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

Deep Work Planner

ASecurity

Plan and protect deep work: scheduling focus blocks, task selection, shutdown rituals, and measuring depth. Use when important work never gets sustained attention or days fill with shallow tasks.

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

Works with

cli

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill deep-work-planner --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Deep Work Planner?

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

Security grade badge for Deep Work Planner
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-deep-work-planner/badge)](https://www.skillsdirectory.com/skills/aicodedecode-deep-work-planner)

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: deep-work-planner
description: Plan and protect deep work: scheduling focus blocks, task selection, shutdown rituals, and measuring depth. Use when important work never gets sustained attention or days fill with shallow tasks.
category: productivity
---

# Deep Work Planner

## Overview

Deep work = cognitively demanding tasks done in distraction-free concentration. It's where valuable output comes from — and it's incompatible with a fragmented calendar.

Shallow work (email, admin, meetings) expands to fill all available time unless deep work is scheduled first.

Planning deep work means: choosing the right tasks, blocking the time, designing the environment, and defending the blocks.

## When to use

- Important projects stall while email and meetings consume days
- Wanting a sustainable routine of focused creative work
- Knowledge workers feeling busy but unproductive
- Designing team norms that protect maker time
- Students or researchers needing long thesis/writing blocks

## Core concepts

- **Deep vs. shallow.**
  Deep: cognitively demanding, creates new value, hard to replicate. Shallow: logistical, easy to replicate, necessary but not valuable. Audit your week by this split.
- **Time blocking.**
  Deep work gets calendar blocks — 90+ minutes, ideally 2-4 hours. Unscheduled deep work doesn't happen; shallow work is the default.
- **Task selection.**
  Not all hard tasks deserve depth. Choose: high-leverage, deadline-meaningful, requiring sustained thought. One deep task per block.
- **The shutdown ritual.**
  End-of-day complete shutdown: review, capture open loops, close everything. Protects evenings and makes mornings start clean.
- **Attention residue.**
  Switching tasks leaves mental residue that degrades the next task. Single-task blocks + real breaks beat 'multitasking.'
- **Depth metrics.**
  Track deep hours per week and per project. What gets measured gets protected. 10-15 deep hours/week is excellent for most roles.
- **Energy alignment.**
  Schedule deep blocks in peak energy (usually morning). Guard the golden hours; shallow work fills the troughs.
- **Boredom tolerance.**
  Deep work requires tolerating boredom without reaching for the phone. This is trainable — start with 50-min blocks and extend.

## Practical workflow

1. **Audit the week.**
   Classify last week's hours: deep vs. shallow. Most find <5 deep hours. That's the baseline to beat.
2. **Choose deep tasks.**
   List this week's 2-3 highest-leverage cognitively-demanding tasks. These earn the blocks; everything else is shallow.
3. **Block 3-5 sessions.**
   90-180 min blocks, mornings preferred, on the calendar as unmovable commitments. Start with 3/week; build up.
4. **Design the environment.**
   Phone out of room, notifications off, door closed / status set, materials ready. Friction against distraction, not willpower.
5. **Define block protocol.**
   One task per block, timer optional, scratch pad for intrusions, break after. Same ritual every time builds the habit.
6. **Run the shutdown ritual.**
   End of day: 10 min to close loops, plan tomorrow's first block, shut down completely. No 'quick checks' after.
7. **Track depth weekly.**
   Log deep hours per block. Review: total, per project, interruptions. Trend matters more than any single week.
8. **Defend and expand.**
   Treat blocks like client meetings. Quarterly: can you add one more block? Can meetings move off golden hours?

## Common pitfalls

- **Scheduling but not defending.**
  Blocks that every 'urgent' request overrides. An undefended block teaches everyone it's fake. Defend or delete.
- **Too-ambitious start.**
  Five 3-hour blocks in week one. Start with 2-3 ninety-minute blocks; build the muscle before the marathon.
- **Wrong tasks in blocks.**
  Deep blocks spent on email triage. Blocks are for the 2-3 chosen deep tasks only — ruthlessly.
- **Phone in the room.**
  'On silent, face down' still tempts and still interrupts (vibration, screen glow). Out of the room, or it doesn't count.
- **Skipping the shutdown.**
  Evenings bleed into work, mornings start groggy. The shutdown ritual is what makes deep work sustainable.
- **Measuring only hours.**
  4 'deep' hours of distracted half-work. Honest focus matters more than clock time — pair with interruption logging.
- **All depth, no shallow time.**
  Deep blocks with no scheduled shallow time means shallow tasks invade the blocks. Schedule admin/email windows too.
- **Ignoring energy.**
  Deep blocks at 4pm for a morning person. Align with chronotype or fight biology every session.

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', ...

698621 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 →