agentleFS
Sign inStart free
TheCraigHewittTheCraigHewitt/cowork-starter-pack/skills/weekly-report/SKILL.md

weekly-report

Skill5 starsChanged 6 months agoMITView on GitHub

Produces a weekly report summarizing what happened this week — completed work, what stalled, decisions made, next week's priorities. Pulls from calendar, messaging, and any work logs in the project folder. Use when the user asks for a weekly report, Friday recap, weekly review, or end-of-week summary. Best run as a scheduled task late Friday afternoon.

We split this skill into the rules it gives an agent

11 rules. 0 are common, 6 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 25 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

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

    Read context/about-me.md — who is this report for, what does the user own?

    line 12
  2. Very specific:

    Read context/preferences.md — what format does the user want?

    line 13
  3. Very specific:

    Read context/voice.md — for any narrative prose in the report.

    line 14
  4. Very specific:

    Check /output/ for last week's report — continuity matters.

    line 15
  5. Very specific:

    If the user specified an audience in preferences.md or about-me.md, tune the tone to that audience

    line 43
  6. Distinctive:

    Do not list every meeting.

    line 48
  7. Distinctive:

    Do not pad. If the week was quiet, the report is short.

    line 49
  8. Distinctive:

    Do not editorialize beyond what the evidence supports.

    line 50
  9. Distinctive:

    Do not skip the "stalled" section because it's uncomfortable.

    line 51
  10. Distinctive:

    For a team report: Add a fifth section: "Team highlights" — named callouts of who shipped what.

    line 81
  11. Distinctive:

    For a self-only report: Add a sixth section: "Energy & load" — one line on how the week *felt.* This is for future-you reading back in …

    line 82

“Common” is measured: kept by at least 6 in 10 of the 25 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 Report

Turn a week of meetings, messages, and scattered notes into a one-page recap the user can send to themselves, a manager, or a team — without spending 45 minutes writing it.

Before starting

  1. Read context/about-me.md — who is this report for, what does the user own?
  2. Read context/preferences.md — what format does the user want? Who is the audience?
  3. Read context/voice.md — for any narrative prose in the report.
  4. Check /output/ for last week's report — continuity matters. Did last week's priorities get done?

What to produce

A markdown file saved to /output/weekly-report-{YYYY-MM-DD}.md, covering Monday through today (or a 7-day window if today isn't Friday).

Four sections:

  1. What moved this week — 3–6 bullets. The wins, the meaningful progress, the decisions made. Specific. No vague "worked on X" — say what shipped, what got decided, what changed.
  2. What stalled or slipped — 1–4 bullets. Honest. Don't cover things up. If something was on last week's list and didn't happen, say so and say why.
  3. Decisions & notable changes — decisions taken this week that someone might want to know about later. One line each. (This section feeds a decision log over time.)
  4. Next week's focus — 3 priorities, ranked. Each with one sentence of why.

Inputs

  • Calendar from the last 7 days
  • Messages / Slack DMs from the last 7 days
  • Last week's weekly report (if exists) — for continuity
  • Any /output/ files created this week — these are the trail of work done
  • Any decision-journal entries in the project folder (if used)

How it works

  1. Pull the week's calendar — identify meetings that produced outputs (reviews, 1-1s, decisions)
  2. Pull message/Slack history — look for commitments made, decisions mentioned, items closed
  3. Scan /output/ for files created/modified this week — this is the actual work trail
  4. Compare to last week's "Next week's focus" — did those priorities move?
  5. Draft the four sections
  6. If the user specified an audience in preferences.md or about-me.md, tune the tone to that audience
  7. Save the file, tell the user one-line what was notable

What not to do

  • Do not list every meeting. Only meetings that produced something.
  • Do not pad. If the week was quiet, the report is short. A two-paragraph weekly report is better than a fake one-pager.
  • Do not editorialize beyond what the evidence supports. "Team morale is high" is not something you can know from the data.
  • Do not skip the "stalled" section because it's uncomfortable. That section is the whole point.

Example output structure

# Weekly Report — Week of 2026-04-14 to 2026-04-18

## What moved
- Shipped the Q2 planning doc; got sign-off from all three department heads
- Closed Northwind contract — signature on file, kickoff scheduled 4/28
- Hired new ops manager (starts 5/5) — offer accepted Wednesday
- Finished vendor migration to new payroll provider; first run clean

## What stalled
- Pricing review pushed to next week — blocked on finance model from Alex
- Board deck outline is still not started; needs 2 hours I haven't made

## Decisions & notable changes
- Decided to delay the Q3 hiring wave by one month (signal from April sales pipeline)
- Switched weekly reporting cadence from Monday to Friday (this report is the first)
- Approved the $18K spend on new analytics stack

## Next week's focus
1. Pricing review — unblock the finance model Monday morning. This is the #1 item on the quarterly plan.
2. Board deck — block 2 hours Tuesday. Draft is due Thursday.
3. Onboard new ops manager — calendar holds and 30/60/90 plan ready before 5/5.

Customization notes

  • For a team report. Add a fifth section: "Team highlights" — named callouts of who shipped what. Use sparingly; too many names and it reads like a bureaucratic formality.
  • For a self-only report. Add a sixth section: "Energy & load" — one line on how the week felt. This is for future-you reading back in three months.
  • For manager reports. Tighten "What stalled" to include what you're doing about it, not just what's stuck.

Download now (ZIP)

  • Other versions49 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 49

    1. genspark-ai/genoffice★ 11ksame name
    2. anthropics/cwc-workshops★ 2.2ksame name
    3. yunshu0909/yunshu_skillshub★ 760same name
    4. Azure/azure-dev★ 571same name
    5. claude-office-skills/skills★ 433same name
    6. CatCatUncle/openworkbuddy★ 375same name
    7. logly/mureo★ 61same name
    8. Itsokay-co/bio-vibing★ 17same name
    9. kudeerliu48-web/CloseCode★ 14same name
    10. weklund/fiduciary★ 10same name

    39 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use agency-clients, cross-post-video 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.
    • posteverywhereSkill

      agency-clients

      Work safely across several clients or brands in PostEverywhere. Use when the user manages social media for more than one client, brand or business, mentions a client by name, asks to switch clients, or when the connected accounts belong to different companies.

      Also in 3 projects that use this

    • posteverywhereSkill

      cross-post-video

      Post one video to several platforms with PostEverywhere, with the right title and caption for each. Use when the user wants to share a video, Reel, Short or TikTok across TikTok, Instagram Reels, YouTube Shorts, LinkedIn and Facebook Reels, or asks to "post this video everywhere".

      Also in 3 projects that use this

    • CodeWithSulemanSkill

      approval-workflow

      Manage human-in-the-loop approval workflows for sensitive actions like payments, emails to new contacts, social media posts, and other actions requiring human oversight.

      Also in 3 projects that use this

    • PostPeer-APISkill

      connect-social-accounts

      Connect, inspect, group, or disconnect social accounts in PostPeer. Use when the user asks to add OAuth integrations, connect LinkedIn/TikTok/Instagram/YouTube/Facebook/X/Pinterest/Threads/Bluesky/Google Business, create customer profiles, list connected accounts, generate OAuth URLs, use Bluesky app passwords, or remove integrations.

      Also in 3 projects that use this

    • HybridAIOneSkill

      write-blog-post

      Draft outlines and publish-ready blog posts tailored to audience, sources, and voice.

      Also in 3 projects that use this

    • +7 more from posteverywhere
  • In this repository6 other files it gives its agents.

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.

Check your setup, free