agentleFS
iwe-orgiwe-org/marketing-workspace/.claude/skills/weekly/SKILL.md

weekly

Skill6 starsChanged 3 days agoMITView on GitHub

Compose a weekly campaign digest from the workspace — what shipped, engagement numbers, pipeline and outreach state, and ranked next-week priorities. Prints the digest; saves it under data/weekly/ only when the user asks to keep it. Use when the user asks for a "weekly digest", "weekly report", or a start-of-week review.

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use capture, inbox and 2 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 4 projects that use this

  • 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:

    Keep it executable — 5 items max.

    line 37

“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 digest

A composer, not a fetcher: roll up what the graph already knows. Best run right after the update skill has refreshed engagement.

Steps

  1. Window. Trailing 7 days (or the range the user asks for). The activity sources are the frontmatter dates (published, completed, created, reviewed, generated.at) and the dated groups in data/log.md. In a git repository git log --since=<date> --name-status -- data adds what changed; without git, the first two are enough.
  2. Shipped. Posts with published in the window; tasks flipped to done (completed in window); plan steps whose stage changed; venues newly worked (planned → active).
  3. Engagement. Current engagement.* for posts published in the last ~14 days, with notable movers called out, and the week's replies counted by outcome (and by names_product). Posts whose verdict was set this week, against their success line. If numbers look stale, suggest running the update skill first.
  4. Pipeline & outreach. Drafts in flight (stage: draft), scheduled posts and emails, people with stage: contacted and sent emails with outcome: none awaiting reply (with days-waiting), replies due their three-day review (no outcome), leads at new or researched with fit: high, mentions filed in the window, experiments running (and any that should have concluded by now or hit their stop_signal), and competitors with watch: true whose updated is more than a month old.
  5. Next week. Ranked shortlist: high-priority planned tasks, the active plan's unmet Definition-of-done items, and any follow-ups implied by 2–4 (a reply to chase, a mention author to contact, an open reading whose deciding evidence is now on file). Each item names the fact it rests on. Keep it executable — 5 items max.
  6. Print the digest with those four sections (Shipped, Engagement, Pipeline and outreach, Next week). If the user asks to keep it, also write data/weekly/YYYY-MM-DD.md (type: weekly-report, window_start, window_end, created, a description, and the sections ## Shipped, ## Engagement, ## Pipeline and outreach, ## Next week) and inclusion-link it at the top of data/weekly.md. A kept report is the only write the digest makes, and it gets its line in data/log.md like any new document (AGENTS.md, step 5). The week's state changes were logged when they happened; do not log them again.

Rules

  • Numbers come from frontmatter, not memory. If a section is empty, say so in one line — an honest "no outreach in flight" beats padding.
  • End with the single most leveraged thing to do next week, stated in one sentence.

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.