skills/focus-timeboxing-8020/SKILL.md
Combines Pareto prioritization (80/20), timeboxing, and deep work techniques to manage attention, eliminate context-switching, and maximize high-impact output. Use when managing time and attention, combating procrastination, prioritizing high-impact work, planning daily/weekly schedules, or when user mentions timeboxing, Pomodoro, deep work, 80/20 rule, Pareto principle, focus blocks, task batching, or energy management.
npx skillsauth add lyndonkl/claude focus-timeboxing-8020Install this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Scenario: Engineer overwhelmed with tickets, meetings, code reviews, and a complex feature.
80/20: Ship payment feature (biggest customer request, revenue impact) = vital 20%.
Weekly Plan:
Outcome: Feature shipped in 3 days (18 hours deep work) vs. estimated 2+ weeks with constant interruptions.
Copy this checklist and track your progress:
Focus & Timeboxing Progress:
- [ ] Step 1: Identify your 80/20
- [ ] Step 2: Design focus blocks
- [ ] Step 3: Timebox your week
- [ ] Step 4: Timebox your day
- [ ] Step 5: Execute with discipline
- [ ] Step 6: Review and adjust
Step 1: Identify your 80/20
What 20% of tasks drive 80% of your results? Separate vital few from trivial many. See resources/template.md.
Step 2: Design focus blocks
Block time for deep work on high-impact tasks. Match duration to task type (Pomodoro 25min, Deep Work 90-120min). See resources/template.md and resources/methodology.md.
Step 3: Timebox your week
Allocate weekly calendar: deep work blocks, meeting blocks, batched admin, buffer time. See resources/template.md and resources/methodology.md.
Step 4: Timebox your day
Break day into time-constrained blocks with start/end times. Schedule breaks. Plan evening hard stop. See resources/template.md.
Step 5: Execute with discipline
Honor timeboxes. Use timers. Eliminate distractions (Slack off, phone away, close tabs). Take breaks. See resources/methodology.md.
Step 6: Review and adjust
Weekly review: Did you protect deep work? What interrupted focus? Adjust schedule. See resources/template.md and resources/methodology.md.
Validate using resources/evaluators/rubric_focus_timeboxing_8020.json. Minimum standard: Average score ≥ 3.5.
Pattern 1: Pomodoro Technique (25 min focus)
Pattern 2: Deep Work Blocks (90-120 min)
Pattern 3: Weekly 80/20 Planning
Pattern 4: Task Batching (30-60 min blocks)
Pattern 5: Maker's Schedule (Half-day or Full-day blocks)
Pattern 6: Energy-Based Scheduling
Protect deep work time: No meetings, no Slack, no email during focus blocks. One interruption destroys 20+ minutes of flow. Schedule deep work during peak energy (usually mornings).
Use Parkinson's Law: Work expands to fill available time. Shorter timeboxes force prioritization and prevent perfectionism. A 90-minute timebox with a clear outcome beats open-ended "work on this."
Identify the 80/20: Force rank tasks by impact. The top 20% should get 80% of focus time. Cut, delegate, or batch the rest.
Energy matters more than time: 8 hours tired produces less than 4 hours energized. Match intensity to energy level. Troughs are for admin and meetings, not complex thinking.
Build in buffer: Leave ~20% unscheduled for unexpected issues, overflow, and breaks. Over-scheduling is fragile; one delay cascades.
Set hard stops: Define an end-of-day time. Constrained time forces prioritization; endless time enables procrastination.
Take breaks: After 90 minutes of deep work, take 10-15 minutes. Walk, stretch, look outside. Focus degrades after 90-120 minutes without a break.
Measure focus quality, not hours: 3 hours of deep work outperforms 8 hours of distracted work. Track completed focus blocks per week, not total hours.
Common pitfalls:
Timeboxing durations:
| Duration | Best For | Rest After | |----------|----------|------------| | 25 min | Pomodoro, high-resistance tasks, building habit | 5 min | | 50 min | Focused work, moderate complexity | 10 min | | 90 min | Deep work, complex thinking, creative tasks | 15 min | | 120 min | Maximum deep work (rare, high expertise) | 20-30 min | | Half-day (4h) | Maker's schedule, breakthroughs, flow state | Lunch + afternoon off |
Energy-based scheduling:
| Time | Energy Level | Task Type | Examples | |------|--------------|-----------|----------| | 6-9am | Peak (early risers) | Deep work | Writing, coding, strategy | | 9am-12pm | Peak (most people) | Deep work | Complex problems, creative work | | 12-2pm | Lunch dip | Meetings, social | Standups, 1:1s, collaboration | | 2-3pm | Trough | Admin, batching | Email, Slack, expense reports | | 3-5pm | Recovery | Moderate work | Code reviews, planning, lighter tasks | | Evening | Low | Rest or routine | Reading, exercise, NOT deep work |
80/20 identification:
Ask these questions:
Focus blockers (eliminate during deep work):
Batching categories:
Weekly planning template (simplified):
Monday-Wednesday mornings: Deep work on Priority 1 (3× 90-min blocks)
Monday-Wednesday afternoons: Meetings, collaboration, moderate work
Thursday: Deep work on Priority 2 (morning), meetings (afternoon)
Friday: Batched admin, planning next week, code reviews
Inputs required:
Outputs produced:
weekly-timeboxed-schedule.md: Calendar with focus blocks, meeting blocks, batch timesdaily-plan.md: Time-blocked day with start/end times, breaks scheduled8020-analysis.md: Prioritized task list with vital few identifiedfocus-time-tracker.csv: Log of focus blocks completed, quality, interruptionstesting
Cluster a conference's event records into a small set of coarse themes with finer sub-clusters, an explicit outlier bucket, and soft (multi-membership) affinities — using the hybrid embed-then-label pipeline (embed abstracts, reduce, density-cluster, then LLM-label the clusters) when embedding libraries are available, and an LLM-reasoned hierarchical fallback when they are not. Embeddings do the grouping; the LLM only names the groups. Conference-agnostic. Use when turning structured event records into a navigable theme map for preference elicitation and scheduling, when you need 6-8 reasonable themes rather than 20 muddy ones, or when overlapping talks must belong to more than one theme. Trigger keywords - theme clustering, cluster talks, embed then label, soft membership, outlier talks, conference themes, topic map.
development
Build a personal conference schedule as a constraint-optimization problem — hard constraints (no time overlap, room-to-room travel time, capacity/registration, the attendee's own must-attends and blackouts) plus a user-owned weighted objective trading interest against breadth, pacing (maximize contiguous free time), and serendipity. Surfaces unbreakable conflicts (two high-value overlapping talks the model cannot rank) as decisions for the human rather than silently picking, and reports what each choice traded away. Conference-agnostic. Use to turn a preference profile plus a theme map into a day-by-day plan, to resolve overlapping sessions, or to balance a packed vs paced schedule. Trigger keywords - schedule optimization, conference schedule, constraint optimization, overlapping talks, contiguous free time, conflict surfacing, packed vs paced.
development
Parse a heterogeneous conference program (markdown, HTML, PDF-derived text, or JSON) into normalized event records with per-field confidence scores and independent classification axes (topic, depth, format, prerequisites, recorded, capacity). Detects the program's format before extracting, treats every inferred field as uncertain (present vs inferred vs missing), and flags thin or missing abstracts so downstream enrichment can target them. Conference-agnostic. Use when ingesting a conference or event schedule into a structured store, normalizing a talk/session list, or extracting per-session metadata with calibrated confidence. Trigger keywords - program ingestion, parse schedule, session extraction, event records, conference program, talk metadata, per-field confidence.
development
Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it can actually ask the person. Conference-agnostic. Use to turn a theme map into a preference profile, to decide what to ask a conference attendee, or to elicit scheduling priorities. Trigger keywords - preference elicitation, ask few questions, information gain, choice-based questions, selection bias probe, objective weights, attendee preferences.