agentleFS
JipletJiplet/transformation-os/skills/program/weekly-review/SKILL.md

weekly-review

Skill2 starsChanged 4 months agoMITView on GitHub

Walk Jacob through the Friday retro or Sunday week-ahead draft at wiki/2-Weekly/, present the proposed kanban diff, apply atomically on approval, and lock the file. Use when Jacob types /weekly-review or asks to "do the Friday review", "Sunday planning", "weekly review", "walk through the weekly draft".

92 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use quarterly-review, daily-plan 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.
  • Phoenixrr2113Skill

    quarterly-review

    Quarterly review — strategic look at the last 3 months. Career trajectory, project health, life balance, big decisions ahead. Runs 1st of Jan/Apr/Jul/Oct.

    Also in 3 projects that use this

  • steptianSkill

    daily-plan

    每日待办计划与日程管理。触发词:'今天要做'、'今日计划'、'今日待办'、'今天安排'、'安排一下'、'加个任务'、'记个任务'、'今日复盘'、'今日回顾'、'今天总结'、'本周计划'、'周总结'、'开始工作'、'上班了'、'完成了'、'加个日程'、'记个日程'、'改一下时间'、'日程调整'、'面试'、'开会'、'约了'。支持四象限优先级、时段分配、固定日程管理、智能时间估算、每日/每周复盘。当用户提到有明确时间的安排(如'下午两点面试'、'10点开会'),自动识别为日程并写入日程表。

    Also in 3 projects that use this

  • seedprodSkill

    daily-brief

    Send a morning briefing via Telegram with weather, news, and a motivational quote. Designed to run via launchd for automated daily delivery.

    Also in 5 projects that use this

  • claude-office-skillsSkill

    meeting-notes

    >

    Also in 8 projects that use this

  • Phoenixrr2113Skill

    morning-brief

    Full morning brief — calendar, email, meeting prep, execute actionable items, create follow-up tasks. Runs at 8:03 AM or when Randy asks for a morning update.

    Also in 4 projects that use this

  • zephyrwang6Skill

    daily-review

    每日工作回顾与洞察分析,对用户前一天的对话历史和使用数据进行总结与建议

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 5 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 80 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before presenting anything, read every file the draft references:

    line 24
  2. Very specific:

    All daily logs for the ISO week (wiki/1-Daily/YYYY-MM-DD.md)

    line 26
  3. Distinctive:

    Do not present any claim you have not grounded in a file you have actually read this session.

    line 29
  4. Very specific:

    Call the kanban-curate skill before walking through the draft.

    line 35
  5. Distinctive:

    Wait for explicit approval before touching any file.

    line 80
  6. Distinctive:

    When Jacob approves the diff (full or partial):

    line 86
  7. Very specific:

    If a status change moves a card between columns, update master.md accordingly (move the - [ ] [[...]] entry to the correct column)

    line 88
  8. Very specific:

    After all changes applied, update the weekly file frontmatter: set status: locked and add locked: <ISO datetime>

    line 89
  9. Distinctive:

    If Jacob rejects part of the diff, apply only the approved subset.

    line 93

“Common” is measured: kept by at least 6 in 10 of the 80 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

Skill: weekly-review

What this does

Walks Jacob through a Friday retro or Sunday week-ahead draft, presents a single consolidated kanban diff, applies changes atomically on approval, and locks the weekly file. Called Friday 7am AEDT (retro) and Sunday 8pm AEDT (week-ahead), or any time Jacob types /weekly-review.


Step 1: Locate the draft

Scan 1 - Knowledge/wiki/2-Weekly/ for files where frontmatter status: draft. Sort by created descending; take the most recent. The flavour field is either friday or sunday.

If no draft exists: read all daily logs in 1 - Knowledge/wiki/1-Daily/ for the current ISO week plus all cards in 1 - Knowledge/wiki/0-Kanban/cards/, then generate a draft file following the _template-friday.md or _template-sunday.md schema (choose by day of week; Friday = retro, Sunday = week-ahead). Write the draft file, then proceed.


Step 2: Pre-flight read

Before presenting anything, read every file the draft references:

  • All [[CLT-NN-*]] and [[INIT-*]] cards linked in the draft
  • All daily logs for the ISO week (wiki/1-Daily/YYYY-MM-DD.md)
  • wiki/0-Kanban/master.md

Do not present any claim you have not grounded in a file you have actually read this session.


Step 3: Invoke kanban-curate

Call the kanban-curate skill before walking through the draft. Receive its structured findings list (read-only mode). Hold these for inclusion in the diff in Step 4.


Step 4: Walk through the draft — section by section

Present each section, pause, and wait for Jacob's edits before moving on. Do not batch all sections at once.

Friday flavour (retro):

  1. Sessions this week (daily-log roll-up) — read aloud, pause for edits
  2. Decisions made — read, pause
  3. Due / overdue items — read, pause
  4. Open threads — read, pause
  5. Proposed kanban diff (see Step 5)

Sunday flavour (week-ahead):

  1. Top 3 priorities — propose from kanban + last week's open threads, pause for Jacob's refinement
  2. Cards landing this week (grouped by sector: telco / transport / dsi / infra / group) — read, pause
  3. Risks / blockers — read, pause
  4. Standing items — read, pause
  5. Proposed kanban diff (see Step 5)

Step 5: Proposed kanban diff

Present one consolidated diff list, grouped in this order. Include curate findings (Step 3) as additions.

### Status moves
- cards/CLT-NN-foo.md — status: In Progress -> status: Review

### Due-date changes
- cards/CLT-NN-foo.md — set due: YYYY-MM-DD (was unset)

### Tag fixes
- cards/CLT-NN-foo.md — add sector/telco (was missing)

### New cards
- cards/CLT-NN-foo.md — title, parent_initiative, status: Backlog

### Hygiene (from kanban-curate)
- cards/CLT-NN-foo.md — [finding from curate]

Wait for explicit approval before touching any file.


Step 6: Atomic apply

When Jacob approves the diff (full or partial):

  • Apply ALL approved changes in one pass: edit card frontmatter fields directly
  • If a status change moves a card between columns, update master.md accordingly (move the - [ ] [[...]] entry to the correct column)
  • After all changes applied, update the weekly file frontmatter: set status: locked and add locked: <ISO datetime>

Confirm with a count: "Applied N changes to M cards. Weekly file locked."

If Jacob rejects part of the diff, apply only the approved subset. Restate the final count accurately.


Conventions

Card frontmatter fields (do not invent new ones): id, title, type, status, project, sector, parent_initiative, owner, raised, last_session, due, output, plan, tags

Valid status values (must match master.md columns exactly): Backlog, In Progress, Review, Done, Archive

Valid sector tags: sector/telco, sector/transport, sector/dsi, sector/infra, sector/group — exactly one per CLT card

Tag format: lowercase, kebab-case only (per 1 - Knowledge/CLAUDE.md tag taxonomy)

master.md column format: - [ ] [[INIT-slug]] #sector/x (Backlog / In Progress / Review / Done) or - [x] [[INIT-slug]] #sector/x (Archive)


Tone

Jacob is Head of Transformation. Lead with the so-what. No preamble. Concise, executive-ready. Take positions. Flag decisions that need his judgment; do not make them silently. Match the voice in <workspace>/CLAUDE.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.