agentleFS
danielrosehilldanielrosehill/Claude-Israel-Agent-Skills-Plugin/skills/home-front-command-guidelines/SKILL.md

home-front-command-guidelines

Skill2 starsChanged 24 days agoMITView on GitHub

Use when the user asks about Israeli civilian emergency / shelter / protection guidelines issued by Pikud HaOref (Home Front Command, פיקוד העורף) — e.g. what to do during a rocket or missile alert, how long they have to reach a protected space (mamad / miklat), what to do in a vehicle, on the road, or outdoors during a siren, hazardous-materials events, terrorist infiltration, hostile aerial vehicle (drone) infiltration, how to prepare a home protected space, emergency equipment lists, family emergency planning, and official alert channels. Answers from a bundled English-language snapshot (22 files, ~31K words) of the official oref.org.il/eng guidelines and always cites the upstream source URL per answer. Trigger phrases - "what do I do during an air raid", "how long to get to a shelter", "rocket siren guidelines", "mamad requirements", "home front command advice", "pikud haoref guidelines", "shelter time in my area", "what to do if siren goes off in car", "hazardous materials instructions", "oref guidelines", "prepare emergency kit Israel".

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read the matching file(s) from data/guidelines/ and answer from the contents verbatim where relevant.

    line 19
  2. Very specific:

    Always cite the upstream source_url from the manifest entry alongside the answer.

    line 20
  3. Very specific:

    Before answering, check manifest.extraction_date.

    line 21
  4. Very specific:

    Never invent numbers. If the user asks "how long do I have in Tel Aviv" and that exact answer isn't in the snapshot, say so and point to …

    line 37
  5. Distinctive:

    Do not present this skill as a substitute for emergency services.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Home Front Command Guidelines (Pikud HaOref)

Answers civilian emergency-preparedness and shelter-protocol questions from a local snapshot of the official Home Front Command (פיקוד העורף, Pikud HaOref) guidelines.

Sources

  • Primary (bundled): data/guidelines/ — 22 English-language Markdown files extracted from https://www.oref.org.il/eng. The snapshot's extraction date is recorded in data/guidelines/manifest.json under extraction_date.
  • Authoritative live source: https://www.oref.org.il/eng — always cite this as the canonical reference in answers, and direct the user there for the most current guidance.

How to answer

  1. Parse data/guidelines/manifest.json to index titles, categories, source URLs, and file paths.
  2. Match the user's question against title, categories, and file-path topic folder (e.g. shelter-and-home, security-threats, faq).
  3. Read the matching file(s) from data/guidelines/ and answer from the contents verbatim where relevant.
  4. Always cite the upstream source_url from the manifest entry alongside the answer.
  5. Before answering, check manifest.extraction_date. If older than ~6 months, add a prominent note that guidelines may have been updated and link to https://www.oref.org.il/eng.

Topic folders

FolderCovers
alerts-and-communication/Alert channels, siren types, app/portal/TV/radio, fake-news guidance
defensive-policy/HFC policy levels, routine during war, education and gatherings
emergency-preparedness/Equipment lists, family plans, emergency contacts
faq/General behavior, hazardous materials, rocket/missile, arrival time to protected space
security-threats/Hostile aerial vehicles (drones), terrorist infiltration, threat-type overview
shelter-and-home/Mamad requirements and maintenance, preparing home, choosing protected space

Answer hygiene

  • Quote the guidelines rather than paraphrasing when the detail matters (e.g. exact times to reach shelter, exact equipment list items).
  • Never invent numbers. If the user asks "how long do I have in Tel Aviv" and that exact answer isn't in the snapshot, say so and point to oref.org.il/eng.
  • Include the upstream source_url for the file(s) you drew from.
  • Do not present this skill as a substitute for emergency services. In an active emergency the user should call 100 (police), 101 (Magen David Adom / ambulance), or 102 (fire) as relevant.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.