安全

storm-ready

试用

Use when a hurricane/typhoon, ice storm, tornado outbreak, atmospheric river, wildfire season, or blizzard is approaching your area, when building a household emergency kit, when deciding how much water and food to store, when sizing a generator or power station for outages, when an advisory or watch is issued and you don't know what to do in what order, or annually to audit family preparedness — profiles your region's real hazards (gulf-coast hurricanes demand 14-day supplies, tornado country demands shelter kits, wildfire WUI demands go-bags), sizes water/food/power for YOUR people and pets with real math, runs a gap audit against your inventory, and prints phase-by-phase countdown checklists from T-72h through the storm to recovery, with the life-safety rules (CO, flood water, downed lines) that kill people every year.

它能做什么

Storm Ready — Household Preparedness Audit & Planner

技能文档

Storm Ready — Household Preparedness Audit & Planner

Overview

Emergency preparedness advice fails people in two ways: it's generic ("have 72 hours of supplies" — meaningless in a 14-day gulf-coast outage), and it's unordered (a 200-item PDF where the life-safety items are indistinguishable from the nice-to-haves). When a named storm is 72 hours out, you don't need a brochure — you need to know what your household is missing, what to do next, and the math for how much water, food, and battery capacity your family actually needs.

This skill is that: region profiles that encode what each hazard actually demands (a hurricane county's 14-day standard vs. tornado country's minutes-long warning), household-specific sizing (4 people + 60-lb dog + CPAP machine = 63 gallons of water, 112,000 kcal, and a battery plan that respects compressor surge), a gap audit against what you've marked as having, and a phase-by-phase countdown checklist from T-72h to recovery — with the P0 rules (generator CO, flood-water depth, fridge discipline) that keep appearing in after-action reports for a reason.

When to Use

  • A watch/advisory is issued for your region and the storm is days out → timeline
  • Building or reviewing a household emergency kit → audit (mark what you have, see the gaps)
  • "How much water/food do we actually need to store?" → water / food
  • Sizing a generator, power station, or battery backup → power
  • Moving to a new region: understand what its hazards demand → regions
  • Don't use for: active life-threatening emergencies (call local emergency services), tornado warnings already in progress (execute your existing plan, don't read docs), or real-time tracking (check NWS/national weather service).

Region Profiles

ProfileWaterFoodThe real demand
hurricane-gulf14 d14 dGrid down 1-3 wk, boil notices; county standard is 14 days
hurricane-atlantic7 d7 dDays-long outages inland after landfall
tornado3 d3 dWarning is MINUTES: safe room, helmets, shoes, whistle
ice-storm3 d5 dCold indoors is the killer; heat one room, CO alarm
atmospheric-river7 d5 dFlooding contaminates water; boil notices follow
wildfire-wui3 d3 dThis is a GO kit: packed by May, 10-minute evacuation
blizzard-plains3 d7 dSnowed IN for days: heat, cookable food, vehicle kit
generic3 d3 dReady.gov 72-hour baseline

regions prints this with notes. Region drives: checklist items included, day-counts in quantities, and which countdown phases apply.

Commands

# See region profiles and what each demands
python3 scripts/storm_ready.py regions

# Set up your household (people, pets with weights, region)
python3 scripts/storm_ready.py profile --region hurricane-gulf --people 4 \
    --pets "dog:60,cat:10"

# Gap audit: what you have (✓), partial (~), missing (✗) — P0 gaps listed last
python3 scripts/storm_ready.py audit
python3 scripts/storm_ready.py profile --mark-have radio first-aid flashlights
python3 scripts/storm_ready.py audit          # re-run: gaps shrink

# Sizing math for your household
python3 scripts/storm_ready.py water          # gallons + storage + purification
python3 scripts/storm_ready.py food           # kcal + pantry-basket plan
python3 scripts/storm_ready.py power --list   # known device loads
python3 scripts/storm_ready.py power --loads fridge,cpap,router-modem \
    --battery-wh 2000                          # Wh/day, runtime, surge, rules

# Countdown checklist when a storm is named
python3 scripts/storm_ready.py timeline --region hurricane-gulf

# Full demo on a gulf-coast family (4 people, 2 pets, CPAP)
python3 scripts/storm_ready.py example

Profile lives at ~/.storm-ready.json. --file overrides on any command.

The Math

  • Water: 1 gal/person/day drinking+basic (Ready.gov) + pets at ~1 oz/lb/day + optional 50% hygiene cushion → total gallons with container-count breakdown (7-gal aquatainers / 2.5-gal jugs / bottle cases) and three purification fallbacks (boil, bleach dosing, filter limits).
  • Food: people × days × 2,000 kcal with a pantry-rotation basket (canned meals first, calorie-dense no-cook foods, region-adjusted: cold regions get cookable options).
  • Power: per-load W × h/day = Wh/day; fridge/freezer duty-cycled at 150 W × 8 h; surge awareness (compressor start ×3.5) for inverter/generator sizing; usable battery fraction 0.85 (inverter + depth-of-discharge); power-station ladder showing runtime for 500/1000/2000/3000/5000 Wh banks.

Workflow

  1. regions → pick your profile; profile → set people/pets/region.
  2. audit → mark what you have (profile --mark-have ); re-run until the P0 gap list is empty.
  3. water / food → buy to the numbers, rotate with your pantry.
  4. power → if you have medical devices or outages are common, size honestly (including surge); register medical needs with your utility.
  5. When a storm is named: timeline --region → work top-to-bottom by phase; T-72h items exist because at T-12h the lines are long and the shelves empty.
  6. After: photograph everything before cleanup, insurance first, DisasterAssistance.gov if declared.

Common Pitfalls

  1. Running generators/grills indoors or in the garage. CO kills silently every single storm, this is the #1 post-storm death cause that isn't water. Outdoors, ≥20 ft from any window/vent, CO alarm indoors. power repeats this because it must.
  2. Driving through flood water. 6 in of moving water floats a car; 12 in takes an SUV. "Turn Around Don't Drown" is in the during phase for a reason.
  3. Generic 72-hour advice in a 14-day region. A gulf-coast hurricane kit that would sail in Kansas is 5× undersized. The region profile exists precisely so the numbers match the hazard.
  4. Forgetting pets in the math. A 60-lb dog drinks ~half a gallon a day and shelters won't take animals without shot records. Pet items are P0.
  5. Undersized inverters. Nameplate watts ≠ surge. A fridge drawing 150 W running needs ~525 W for compressor start; peak-line sizing in power accounts for it, cheap listings don't.
  6. Storing water you never rotate. Tap-water containers: refresh 6-12 months; keep bleach FRESH (it loses potency) and dated.
  7. Evacuating "to ride it out one more time." If you're in an evacuation/surge zone and officials say go — GO. Every hurricane after-action report says the same thing: the people who died mostly could have left.
  8. Tape on windows. Does nothing. Measured, cut, labeled plywood or tested film — installed at T-24h, not during the storm.

Verification Checklist

  • python3 scripts/test_storm_ready.py → ALL TESTS PASSED (35 assertions)
  • python3 scripts/storm_ready.py example renders audit + water + power + timeline
  • Profile set with correct region, people, and pets
  • audit P0 gap list is empty before storm season starts
  • Water/food stored to the computed numbers, dated for rotation
  • Everyone in the household knows shutoffs, safe room, and meeting point

相关技能

诊断生产力系统反复失效的根因,给出最小干预——容量测算、瓶颈定位、可靠的本地记录。

作者 Iván855 次安装69 星标

在本地磁盘以分类纯 Markdown 文件保存需要长期留存的事实,与智能体内置记忆并存。

作者 Iván559 次安装18 星标

把自然语言描述转为结构化 JSON,并由 mcp-diagram-generator MCP 服务生成 Draw.io、Mermaid 或 Excalidraw 图表文件。

作者 nssa.io1.0k 次安装47 星标

以 AI 机器人身份加入视频会议,提供语音、虚拟形象与屏幕共享四种模式。

作者 johnpatternai22 次安装8 星标

从 AdMapix API 拉取广告创意、应用、榜单和收入预估等数据,原样返回结构化 JSON。

作者 fly0pants4.3k 次安装296 星标

执行 Git 操作(提交、分支、合并、变基、冲突解决与恢复)时强制套用安全规则。

作者 Iván535 次安装31 星标

voronindenis5 的更多技能

浏览全部技能

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.

作者 voronindenis51 次安装

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.

作者 voronindenis52 次安装

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.

作者 voronindenis51 次安装

Turn flat resume bullets ('Responsible for X') into quantified STAR-method achievement narratives, score resumes against job descriptions for ATS keyword coverage and weak-phrase hazards, and expand each bullet into interview-ready stories with likely follow-up questions. Use when the user is writing or updating a resume/CV, preparing bullets for a job application, tailoring a resume to a specific job posting, or preparing interview stories from their experience.

作者 voronindenis51 次安装

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.

作者 voronindenis5