to the north star (context/north-star.md) — derived from the 90-day priorities and today's calendar, not from the task backlog.
  • Suggested plan: prioritized list (e.g. ABCDE: A = must today, B = should, C = could, D = delegate, E = eliminate), each item on its own line.

Evolution

Every piece of owner feedback ("don't plan X on Fridays", "this label means an external blocker") gets written into THIS file immediately — the brief learns or it decays.

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.