weekly-review
Skill1 starsChanged 19 days agoApache-2.0View on GitHub
Weekly pass over the task board; chase Waiting blockers, name carried Doing tasks, read Done against plan, schedule one important non-urgent task. The person decides every move. Run after a daily-review, which it does not replace.
92 other projects use a version of this.
Adopted by
Most recently taken up by
- nicolas-diez/personal-ostheir own version, first seen Nov 8, 2026
- chrisblattman/claudeblattmantheir own version, first seen Nov 8, 2026
- totorototo/ledgertheir own version, first seen Nov 8, 2026
- TalkToHumans/pull-labtheir own version, first seen Nov 8, 2026
- Castan-AI/founder-commandstheir own version, first seen Nov 8, 2026
- jwm-axoni/claude-workbenchtheir own version, first seen Nov 8, 2026
Used with
Projects with it also use quarterly-review, daily-plan 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.
Phoenixrr2113Skillquarterly-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
steptianSkilldaily-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
seedprodSkilldaily-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-skillsSkillmeeting-notes
>
Also in 8 projects that use this
Phoenixrr2113Skillmorning-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
TheCraigHewittSkillresearch-brief
Produces a one-page research brief on a topic, person, or company — what they do, what matters, what's changed recently, sources. Use when the user asks to research, look into, brief me on, or get context on a specific topic, company, competitor, or person. Pulls from the web, any project context, and recent emails involving the subject.
Also in 3 projects that use this
Other versions92 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 92
- QuixiAI/agi-memory★ 623same name
- QuixiAI/Hexis★ 623same name
- chrisblattman/claudeblattman★ 479same name
- andreaskelm/pm-brain★ 235same name
- duncan-buildroom/freeskills★ 65same name
- andrehuang/researcher-pack★ 50same name
- seandavi/lifeos-template★ 46same name
- chacosoldier/compabob★ 34same name
- cookyman74/llmwiki-harness★ 34same name
- jexchan/dailyup-second-brain-starter★ 33same name
82 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.
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/agents.mdcCursor rule
- commandsSkill
- daily-dashboardSkill
- daily-reviewSkill
- document-standardsSkill
- jotSkill
- merge-proxySkill
- monthly-reviewSkill
- orientSkill
- redaction-gateSkill
- session-closeSkill
- session-logSkill
- skill-creationSkill
- skill-discoverySkill
- surface-regimesSkill
- technical-documentsSkill
- touchSkill
- working-preferencesSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 80 edited versions we read keep these.
3
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
- Distinctive: line 29
Run the lane-board command once and read all of it, including the coverage line.
- Distinctive: line 44
Doing, by count: Every task in Doing whose carry count is three or more, with its count and its next action.
- Distinctive: line 49
Done, read back: Every task that reached Done since the last weekly review.
“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.
Files
When to Use
Once a week, on a fixed day, after that day's daily review. Invoked by a person, never by an agent.
Adapting this skill: filenames below name roles rather than literal paths. It assumes the same
task queue, lanes and lane-board tool as daily-review, and reads its lanes table and its
definition of urgency from there rather than restating them. CLAUDE.md names the command. Check
the tool's coverage line before starting: this review needs each task's blocker, carry count, due
date, consequence and quadrant, and for a Done task its close date and verification, and a field the tool does not print is a reason to extend the tool,
not to read the queue by hand.
Why a weekly pass exists
The daily review handles what arrives and what is next. Three things move too slowly for it to see. A blocker named on Monday is still named on Friday, and nobody has asked whether it is still true. A task carried one day at a time never looks stuck on any single day. And because urgency is read from due dates, the Decide quadrant never forces itself onto the day: each important task loses to something urgent every morning, and is never refused, only postponed. This pass looks at all three on purpose, once a week, so the daily pass can stay short.
Phase 1: Observe
Run the lane-board command once and read all of it, including the coverage line. If it fails
validation, stop and report the fault. If the week's daily reviews recorded their moves in each
task's note, as daily-review asks, read the notes of the tasks this review proposes to move; they
are the only record of how a task got where it is.
Phase 2: Propose, lane by lane
For each step, a short table of proposed moves, one row per task, each with a one-line reason. Do not write anything yet. A step with nothing to propose is one line saying so.
- Waiting, chased. For each Waiting task, ask whether its blocker is still true, and who clears it. Propose one of: keep it Waiting with the blocker restated and a next action naming who takes it; return it to Next because the blocker has cleared; or, where the blocker is a person who has not answered, a next action to ask them again by a named day. A blocker that names no person, task or event is a finding: it cannot clear, so it is not a blocker.
- Doing, by count. Every task in Doing whose carry count is three or more, with its count and its next action. Propose one of: split it, so the part that can finish this week is a task of its own; return it to Next, freeing the seat; or keep it, with the reason it is still the right work. A task carried all week is a plan that did not survive contact, and the question is which part of the plan was wrong, not who was slow.
- Done, read back. Every task that reached Done since the last weekly review. For each, say whether its verification, as written when the task was added, was the check that actually closed it. A close that rested on a different check is not reopened here; it is named, so the next task written in that shape states its verification more honestly. Then list anything the week finished that has no task, and propose recording it, so the Done lane is a true record of the week.
- One important task, scheduled. Choose one Decide task from Next and propose a day this week on which it is the person's first work. Record the day in its next action and its note, never as a due date: a due date with a consequence makes a task urgent, and turning an important task into an urgent one to get it done is the starvation this step exists to stop. Choose by the long-term goals the tree has written down; where none are written, the choice is the person's, and the review says so rather than inventing a basis.
Phase 3: Ask, then stop
Chat output, not a document. End with questions: one per step that has proposals, each accepting that step's table as written, and the person answers exceptions by task ID in prose. Then stop.
Phase 4: After the answers
Apply exactly the accepted moves, in one scripted edit that asserts each task's current lane before changing it. A task returning to Next takes the bottom rank of its quadrant unless the person names another. Record each move in the task's note with the date and "weekly review". Run the lane-board command again and show the lanes that changed. Nothing moves on a task the person did not answer; an unanswered row stays where it was and is listed as unanswered.
Scope Pointer
daily-review: the once-a-day pass. It empties the Inbox, orders Next and names the day's Most Important Task. This skill does none of those, and a task scheduled here enters Next's order through the next daily review.daily-dashboard: the state view. It checks the standing files and working trees against their claims; this reads the board.monthly-review: Someday adopted or rejected, and archive candidates chosen by the person. A Waiting task chased here more than once with no change is a candidate for it.session-close: updates the standing files at the end of a session. A move made here is already in the queue and does not wait for it.
<!--
SPDX-FileCopyrightText: 2026 Aidan Naveja
SPDX-License-Identifier: Apache-2.0
-->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
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.

