Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
Coding
laundry-decoder
Try itDecode laundry care symbols from text descriptions (tub, triangle, iron, circle, square shapes with dots/bars), build a safe wash plan for a mixed load (color bleeding risk, temperature ceilings, fabric conflicts), and give evidence-based stain removal protocols by stain type. Use when the user asks what a care label means, whether clothes can be washed together, what temperature is safe, or how to remove a specific stain without ruining the fabric.
What it does
Care labels are a pictographic language most people can't read — surveys consistently show **the majority of consumers misinterpret care symbols**, which is why shrinking sweaters and pink-white laundry are universal experiences. This skill translates symbols to plain instructions, tells you whethe…
The skill document
Laundry Decoder 🧺
Care labels are a pictographic language most people can't read — surveys consistently show the majority of consumers misinterpret care symbols, which is why shrinking sweaters and pink-white laundry are universal experiences. This skill translates symbols to plain instructions, tells you whether today's pile can be one load or must be several, and gives stain-specific first aid ordered by least-destructive-first.
Overview
Three jobs, one tool (scripts/laundry_decoder.py):
- Symbol decode — describe a symbol in words (
tub 40,triangle crossed,iron 2 dots,circle p,square circle 1 dot) and get the meaning, the risk if ignored, and the safe-action phrasing. Covers the ISO 37500 / GINETEX families: washtub (wash), triangle (bleach), square with circle (dry), iron (iron), circle (professional care). - Load planner — enter garments with color class, max temperature,
fabric, and delicates flag; the planner partitions them into the fewest
safe loads using real rules:
- temperature = min of the load's ceilings
- new/dark cottons bleed onto lights (hot water worsens it)
- delicates never mix with heavy cottons/towels (abrasion)
- wool/silk never mix with cotton terry (felting + snagging)
- items flagged "hot wash only" (bad towels, workout synthetics) can't go cold
- Stain first aid — 20+ common stains, each with a protocol ordered from least to most aggressive for the stated fabric, plus the one thing you must NOT do (heat-set proteins! bleach on wool!).
Everything is stdlib-only and offline — the data lives in the script.
When to Use
- "What does this symbol on my shirt mean?" (user describes it in words)
- "Can I wash these together?" — jeans + new red tee + white towels
- "What temperature should this load be?"
- "How do I get [red wine/blood/coffee] out of [cotton/wool/silk]?"
- "I washed a red shirt with whites — now what?" → reversal advice for dye-transfer accidents (in references)
Don't use for: dry-cleaning chemical handling (that's professional territory), leather/suede care (different domain entirely).
How It Works — Steps
- Decode a label — user reads the symbols aloud:
python3 scripts/laundry_decoder.py decode "tub 30" "triangle crossed" "iron 1 dot" "circle p" - Plan loads — one garment per
--item(format:name;color;temp;fabric[;flags], color ∈ white/light/dark/red/new, temp = max °C, flags: delicate, hot-only):python3 scripts/laundry_decoder.py plan \ --item "white towels,white,90,cotton" \ --item "red tee,new,40,cotton" \ --item "jeans,dark,40,denim" \ --item "silk blouse,light,30,silk,delicate" - Get the partition: which loads, what temperature, what cycle, and the specific rule that forced each split.
- Stain help:
python3 scripts/laundry_decoder.py stain "red wine" --fabric cotton - Browse all symbols (
--list) when the user wants a reference sheet.
Conflict Rules (the load-planner brain)
| Rule | Effect |
|---|---|
bleeder (new/red) + non-bleeder | separate load — no exceptions |
| delicate + heavy fabric | separate (delicates cycle protects both) |
| wool/silk + terry/towels | separate (felting, snagging) |
| hot-only + cold-max item | separate (can't satisfy both temps) |
| load temperature | min of members' ceilings |
| mixed colors without bleeders | allowed, cold/warm |
Worked Example
Items: white towels (90°C), new red tee (40°C), jeans (40°C), silk blouse (delicate, 30°C) →
Load 1: white towels — 90°C, cotton/heavy cycle
Load 2: red tee — 40°C, first wash alone (color-set: cold + salt/vinegar soak)
Load 3: jeans — 40°C, turned inside-out
Load 4: silk blouse — 30°C, delicates cycle, mesh bag
4 loads, each split justified by a rule — the planner names the rule.
Common Pitfalls
- Heat-setting protein stains (blood, egg, milk). Hot water cooks the protein into fibers permanently. Always cold first — the stain table enforces this ordering.
- Bleach on wool/silk/lycra — dissolves the fibers. Chlorine bleach is whites-cotton-only; oxygen bleach is the safer general choice.
- Overloading detergent "for extra clean" — excess traps soil back into fabric and wreks machines (yes, the residue myth is real: it's called redeposition).
- Assuming "dry clean" means dry clean ONLY. The circle means the manufacturer chose not to test home care; many silks and wools handle careful hand-washing — see references for the risk framework.
- Tumble-drying what says "dry flat" — wool knits stretch under their own weight + tumble; the shape never comes back.
- Mixing a bleeder "just once, cold" — new red/black cottons bleed even cold. Two solo washes first, then they join the family.
Verification Checklist
- Every load's temperature ≤ min of member ceilings
- No bleeder shares a load with a non-bleeder
- No delicate shares with heavy cotton/terry
- Stain protocol starts with the least aggressive step
- Protein stains never meet hot water in step 1
One-Shot Recipes
"Translate this whole label":
python3 scripts/laundry_decoder.py decode "tub 40 with bar" "square circle 1 dot" "triangle" "iron crossed" "circle p"
Weekly load plan for the family pile:
python3 scripts/laundry_decoder.py plan --item ... (one per garment) --json
Emergency stain card (print & keep by the washer):
python3 scripts/laundry_decoder.py stain --fabric cotton | a2ps
Related skills
Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.
Post videos, photos, text, and documents to 10 social platforms through a single REST API call.
Trade crypto, manage a multi-chain wallet, and query an AI analyst from one CLI.
Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
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.
Agent self-awareness of cognitive states — context fatigue, attention drift, memory debt, confidence erosion, and skill staleness. Detect, report, and mitigate degrading conditions before they cause failures.
Plan what happens to your digital life if you die or become incapacitated. Inventory accounts, subscriptions, crypto wallets, important files, social media legacy contacts, and generate a sealed instruction document for trusted family. Includes encrypted digital will template and printable emergency access guide.
Use when an agent task fails or produces unexpected results. Performs structured post-mortem root cause analysis: categorizes the failure, traces the exact failure point through tool-call logs, reconstructs the decision chain, generates a post-mortem report, and saves lessons to prevent recurrence.
Excavate forgotten solutions, code snippets, and decisions from past conversation sessions. Use when the user is re-solving a problem you've likely solved before, hunting for a lost snippet, or wants to mine session history for buried knowledge instead of starting from scratch.