After The Disaster logo

After The Disaster

CommunityPopular
mohitagw15856
after-the-disaster

Work through the first hours and days after a disaster — a fire, flood, storm, or evacuation — in the right order: safety and people first, then documenting for insurance and aid, then the immediate recovery steps, without missing the things that cost money or health later. Use when someone says 'my house flooded/burned', 'what do I do after the disaster', 'we just evacuated, now what', or 'the storm damaged everything'. Produces a triaged action plan (safety → document → claim → recover), the do-not-miss list, and where to get help. Not legal advice; routes to emergency services and official aid.

Overview

Publishermohitagw15856
Repositorypm-claude-skills
Skill nameafter-the-disaster
Stars
1.4K
Forks
240
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by mohitagw15856 on GitHub. Read the source before you install it.

Installation

Install the After The Disaster AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git /tmp/pm-claude-skills
mkdir -p .claude/skills
cp -r /tmp/pm-claude-skills/exports/openclaw/after-the-disaster .claude/skills/after-the-disaster
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable After The Disaster in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads After The Disaster on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so After The Disaster is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

After The Disaster Skill

In the hours after a disaster, shock and urgency make people do things in the wrong order — re-entering an unsafe building, throwing out damaged items before documenting them (and losing the insurance claim), or missing the aid window. There is a right order: people and safety first, then documentation, then claims and recovery — and knowing it turns a chaotic, costly aftermath into a sequence you can follow. This skill triages the first hours and days, front-loads the safety non-negotiables, and flags the do-not-miss steps (the photos before cleanup, the claim deadline, the aid you're entitled to) that quietly cost people the most later. It routes emergencies to services and claims/aid to the official bodies.

What This Skill Produces

  • A triaged action plan in strict order: (1) safety & people, (2) document everything, (3) notify insurance & register for aid, (4) immediate recovery — because doing these out of order costs money and safety
  • The do-not-miss list: the steps people skip in the chaos and regret — photograph damage before cleaning up, don't discard items until documented, hit the claim/aid deadlines, keep every receipt
  • Where to get help: emergency services for danger, the insurer to start the claim, and official disaster-aid/relief programs to register for (which have windows)
  • A health & safety brief: the hidden post-disaster hazards — contaminated flood water, structural instability, mold, carbon monoxide, downed lines — so recovery doesn't create the next injury

Required Inputs

Ask for (if not already provided):

  • What happened and the current situation — are people safe now, is the building safe, is anyone hurt or missing
  • The type and rough extent of damage (flood, fire, wind, evacuation with home intact)
  • Whether they have insurance and their [[emergency-doc-kit]] (policy numbers, contacts)
  • Where they are (country/area) so official aid/relief routes can be pointed to

Framework

  1. People and safety first — always. Before anything: is everyone accounted for and uninjured? Injuries → medical help. Is the structure safe to be in (fire damage, flood, gas, downed power lines)? Do not re-enter an unsafe building for belongings — this is where post-disaster deaths and injuries happen. Contaminated flood water, CO, and structural collapse are the immediate killers; the skill leads here, firmly.
  2. Document before you touch anything. The costly, universal mistake: cleaning up or discarding damaged property before photographing it, which cripples the insurance claim. Photograph and video everything — the damage, every damaged item, the waterline — before any cleanup, and keep damaged items until the insurer says otherwise. The [[emergency-doc-kit]]'s home inventory pairs with this.
  3. Notify insurance and register for aid — mind the windows. Contact the insurer as soon as safe to start the claim (policy number from the doc kit), and register for official disaster relief/aid programs, which frequently have application deadlines and are missed in the fog. Keep every receipt from the moment of the disaster (emergency accommodation, supplies) — many are reimbursable.
  4. Immediate recovery, in safe order. Prevent further damage where safe (tarp a roof, stop water) since insurers expect reasonable mitigation, but not at the cost of safety. Secure the property, sort temporary accommodation, and preserve the doc-kit records. Guard against post-disaster scams — fake contractors and charities target disaster victims ([[scam-message-decoder]]).
  5. Watch the delayed hazards and the human toll. Mold after flooding, ongoing structural risk, contaminated water, and the CO risk from generators/pumps during recovery. And the emotional reality: disaster recovery is a marathon of stress and grief; name that support (disaster mental-health lines, community relief) is part of the plan, not weakness.

Output Format

## FIRST: are people and the building safe?
[Everyone accounted for/uninjured? · is it safe to be in the building? · do NOT re-enter an
unsafe structure · the immediate hazards: flood water, gas, power lines, CO]

## Document before you touch anything
[Photograph/video ALL damage and every damaged item BEFORE cleanup · keep damaged items ·
the waterline/extent]

## Notify & register (mind the deadlines)
[Insurer — start the claim (policy # from your doc kit) · official disaster aid/relief —
register, note the window · keep every receipt from now]

## Immediate recovery (safe order)
[Prevent further damage where safe · secure property · temp accommodation · beware
disaster scammers]

## Delayed hazards & support
[Mold, structural, contaminated water, CO during recovery · disaster mental-health/
community support — part of the plan]

⚠ Emergencies → emergency services. This is not legal/insurance advice — route claims to
your insurer and aid to official relief programs, and follow the authorities.

Quality Checks

  • Safety and people are handled first, with a firm "do not re-enter an unsafe building"
  • "Document before cleanup" is prominent — the costliest common mistake
  • Insurance notification and official-aid registration are included with their deadline windows and the keep-receipts rule
  • The delayed hazards (mold, structural, contaminated water, CO) are covered
  • Emotional/mental-health support is named, and scams are flagged

Anti-Patterns

  • Do not put property before people — re-entering an unsafe structure for belongings is how the aftermath kills
  • Do not let cleanup happen before documentation — it destroys the insurance claim
  • Do not miss the aid/claim deadlines — they're real and easily lost in the shock
  • Do not ignore the delayed hazards or the mental-health toll — recovery is where the second wave of harm lands
  • Do not give legal/insurance determinations — route to the insurer, official aid, and professionals; watch for the scams that target victims

Related

[[emergency-doc-kit]] supplies the records to start claims; [[insurance-claim]] and [[claim-denial-decoder]] for the claim itself; [[scam-message-decoder]] for disaster scams; [[grief-admin]] and [[stoic-setback-debrief]] for the human aftermath; [[family-emergency-plan]] for reconnecting.

Frequently asked questions

What does the After The Disaster AI skill do?

Work through the first hours and days after a disaster — a fire, flood, storm, or evacuation — in the right order: safety and people first, then documenting for insurance and aid, then the immediate recovery steps, without missing the things that cost money or health later. Use when someone says 'my house flooded/burned', 'what do I do after the disaster', 'we just evacuated, now what', or 'the storm damaged everything'. Produces a triaged action plan (safety → document → claim → recover), the do-not-miss list, and where to get help. Not legal advice; routes to emergency services and offici...

Why use After The Disaster on TypingMind?

Because you install it once and use it with any model. After The Disaster is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install After The Disaster in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mohitagw15856/pm-claude-skills/tree/main/exports/openclaw/after-the-disaster. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use After The Disaster?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with After The Disaster?

As many as you like. As long as a model supports skills, you can use After The Disaster with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the After The Disaster AI skill free?

Yes. It is published on GitHub by mohitagw15856 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇