agentleFS
aminbadhaminbadh/workspace-starter/.agents/skills/weekly-review/SKILL.md

weekly-review

Skill0 starsChanged 25 days agoMITView on GitHub

The weekly review: upkeep that keeps the workspace true (leftover work, the linter worked against reality, each installed skill's Weekly step), then the user's own planning rhythm, which puts the week's plan in the task home. Use when the user says it is review time, asks to plan the week, or asks what needs attention across the whole workspace. Never unprompted, and not for routine work inside one domain.

99 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 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.
  • 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

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 84 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Read every SKILL.md in .agents/skills/ and run each one's ## Weekly section, if it has one.

    line 33
  2. Distinctive:

    If the task home is TASKS.md, clear the ticked tasks and empty last week's This week section.

    line 37
  3. Distinctive:

    Do not commit: the user reviews and commits (AGENTS.md).

    line 53

“Common” is measured: kept by at least 6 in 10 of the 84 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

The Weekly Review

Two jobs, kept apart. Upkeep is the same for everyone and keeps the files true. The rhythm is the user's own way of planning and reflecting, chosen at onboarding and written in PROFILE.md, so this skill stays the same in every workspace. Upkeep runs first, because planning from stale files means planning against something that is no longer true.

The linter is the agenda. A domain being worked stays fresh, because work updates what it invalidates (AGENTS.md, rule 5). A quiet domain goes stale and the linter flags it. So the review never sweeps every domain: it works what is flagged, and nothing else.

Upkeep

1. Leftover work

  • If the workspace has a remote of the user's own (git remote -v; the upstream named on README.md's Upstream: line, the template this workspace was made from, does not count), pull first with git pull --ff-only, to pick up work from another machine. With no remote, skip this. With no git at all, skip this whole step.
  • A dirty tree is normal, not a blocker. Work is committed by the user when it is done, never by the review.
  • Flag only stale dirty files: uncommitted and untouched for a week or more. That is abandoned work rather than live work; ask whether to finish, commit or drop it.

2. Work the linter

uv run .agents/scripts/workspace-lint.py. Fix the errors. Then, for each warned file:

  • Read it and check it against reality: the task home, the sources it was filled from, the user. Do not just bump the date. Bumping without verifying turns a stale file into one that looks fresh.
  • Look for: Next Up items already done, blocked (name the blocker; if it is a person, the item is the unblock) or not actions at all; dates written as pending that have passed, or that belong in the task home (CONVENTIONS.md); facts stated in two places (the more specific file wins).
  • Fix what rotted, then bump last_reviewed. If nothing rotted, say so and bump.
  • Stable by nature rather than unreviewed: give it a longer review_interval instead of rereading it every fortnight.
  • Dormant and flagged: archive it or wake it. Dormant is a holding state, not a graveyard.
  • Active but not moved in a month, with no trigger: it is dormant. Say so.

3. Each skill's Weekly step

Read every SKILL.md in .agents/skills/ and run each one's ## Weekly section, if it has one. A skill declares its own weekly step there, so this list never needs editing when an add-on is moved in.

4. The task home

If the task home is TASKS.md, clear the ticked tasks and empty last week's This week section. In a task app, leave its own housekeeping to it.

5. The rhythm, after a few weeks

If the rhythm in PROFILE.md was chosen four or more weeks ago and has not been checked since, ask whether it is working: is the review getting done, and does the plan get followed? If not, the onboard skill's update mode swaps it. Note the answer under the rhythm, with the date, either way.

The rhythm

Read the rhythm named in PROFILE.md's "Weekly rhythm" section, and run its planning and reflection steps from its entry in the rhythms reference. What PROFILE.md adds is the user's own: their day, steps they skip or add, and weekly steps of theirs that belong to no skill. Where the two differ, PROFILE.md wins.

Until one is chosen: read each active domain's Next Up, ask the user which one to three to do this week, and put them in the task home.

Close

  • Bump last_reviewed on everything actually verified, and nothing else.
  • Say in a few lines what changed and what the week's plan is.
  • Do not commit: the user reviews and commits (AGENTS.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.