Agent skill

Deep Work Blocking

by mohitagw15856 in mohitagw15856/pm-claude-skills

Protect focus time that actually survives the week — the block placement matched to real energy hours, the defense rules (what moves a block, what never), the entry ritual that beats the blank-stare…

MITAuto-check passedProductivity & Automation

Install Deep Work Blocking

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill deep-work-blocking -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills deep-work-blocking --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/deep-work-blocking .claude/skills/deep-work-blocking && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
deep-work-blocking
GitHub stars
1.4k
Token cost
~1.5k tokens
SKILL.md length
776 words
Files
1
Skills in repo
1,322
Repo updated
First seen
Licence
MIT

At a glance

Protect focus time that actually survives the week — the block placement matched to real energy hours, the defense rules (what moves a block, what never), the entry ritual that beats the blank-stare…

  • Works in 5 steps: Size honestly, place on peaks: 90–120… → Defense tiers, pre-decided: Tier 1… → The entry ritual kills the warmup tax:… → …
  • Asked block focus time that keeps getting eaten
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework: The Blocking Rules and Output Format, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Deep Work Blocking is an agent skill from mohitagw15856/pm-claude-skills. Protect focus time that actually survives the week — the block placement matched to real energy hours, the defense rules (what moves a block, what never), the entry ritual that beats the blank-stare start, and the honest sizing that stops 8-hour fantasy blocks. Use when asked block focus time that keeps getting eaten, when should I schedule deep work, my calendar has no room to think, or I block time and then waste it. Produces the block design, the defense tiers, the entry ritual, and the meeting-culture…

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation, covering Focus and ADHD support. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Asked block focus time that keeps getting eaten
  • Should I schedule deep work
  • My calendar has no room to think
  • I block time and then waste it

Example prompts

  • “/deep-work-blocking”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Size honestly, place on peaks: 90–120 minutes is the sustainable unit (attention's real budget); two such blocks is a strong day. The…
  2. Defense tiers, pre-decided: Tier 1 (never moves): the two weekly anchor blocks — invites get the script: "I have a commitment then…
  3. The entry ritual kills the warmup tax: the day before, the block gets its named task ("draft sections 2–3," not "work on the doc") · entry…
  4. Blocks are legible, not secret: the calendar shows "Focus block" (visible, normalized), the team knows the pattern ("mornings I'm deep…
  5. The block reviews itself: each block ends with 60 seconds — did the named task move? If blocks keep producing nothing, the diagnosis tree…

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deep Work Blocking loads about 1.5k tokens when it runs. Until then it costs about 136 tokens; SKILL.md has 776 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~136
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 776 words, ~1,508 tokens.

Download SKILL.mdSave it as .claude/skills/deep-work-blocking/SKILL.md (or your agent's skills folder).
name
deep-work-blocking
description
Protect focus time that actually survives the week — the block placement matched to real energy hours, the defense rules (what moves a block, what never), the entry ritual that beats the blank-stare start, and the honest sizing that stops 8-hour fantasy blocks. Use when asked block focus time that keeps getting eaten, when should I schedule deep work, my calendar has no room to think, or I block time and then waste it. Produces the block design, the defense tiers, the entry ritual, and the meeting-culture negotiation.

Deep Work Blocking Skill

Focus blocks fail three ways: placed wrong (2pm slump hosting the hardest work), defended badly (the block that moves for every invite is decoration with a border color), and entered badly (twenty minutes of warmup-shuffling inside a 90-minute block is a 70-minute block wearing a lie). The design fixes all three: blocks land on the user's actual high-energy hours (energy-scheduling supplies the map), carry explicit defense tiers (what outranks them — almost nothing — and the decline scripts), and start with an entry ritual — the named task waiting, the environment pre-set — because a block is a container, and containers need contents chosen before the clock starts.

What This Skill Produces

  • The block design — count, length (90–120 min beats the 8-hour fantasy), and placement on real energy hours
  • The defense tiers — what moves a block (genuine emergencies, defined), what never does, and the decline scripts
  • The entry ritual — the task named the day before, the environment checklist, the first-five-minutes rule
  • The culture negotiation — making blocks legible to the team (the shared norm beats the solo fight)

Required Inputs

Ask for these if not provided:

  • The energy reality — when the user's genuinely sharp hours fall (the honest answer, not the aspirational one); blocks on slump hours produce guilt, not work
  • The calendar's constraints — the immovable meetings, the team's collaboration hours, the time zone spread; blocks live in the real grid
  • The work that needs the blocks — the big-three outcomes (weekly-review-ritual) the blocks exist to serve; blocks without assigned work become email time with the door closed
  • The interruption culture — can a block survive here socially? The negotiation section scales to the actual environment

Framework: The Blocking Rules

  1. Size honestly, place on peaks: 90–120 minutes is the sustainable unit (attention's real budget); two such blocks is a strong day. The 8-hour focus fantasy collapses by 11am and discredits the practice. Placement follows the energy map — the best hours go to the hardest work first, before the calendar's entropy claims them (recurring-meeting-pruner reclaims supply this space).
  2. Defense tiers, pre-decided: Tier 1 (never moves): the two weekly anchor blocks — invites get the script: "I have a commitment then — Thursday 2pm works?" (a block IS a commitment; the script just declines to itemize it). Tier 2 (moves for named things): the flex blocks, moved forward in the same week, never deleted. The emergency definition is written: production-down and boss-says-now qualify; "quick sync?" does not.
  3. The entry ritual kills the warmup tax: the day before, the block gets its named task ("draft sections 2–3," not "work on the doc") · entry checklist: notifications off, the one document open, phone elsewhere · the first-five-minutes rule: start on the named task immediately, badly if necessary — momentum converts; browsing "to warm up" evaporates blocks whole.
  4. Blocks are legible, not secret: the calendar shows "Focus block" (visible, normalized), the team knows the pattern ("mornings I'm deep, afternoons I'm reachable" — working-agreements material), and the async norms (async-update-format) carry what would have interrupted. The solo fight against a synchronous culture loses; the negotiated norm holds.
  5. The block reviews itself: each block ends with 60 seconds — did the named task move? If blocks keep producing nothing, the diagnosis tree runs: wrong hours (re-place), wrong sizing (shrink), vague tasks (the naming discipline), or leaks (the defense failed — count what actually interrupted). Blocks that fail silently get quietly deleted by their owner within a month; the review is the early-warning.
Show full SKILL.md (207 more words)Show less

Output Format

Deep Work Design: [name] — [N] blocks/week

The Blocks

[Day × time × tier · placed on: (the energy map's peaks) · serving: (the big three)]

Defense

[Tier 1 anchors + the decline script · Tier 2 flex + the same-week-move rule · the written emergency definition]

The Entry Ritual

[Named-task-the-day-before · the environment checklist · the first-five-minutes rule]

The Culture Layer

[The calendar's public label · the team norm proposed · where the interruptions route instead]

Quality Checks

  • Blocks are 90–120 min on honest energy peaks
  • Every block has a tier and the scripts exist
  • Tomorrow's block already has its named task
  • The team-legibility norm is proposed, not just personal stealth
  • The 60-second self-review closes each block

Anti-Patterns

  • Do not block the fantasy 8 hours — two real units beat one heroic collapse
  • Do not place deep work on slump hours because they're free — free and useless is why they're free
  • Do not enter without a named task — an unassigned block is email with ambiance
  • Do not defend by itemizing — "I have a commitment" is complete; justification invites negotiation
  • Do not fight the culture solo forever — the negotiated norm is the sustainable version of the fight

Example Trigger Phrases

  • "Should I schedule deep work?"
  • "My calendar has no room to think."
  • "I block time and then waste it."

© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/deep-work-blocking of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Deep Work Blocking next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deep Work Blocking compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deep Work Blocking this skillmohitagw15856/pm-claude-skills1.4k—~1.5kAutomated safety check: PassMIT
I Have AdhdTanStack/ai3.2k5 repos~1.8kAutomated safety check: PassMIT
Attention Kindalexgreensh/attention-span1.4k—~2kAutomated safety check: PassAGPL-3.0
Remind Meshaheer-00/claude-adhd104—~1.1kAutomated safety check: PassNone
Daily Focus Boardgithub/awesome-copilot40k—~3kAutomated safety check: PassMIT
Attention Controlaaddrick/attention-control118—~3.6kAutomated safety check: PassMIT

Similar skills

  • I Have Adhd

    TanStack/ai

    A skill your agent uses when the user invokes /i-have-adhd, says they have ADHD, or asks for ADHD-friendly output.

    3.2k GitHub starsUsed in 5 repos~1.8k tokens
    Productivity & AutomationAuto-check passed
  • Attention Kind

    alexgreensh/attention-span

    Answer in the ADHD-friendly Attention-kind style for the rest of this chat.

    1.4k GitHub stars~2k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed
  • Remind Me

    shaheer-00/claude-adhd

    Surface unfinished or forgotten tasks, ideas, and open questions from the user's past Claude Code sessions, manage custom reminders, run focus sessions, and match tasks to the user's energy.

    104 GitHub stars~1.1k tokensUpdated 28 days ago
    Productivity & AutomationAuto-check passed
  • Daily Focus Board

    github/awesome-copilot

    Official

    Builds a warm, browser-based daily focus board the user updates by talking to their agent, with Eisenhower priorities, a brain-dump box and kind not-today carryover.

    40k GitHub stars~3k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Attention Control

    aaddrick/attention-control

    Shape output for a reader with ADHD, then write each sentence in controlled English: action first, one word one meaning, active voice, simple tenses, state restated every turn.

    118 GitHub stars~3.6k tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed
  • Fable Fable

    mrtooher/fable-mode

    Run fable-mode execution discipline on Claude Fable 5.1 — the top of the escalation ladder and the strongest staged run available.

    870 GitHub stars~1.1k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,322 skills in this repo
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • Offer Comparison

    mohitagw15856/pm-claude-skills

    Compare two or more job offers as total-comp curves over four years — vesting cliffs, bonuses, 401(k) match, and the crossover year computed, not vibed.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Refinance Breakeven

    mohitagw15856/pm-claude-skills

    Compute the month a refinance actually starts saving money — payment delta, breakeven month, and total interest on both paths including the term-reset trap.

    1.4k GitHub stars~1k tokensUpdated yesterday
    Auto-check passed
  • Rent Vs Buy

    mohitagw15856/pm-claude-skills

    Model rent-vs-buy honestly — year-by-year net position for both paths including the assumption everyone drops (the renter invests the difference), with a breakeven horizon instead of a verdict.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Deep Work Blocking

What does Deep Work Blocking do?

Protect focus time that actually survives the week — the block placement matched to real energy hours, the defense rules (what moves a block, what never), the entry ritual that beats the blank-stare…. Deep Work Blocking is an agent skill from mohitagw15856/pm-claude-skills. Protect focus time that actually survives the week — the block placement matched to real energy hours, the defense rules (what moves a block, what never), the entry ritual that beats the blank-stare start, and the honest sizing that stops 8-hour fantasy blocks.

When should I use Deep Work Blocking?

Deep Work Blocking fits situations like: asked block focus time that keeps getting eaten; should I schedule deep work; my calendar has no room to think; I block time and then waste it.

How do I install Deep Work Blocking in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill deep-work-blocking -a claude-code`. Or copy the skill folder (skills/deep-work-blocking in mohitagw15856/pm-claude-skills) into .claude/skills/deep-work-blocking in your project. Claude Code loads it when a task matches its description.

How do I install Deep Work Blocking in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill deep-work-blocking -a codex`. Or copy the skill folder (skills/deep-work-blocking in mohitagw15856/pm-claude-skills) into .agents/skills/deep-work-blocking in your project. Codex loads it when a task matches its description.

Can I use Deep Work Blocking in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mohitagw15856/pm-claude-skills --skill deep-work-blocking -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deep-work-blocking, .gemini/skills/deep-work-blocking, .github/skills/deep-work-blocking and .opencode/skills/deep-work-blocking in your project.

What does Deep Work Blocking need to run?

SKILL.md names no scripts, command-line tools or credentials: Deep Work Blocking is instructions for the agent only.

Does Deep Work Blocking access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Deep Work Blocking safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Deep Work Blocking use?

Deep Work Blocking is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deep Work Blocking use?

About 1.5k tokens (SKILL.md is roughly 6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Deep Work Blocking?

Skills that share tags, products or a category with Deep Work Blocking: I Have Adhd (TanStack/ai, 3.2k stars), Attention Kind (alexgreensh/attention-span, 1.4k stars), Remind Me (shaheer-00/claude-adhd, 104 stars) and Daily Focus Board (github/awesome-copilot, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deep Work Blocking?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,431 GitHub stars. The repository holds 1,322 skills in this directory. The repository was last updated on October 7, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.