AGENT SKILL

ams-weekly-review

暂无简介

License 许可
MIT
所属仓库
TanNhatCMS/jarvis
最近更新
2026-11-07
Stars
★ 0
Forks
1

03 SKILL.md 正文

Weekly Review

Overview

The weekly review is the heartbeat of any productivity system: 30-60 minutes that keep capture trusted, projects current, and next week intentional.

Without it, inboxes overflow, projects stall silently, and the calendar fills with other people's priorities.

With it, you start each week clear: everything captured, everything current, next actions defined, week planned.

When to use

  • Tasks and commitments slipping through cracks
  • Productivity system feels stale or untrusted
  • Weeks feel reactive instead of intentional
  • Setting up GTD-style or any structured review habit
  • Transitioning between intense periods (post-launch, new quarter)

Core concepts

  • Get clear. Capture everything: inbox to zero, notes processed, loose papers and open loops collected. A trusted system starts empty-headed.
  • Get current. Review every active project: is there a defined next action? Update statuses, check waiting-fors, review calendar past + two weeks ahead.
  • Get creative. Review someday/maybe, goals, and vision. New ideas captured; stale ones deleted. The review is also for thinking, not just processing.
  • The trigger list. A checklist of areas to jog memory: projects, people, commitments, finances, health, home. Prevents 'oh no I forgot' discoveries.
  • Calendar review. Past week: what slipped and why. Next two weeks: deadlines, travel, big events. The calendar holds the constraints.
  • Project check. Each project: outcome still wanted? Next action defined and scheduled? Stalled projects get a decision: next action, park, or kill.
  • Someday/maybe sweep. Incubating ideas reviewed: anything now relevant? Anything to delete? Keeps the parking lot from becoming a junkyard.
  • The weekly plan seed. End the review by placing next week's big rocks on the calendar. The review flows directly into planning.

Practical workflow

  1. Schedule it fixed. Same 60-min slot weekly (Friday afternoon or Sunday evening). Non-negotiable, on the calendar, defended like a meeting.
  2. Set up the space. Checklist open, inboxes gathered (email, notes, paper, voicemail), distractions off. Ritual space = ritual happens.
  3. Get clear (15 min). Process every inbox to zero: 2-minute rule, delegate, defer with dates, file reference. Empty head, empty inboxes.
  4. Review calendar (10 min). Past week debrief + next two weeks scan. Note deadlines, prep needed, conflicts. Update or create tasks.
  5. Review projects (15 min). Each active project: next action defined? Status current? Waiting-fors followed up? Kill or park the dead ones.
  6. Review higher horizons (10 min). Goals progress, someday/maybe sweep, areas-of-focus check. Are projects aligned with what matters?
  7. Plan next week (10 min). Big rocks onto the calendar, top 3 outcomes for the week written down, Monday's first actions clear.
  8. Close the ritual. Tidy workspace, note one win from last week, one focus for next. End with clarity, not just completeness.

Common pitfalls

  • Skipping weeks. One skipped review is recoverable; two is a rotted system. Never skip twice — reschedule, don't cancel.
  • Marathon reviews. Letting it balloon to 3 hours because inboxes were ignored all week. Daily 5-min processing keeps the review to an hour.
  • Processing without deciding. Moving emails between folders instead of deciding. The review decides: do, delegate, defer, delete.
  • No trigger list. Reviewing from memory guarantees blind spots. A written trigger list (projects, people, areas) jogs the forgotten.
  • Review without planning. Getting clear and current but not placing next week's rocks. The review must end with next week planned.
  • Perfectionism. Trying to make the system perfect instead of current. 'Good enough and trusted' beats 'perfect and abandoned.'
  • Wrong time slot. Scheduling when you're exhausted or always interrupted. Pick a reliably quiet slot and protect it.
  • Solo without horizons. Only reviewing tasks, never goals. The higher-horizon sweep is what keeps the task list pointed the right direction.

04 同仓库更多 Skills

TanNhatCMS
TanNhatCMS/jarvis

web-scrape

Turn web pages into LLM-ready markdown via the Firecrawl API (renders JS, anti-bot handling). Use when browser_open/fetch fails on JS-heavy pages, or when you need clean markdown/structured extraction from a site. Requires FIRECRAWL_API_KEY.

★ 0
TanNhatCMS
TanNhatCMS/jarvis

design-taste-frontend

tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict no-slop house style with a real-browser inspector, and runs a look-and-fix loop on screenshots. Use this whenever you build, design, redesign, restyle, polish or review a landing page, marketing site, portfolio, product page, one-pager, hero or any public-facing web page, in any stack (HTML/CSS, React, Next.js, Vue, Svelte, Astro, Tailwind) — also when the user says a page looks generic, templated, "AI-made", sloppy, or asks to make it look designed, premium, award-level or less like every other site. Not for dashboards or app screens.

★ 0
TanNhatCMS
TanNhatCMS/jarvis

test-driven-development

Use when implementing any feature or bugfix, before writing implementation code

★ 0
TanNhatCMS
TanNhatCMS/jarvis

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

★ 0
TanNhatCMS
TanNhatCMS/jarvis

requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

★ 0
TanNhatCMS
TanNhatCMS/jarvis

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).

★ 0