Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.
Coding
deep-clean-battle-planner
Try itUse when planning a whole-house deep clean (spring cleaning, move-out, post-illness, before-guests) — turns rooms + available hours into ordered cleaning waves (dusty-first, top-down, machines working while you do), maps waves onto real weekend time blocks with a 15% buffer, matches surfaces x soils to the correct cleaner chemistry with never-mix warnings (bleach+acid, bleach+ammonia), and prints per-room zone playbooks with running time markers and upkeep recurrence cadences.
What it does
Overview Deep cleaning fails the same way every time: people start in the wrong room (mopping before dusting), underestimate by 2× (no dwell-time buffer), run out of energy mid-house with the worst rooms untouched, and improvise cleaner chemistry that damages surfaces (vinegar on stone) or actually…
The skill document
Deep-Clean Battle Planner
Overview
Deep cleaning fails the same way every time: people start in the wrong room (mopping before dusting), underestimate by 2× (no dwell-time buffer), run out of energy mid-house with the worst rooms untouched, and improvise cleaner chemistry that damages surfaces (vinegar on stone) or actually harms them (bleach + acid = chlorine gas; the US poison centers log tens of thousands of cleaning-substance exposures a year).
This skill treats the deep clean as a schedulable project:
- plan — rooms + hours → ordered waves. Dust-generating and high traffic zones first; top-down inside every room; machines (washer, oven cleaner) started at T-0 so they clean in parallel; 15% buffer.
- schedule — waves mapped onto your real time blocks ("Sat 3h, Sun 2h") with leftovers explicitly deferred, plus the upkeep cadence table that keeps the deep clean from relapsing in 3 weeks.
- products — surface × soil → the correct cleaner, dwell time, and warnings; always prints the never-mix danger table.
- zone — one-room playbook: ordered tasks with running time marks.
Pure stdlib, offline.
When to Use
- "This weekend I'm finally deep cleaning" — plan + schedule
- Spring cleaning / seasonal reset
- Move-out cleaning (deposit stakes)
- Post-illness household reset, before-guests blitz
- "What do I actually clean WITH?" — surface chemistry questions
- Building a recurring upkeep routine from the cadence table
Don't use for: hoarding-level remediation (professional help), post-flood/post-fire restoration (insurance + remediation contractors), or commercial/janitorial contracts (different standards and products).
How It Works — Numbered Steps
- Inventory the rooms and honest hours:
→ waves with per-task minutes; what fits is planned, what doesn't is DEFERRED (a rushed room is worse than a planned one).python3 scripts/clean_planner.py plan --rooms kitchen,bathroom-main,livingroom --hours 4 - Map to actual calendar blocks:
→ each block loaded to 85% capacity, leftovers named, upkeep cadence per room (kitchen 7d, bathroom 5d, hallway 30d...).python3 scripts/clean_planner.py schedule --blocks "Sat 3h,Sun 2h,Mon 1h" \ --rooms-list kitchen,bathroom-main,livingroom,bedroom,hallway,entry - Check every unfamiliar surface before spraying:
python3 scripts/clean_planner.py products --surface hardwood --soil general python3 scripts/clean_planner.py products --surface tile-grout --soil mold - Execute a room with the zone playbook (running time marks keep pace
honest):
python3 scripts/clean_planner.py zone --room kitchen - After the deep clean, adopt the upkeep cadences — recurrence (5d bathroom, 7d kitchen) prevents the next 8-hour marathon.
Ordering Rules (why the waves sort the way they do)
- Dusty work first — dust falls; cleaning under falling dust is rework. Entry and kitchen (grease+traffic soil) lead.
- Top-down in-room — fans → shelves → surfaces → floors, always.
- Machines at T-0 — washer, dishwasher, oven-cleaner dwell, hood filter soaking: they clean unattended while your hands do other work.
- Dwell chemistry — spray the tub, let it work 10 min WHILE doing the toilet and sink; scrubbing un-dwelt cleaner is 3× the effort.
- 15% buffer — supplies hunt, labels, phone. A plan at 100% capacity is a plan to fail by 4 PM.
Common Pitfalls
- Mixing cleaners. Bleach + vinegar/acid → chlorine gas; bleach +
ammonia → chloramine; peroxide + vinegar → peracetic acid. One cleaner
at a time, rinsed between. The danger table prints on every
productsrun for a reason. - Vinegar on stone/marble/granite etches permanently — pH-neutral only on natural stone (same for hardwood finishes long-term).
- Starting with floors. Floors are LAST in every room, after all dust has settled and been removed above them.
- No dwell time. Degreaser needs 5-10 min, oven cleaner needs overnight, mold gel 15 min. Spray-then-immediately-scrub wastes most of the chemical's work.
- Planning 100% of hours. The 85% capacity rule: 4h block = 204 planned minutes, not 240.
- The relapse cycle. Deep clean once, no cadence → back to start in a month. The recurrence table (bathroom 5d, kitchen 7d, hallway 30d) is the actual product of the deep clean.
- Magic eraser on glossy paint/sheen — it's micro-abrasive; test in a corner first (hallway task list warns).
- Boiling-water drains or caustic + plunger sequences — drain cleaners are exothermic; follow label timing exactly, full flush between different products.
Example
Saturday-Sunday plan, 6 rooms, blocks "Sat 3h, Sun 2h, Mon 1h":
$ plan --rooms kitchen,bathroom-main,livingroom --hours 4
→ WAVE1 kitchen 90m (8 tasks) → WAVE2 bathroom 60m (7 tasks);
livingroom DEFERRED.
$ schedule --blocks "Sat 3h,Sun 2h,Mon 1h" \
--rooms-list kitchen,bathroom-main,livingroom,bedroom,hallway,entry
→ Sat: entry+kitchen+hallway (135m of 153m usable)
Sun: bathroom+bedroom (100m of 102m usable)
Mon: catch-up block; livingroom left over → next weekend's wave 1.
$ products --surface tile-grout --soil mold
→ chlorine bleach gel, 15m dwell, ventilate, never-mix table.
Upkeep cadence printed at the bottom — bathroom every 5 days is what
keeps grout mold from ever coming back.
References
references/wave-method.md— the theory: soil types, ordering proofs, dwell chemistry, parallelizing machines, pace data behind task minutes.references/cleaning-chemistry.md— full surface × soil matrix, pH reasoning, the danger-mix table with symptoms and first response.
Related skills
Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.
Write, debug, and tune Playwright specs with locator strategy, trace diagnosis, and CI-aware timeouts.
More from voronindenis5
Browse all skillsPryamoy Russkiy (Straight Russian) — AI assistant that tells it like it is. Direct answers, no fluff, occasional profanity. Specializes in honest analysis, t...
Prepare salary negotiations with a structured toolkit: market-rate anchoring math, walk-away floor calculation, total-compensation evaluation (equity, bonuses, benefits), negotiation scripts for offers, raises, and counter-offers, and BATNA analysis. Use when the user has a job offer, is preparing a raise conversation, wants to know if their pay is competitive, or needs scripts and a strategy for negotiating compensation.
Use when your calendar is eating your week and you want to know exactly where the time goes, when planning recurring meetings for a team, before proposing a new recurring meeting, when someone says 'we should sync weekly' and you want data, or when auditing which meetings to kill — imports ICS calendar files, measures meeting hours per week/person/meeting-series (including double-bookings and fragmentation), computes focus-time destruction from meeting placement, scores the true cost of each series (hours × attendees × frequency), flags specific meetings to kill/shorten/make-async using explicit rules, and simulates the recovered hours before anyone has to argue about it.
Use when you realize your photos/code/documents exist in exactly one place (or your 'backup' is a external drive in the same room as the computer) — audits your actual data-loss risk against the 3-2-1 rule (3 copies, 2 media, 1 offsite) asset by asset, scores blast radius (ransomware encrypts synced copies too), prices honest recovery (professional recovery lab $300-3000 vs $0), generates the minimum-cost redundancy plan for YOUR asset list, and produces a restore-test drill because an untested backup is a hope, not a backup.
Audit password vault exports (Bitwarden, 1Password, KeePass, Chrome, Firefox) for reuse, weakness, staleness, breach exposure, and 2FA gaps without ever storing or transmitting a plaintext password. Use when the user asks to audit passwords, check password strength/reuse, review vault health, or verify whether credentials appeared in breaches.
Use before any difficult phone call you're anxious about or that has stakes — calling customer service to dispute a fee, negotiating a bill, cold-calling a client, delivering bad news to a vendor, calling a landlord about repairs, insurance disputes, or handling collections calls — builds a branching call script from your situation (goal, leverage, fallback), generates objection→response trees for the specific counter-arguments you'll hear, produces a one-page printable cheat sheet, and includes a practice-drills mode that plays the other side and scores your responses.