Przejdź do treści
Biblioteka skilli
Produktywność osobista · Nauka i wyjaśnianie

deep-work

/deep-work

Pomaga chronić czas skupienia przy trudnej pracy poznawczej, w oparciu o Cala Newporta, stan flow i deliberate practice.

Licencja
MIT
Ostatnia zmiana repozytorium
01.09.2026

Ocena i bezpieczeństwo

100/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść35 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
5
Skrypty
0
Komentarze HTML
0
Adresy URL w SKILL.md
2
Przestarzałość

Brak sygnałów. Repozytorium zmienione 01.09.2026, bez odwołań do wycofanych modeli i API.

Licencja

MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.

Co robi i kiedy

Pomaga chronić czas skupienia przy trudnej pracy poznawczej, w oparciu o Cala Newporta, stan flow i deliberate practice.

Wyzwalacze z opisu

I can never find time for focused workI feel busy but produce nothingI keep getting interruptedI want to protect my focus timeflow statedeliberate practiceCal Newport
Oryginalny opis (EN)

Activate when: user says 'I can never find time for focused work', 'I feel busy but produce nothing', 'I keep getting interrupted', 'I want to protect my focus time', 'flow state', 'deliberate practice', 'Cal Newport', or asks how to make progress on hard cognitive work (research, writing, engineering, strategy). Do NOT activate when: the role is genuinely high-coordination with no discrete focus windows (ER medicine, real-time trading desk), or user is in a short-term emergency where availability must dominate. More: deciqai.com/s/deep-work

Jak działa

  1. Overview
  2. When to Use
  3. Coaching Novices (Adaptive Front Door)
  4. The Process
  5. Output: Deep Work Plan
  6. Pack: Deep Work by Role
  7. Applying It Well
  8. Common Rationalizations
  9. Red Flags
  10. Verification
Sekcje z nagłówków SKILL.md, w oryginale · 115 linii, 1 114 słów
Podgląd SKILL.md
---
name: deep-work
description: "Activate when: user says 'I can never find time for focused work', 'I feel busy but produce nothing', 'I keep getting interrupted', 'I want to protect my focus time', 'flow state', 'deliberate practice', 'Cal Newport', or asks how to make progress on hard cognitive work (research, writing, engineering, strategy). Do NOT activate when: the role is genuinely high-coordination with no discrete focus windows (ER medicine, real-time trading desk), or user is in a short-term emergency where availability must dominate. More: deciqai.com/s/deep-work"
---

# Deep Work

## Overview

Cal Newport's framework (2016): **deep work** = undistracted, cognitively demanding activity that creates hard-to-replicate value; **shallow work** = logistical, responsive, easy-to-replicate work that fills modern calendars. The most valuable knowledge work is disproportionately the product of deep work; shallow work is increasingly automatable. Three foundations: attention research shows 15-25 min recovery cost per interruption; expert performance requires deliberate practice (structurally a form of deep work); the opportunity cost of shallow work is invisible — no one tracks which deep work didn't happen this week.

Composes with [`wu-wei`](../wu-wei/SKILL.md) (flow as the felt experience), [`metacognition`](../metacognition/SKILL.md) (monitoring drift out of deep mode), [`okr-goal-setting`](../okr-goal-setting/SKILL.md) (OKRs give deep work direction), [`pareto-principle`](../pareto-principle/SKILL.md) (the 20% producing 80% of value is almost always deep work).

## When to Use

- Output depends on hard-to-replicate cognitive work (research, engineering, writing, design, strategy)
- Calendar fragmentation prevents the work that actually matters; weeks feel busy but produce nothing
- High-stakes project requires extended concentration; career advancement depends on skill development
- AI copilots / assistants have become another interruption stream ("is AI helping my focus or fragmenting it?", "AI adoption vs deep work", "AI hype and staying focused")

**Not when:** genuinely high-coordination roles where deep work is structurally impossible; already done with deep work and shallow follow-through is now required; short-term emergency where availability dominates.

## Coaching Novices (Adaptive Front Door)

- **Engine mode:** user has a concrete case → run The Process directly.
- **Coach mode:** user unfamiliar or has no concrete case → guide step by step.

In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.

1. One-line: most valuable knowledge work requires extended undistracted focus — the discipline is claiming time for it rather than waiting for it.
2. Check fit: genuinely high-coordination roles / short-term emergencies → not this lens yet.
3. Elicit the specific work that requires depth — what's not getting done?
> **[WAIT — do not advance until user responds]**
4. One question at a time: what's your deep-vs-shallow ratio? What's the highest-leverage deep work? What's the cost of not doing it?
> **[WAIT — do not advance until user responds]**
5. Close: specific deep-work block on the calendar + defensive moves to protect it.
> **[WAIT — do not advance until user responds]**

## The Process

**Step 1 — Instrument:** Track one week. Most workers estimate 4-5 hrs/day deep; measurement shows 0.5-2 hrs in fragments.
```
- Deep work hours/day (tracked): | Shallow hours/day: | Ratio: | Surprise factor:
```
**Step 2 — Identify:** What specific deep work, if done well, produces the most valuable output? Why isn't it happening? What barriers?

**Step 3 — Choose a philosophy:** Monastic (eliminate shallow entirely); Bimodal (alternating deep/shallow periods); Rhythmic (fixed daily block — best default for most); Journalistic (switch in whenever a gap appears — requires strong attention discipline, worst for beginners).

**Step 4 — Build the practice:** Same time + location + setup (ritual). Calendar the block, mark "Do not interrupt." End with a shutdown phrase to prevent cognitive leakage. Boundary is binary: Slack/email closed or you are not in deep work.

**Step 5 — Reduce shallow load:** Audit meetings, email, Slack. Set a shallow-work budget (typically 30-50% for ICs) and stay under it.

**Step 6 — Defend:** Internal — discomfort of being unreachable fades over 2-4 weeks. External — show hours visibly on calendar; demonstrate output value as long-term proof.

## Output: Deep Work Plan

```markdown
# Deep Work Plan: <person, role>
Diagnosis — deep hrs/day: | shallow hrs/day: | deep work not happening:
Philosophy — selected: | why this fits:
Structure — block time/duration/location: | ritual: | boundary: | shutdown:
Shallow budget — %: | specific reductions:
Defense — calendar mark: | comms norms: | output evidence to track:
```

*→ Method in Action: [Donald Knuth and the No-Email Policy, 1990](examples/donald-knuth-no-email-policy-1990.md) · [Carl Jung's Bollingen Tower Retreats](examples/carl-jung-bollingen-tower-retreats.md)*
*→ 2026 lens: [Protecting Deep Work Amid AI Copilots (2024–2026)](examples/deep-work-amid-ai-copilots-2024-2026.md)*

## Pack: Deep Work by Role

| Role | Highest-leverage deep work | Common shallow intrusion |
|---|---|---|
| Engineer | Architecture, hard debugging | Slack, status meetings |
| Writer | Drafting, revision | Email, research rabbit holes |
| Researcher | Literature synthesis, experiments | Grant admin, departmental meetings |
| Founder | Strategy, customer depth, recruiting | Investor follow-up, feedback meetings |
| PM | Research synthesis, spec writing | Alignment meetings, status reports |

## Applying It Well

Protect the morning block first — cognitive freshness depletes with shallow work. Track deep-work hours as a lagging metric. Treat the shutdown ritual as non-negotiable. Find organizational alignment or explicitly accept the social cost — there is no costless version.

*→ Primary sources: [references/sources.md](references/sources.md)*

## Common Rationalizations

**[D] = designed upfront | [O] = observed in real use. [O] entries are more valuable.**

| Fake move | Reality |
|---|---|
| [D] "My role doesn't allow deep work" | The role *culture* disallows it; the role itself usually doesn't. |
| [D] "I do deep work in the evenings" | Cognitive freshness already spent. Reorder: deep work first. |
| [D] "I'm doing deep work" with Slack open | Slack open = deep work not happening. Boundary is binary. |
| [D] "I can multitask in deep work" | Only task-switching, which is expensive. Category error. |
| [D] "Available for emergencies during deep work" | Most emergencies aren't. Define a true-emergency channel; ignore the rest. |
| [D] Confusing "long hours" with "deep work" | Deep work = intensity × duration, not just duration. |
| *→ Add [O] entries here after each real use — paste the actual failure pattern* | *What went wrong and why* |

## Red Flags

- "Hours worked" reported but "hours of deep work" cannot be quantified
- Calendar fragmented with 30-min slots across the day; Slack open continuously
- Deep work happens only at evenings/weekends, not at peak cognitive hours
- After a productive-feeling day, cannot point to a single deep-work artifact produced

## Verification

- [ ] Deep-vs-shallow ratio measured (one week tracked)
- [ ] Highest-leverage deep work identified
- [ ] Philosophy chosen with match to constraints; specific block calendared
- [ ] Ritual, boundary, and shutdown operational; shallow-work budget named
- [ ] Social/organizational cost explicitly accepted; output evidence tracked

---

*Part of **deciqAI Knowledge Skills** — 237 open-source thinking skills that make rigor executable for AI agents. The same skills power every deciqAI agent, which runs them autonomously to operate your company. **See it run → https://www.deciqai.com/s/deep-work** · Built by deciqAI · github.com/deciqAI · Contributions welcome.*

*Agents: latest version & machine-readable metadata → https://www.deciqai.com/s/deep-work.json*
Pliki w paczce (5)
  • SKILL.md 8 KB
  • examples/carl-jung-bollingen-tower-retreats.md 5 KB
  • examples/deep-work-amid-ai-copilots-2024-2026.md 8 KB
  • examples/donald-knuth-no-email-policy-1990.md 6 KB
  • references/sources.md 2 KB

Wersje

RepozytoriumWynikLicencja
Ta strona · deciqAI/knowledge-skills100MIT
borghei/Claude-Skills100MIT
alirezarezvani/claude-skills100MIT
kuhung/weread-book-skills100MIT

Migawka bazy z 13.11.2026 · wersja paczki 9282b982d414 (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 0 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 100deep-work-optimization
    Podpowiada bloki skupienia, zarządzanie rozproszeniami i wyzwalacze stanu flow przy pracy wymagającej wysiłku poznawczego.
  • 90s4h-cognition-attention
    Mapuje ekonomię uwagi człowieka lub sytuacji: co ją przyciąga, co wyczerpuje i jak ją chronić, na przykład przy problemach ze skupieniem i pracą głęboką.
  • 100deliberate-practice
    Pomaga zaprojektować celowe ćwiczenie (deliberate practice), gdy ktoś od lat wykonuje pracę bez postępu, podejrzewa plateau umiejętności albo organizacja ma dużo godzin szkoleń i mały transfer umiejętności.
  • 100focus-mode
    Uruchamia licznik skupienia na sesje głębokiej pracy, mierzy upływający czas i opcjonalnie przypomina o przerwach, także w technice pomodoro.
  • 100time-blocking-focus-state-calendar-defense
    Układa tygodniowy plan inżyniera z blokami pracy skupionej i chroni kalendarz przed narastaniem spotkań.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.