Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Weekly Review

ASecurity

Run a weekly review that keeps your whole system trusted: capture, clarify, calendar, and project check-ins. Use when tasks slip, the system goes stale, or weeks feel reactive.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsrustgoreact

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill weekly-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Weekly Review?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Weekly Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-weekly-review-awesome-muse-skills/badge)](https://www.skillsdirectory.com/skills/aicodedecode-weekly-review-awesome-muse-skills)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: weekly-review
description: Run a weekly review that keeps your whole system trusted: capture, clarify, calendar, and project check-ins. Use when tasks slip, the system goes stale, or weeks feel reactive.
category: productivity
---

# 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.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →