agentleFS
SkillMedevSkillMedev/personal-operating-system/skills/deep-work-planner/SKILL.md

deep-work-planner

Skill1 starsChanged 38 days agoMITView on GitHub

Designs a daily schedule that protects deep work - classifies tasks as deep or shallow, places 2-4 focus blocks of 60-120 minutes at peak energy hours, batches shallow work into fixed windows, and defines each session with a goal, definition of done, distraction plan, and first action, plus startup/shutdown rituals and a weekly scorecard. Use when someone says "I can't get any focused work done", "plan my day around deep work", "how do I stop context switching", or wants to defend calendar time for demanding work. Do NOT use for processing an email backlog - use inbox-zero instead - or for a full task-capture system - use gtd-system instead.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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
  1. Distinctive:

    Place 2-4 deep blocks of 60-120 minutes at your peak energy hours (for most people, the first hours after starting).

    line 24
  2. Distinctive:

    The 5-minute rule: when the urge to switch hits, commit to 5 more minutes first.

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Deep Work Planner

Deep work is cognitively demanding work done without distraction. It produces disproportionate value. This skill helps you protect and design it.

Step 1: Classify your tasks

Sort the day's tasks into two lists:

  • Deep - requires sustained focus, creates new value, hard to replicate (writing, designing, coding hard logic, strategy).
  • Shallow - logistical, low-concentration, often interrupt-driven (email, Slack, scheduling, quick reviews).

Step 2: Schedule deep blocks

  • Place 2-4 deep blocks of 60-120 minutes at your peak energy hours (for most people, the first hours after starting).
  • Block them on the calendar as real events - defend them like meetings.
  • Single-task: one project per block. No context switching mid-block.
  • Cap deep work at ~4 hours/day; it is a finite daily resource.

Step 3: Batch the shallow

  • Collect shallow tasks into 1-2 fixed windows (e.g. 11:30 and 16:30).
  • Communicate your async hours so people know when to expect replies.
  • Anything under 2 minutes during a batch window: just do it.

Step 4: Design the session

For each deep block, define before you start:

Block: <time range>
Goal: <one concrete deliverable>
Definition of done: <how you'll know you're finished>
Distraction plan:
  - Phone: in another room / focus mode
  - Notifications: off
  - Tabs: only what's needed
First action: <the very first move so you don't stall>

Focus rituals

  • Startup ritual: clear desk, water nearby, close comms, write the goal at the top.
  • The 5-minute rule: when the urge to switch hits, commit to 5 more minutes first.
  • Shutdown ritual: at day's end, review what shipped, plan tomorrow's first block, then disconnect completely.

Energy management

  • Match task type to energy: deep work at peaks, shallow at troughs.
  • Take a real break between deep blocks (walk, no screens) - focus needs recovery.
  • Protect sleep; deep work quality collapses when under-rested.

Weekly scorecard

Track and review each week:

  • Deep hours completed vs. planned.
  • Biggest distraction source - eliminate one per week.
  • Best deliverable produced in deep time.

Anti-patterns

  • "I'll focus when I get a free moment" - free moments never come; schedule it.
  • Checking messages inside a deep block - even a glance costs 20+ min of refocus.
  • Stacking back-to-back deep blocks with no recovery - quality decays fast.

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.