discover-israel-skills
Skill2 starsChanged 3 days agoMITView on GitHub
Use when the user wants to browse, discover, or install third-party Claude Code agent skills focused on Israel (tax/accounting, government services, healthcare pharmacies, rail, cinema, post tracking, legal research, security compliance, communication, etc.) — skills authored by people other than this plugin's author, indexed here for easy installation alongside this plugin. Reads a curated list from `data/third-party-skills.yaml` (monorepo skill collections from github.com/skills-il plus standalone skill repos), shows each entry with its source repo / subpath / blurb, confirms the user's selection, and installs the chosen skill(s) into `~/.claude/skills/<name>/` via `git clone` or sparse-checkout. Does not install anything without explicit confirmation. Also surfaces the awesome-list reference (alexpolonsky/awesome-agent-skills-israel) for broader discovery. Trigger phrases - "what other israel skills are there", "install israeli agent skills", "find me a skill for [israel rail / clalit / maccabi pharmacy / cinema / israel post / tax / accounting]", "discover israel skills", "browse israel agent skills", "third-party israel skills".
- Deletes or force-pushes
In this repository20 other files it gives its agents.
- add-skill-to-pluginSkill
- ben-gurion-flight-boardSkill
- drug-co-il-lookupSkill
- environment-checkSkill
- fiber-availability-checkSkill
- home-front-command-guidelinesSkill
- install-israel-pluginsSkill
- israel-conferencesSkill
- israel-drugs-registry-lookupSkill
- israel-news-rssSkill
- jerusalem-council-meetingsSkill
- jerusalem-municipality-reportSkill
- kol-zchut-lookupSkill
- list-skillsSkill
- maccabi-medicine-lookupSkill
- medicine-availability-checkSkill
- miklatim-lookupSkill
- nsc-travel-threatSkill
- salary-conversionSkill
- update-plugin-readmeSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 29
Ask which to install (all, none, or a comma-separated list of names).
- Very specific: line 43
Verify the installed folder contains a SKILL.md.
- Distinctive: line 52
Add repos to the list automatically.
- Very specific: line 69
Verify the upstream skill actually has a SKILL.md (or SKILL_HE.md) before adding.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
Discover Israel Agent Skills
Curated index of third-party Claude Code agent skills for life in Israel, with one-command install. The list lives in data/third-party-skills.yaml and is the authoritative source — do not enumerate entries in the README; direct users to invoke this skill.
What's indexed
Three shapes of upstream source:
- Monorepo collections —
github.com/skills-il/*organises several skills per repo, one per subfolder (each with its ownSKILL.md). Install the specific subfolder, not the whole repo. - Standalone skill repos — one skill per repo,
SKILL.mdat the top level (or under a stated subpath). - Awesome list —
alexpolonsky/awesome-agent-skills-israelis a human-readable index only; point the user there for browsing beyond the curated shortlist.
Projects that are not Claude Code skills (e.g. full web apps like shneorAziza/MyLaw) are intentionally excluded even if the user named them — mention that when asked.
Procedure
- Read
data/third-party-skills.yaml. - Group the entries by
categoryand show a numbered menu — one line per skill:<name> — <blurb> (<owner>/<repo>[/<subpath>]). - For each entry, check whether it's already installed:
test -d "$HOME/.claude/skills/<install_name>" && echo installed || echo missing - Ask which to install (
all,none, or a comma-separated list of names). - For each selected entry:
- Standalone repo, whole repo:
git clone --depth 1 https://github.com/<owner>/<repo>.git "$HOME/.claude/skills/<install_name>" - Monorepo subpath (sparse):
tmp=$(mktemp -d) git clone --depth 1 --filter=blob:none --sparse https://github.com/<owner>/<repo>.git "$tmp" git -C "$tmp" sparse-checkout set <subpath> mv "$tmp/<subpath>" "$HOME/.claude/skills/<install_name>" rm -rf "$tmp"
- Standalone repo, whole repo:
- Verify the installed folder contains a
SKILL.md; if not, warn the user and leave the folder in place for inspection. - Remind the user to restart Claude Code (or reload skills) so the new skill is picked up.
What this skill does NOT do
- Install without explicit user confirmation.
- Uninstall, update, or upgrade existing skills (point users at
rm -rf ~/.claude/skills/<name>+ re-install if they ask). - Install skills with
package.jsonscripts that requirenpm install— flag those and let the user run npm themselves; they may have their own Node environment preferences. - Vouch for the quality or safety of third-party skills. Surface the repo URL so the user can audit before running.
- Add repos to the list automatically. Maintainers add entries to the YAML after reviewing the upstream.
Safety
Third-party skill folders can contain executable scripts invoked by the agent. Before running an install, show the user the repo URL and a one-line blurb; encourage them to open the repo in a browser first if they don't recognise the author. Never auto-run post-install setup scripts.
Extending the list
Edit data/third-party-skills.yaml. Each entry needs:
install_name— the target folder name under~/.claude/skills/(kebab-case).owner,repo— GitHub coordinates.subpath(optional) — set for monorepo entries.category— one ofTax & Finance,Accounting,Government,Healthcare,Transport,Post & Logistics,Media & Entertainment,Legal & Compliance,Communication,Other.blurb— one line, plain English.upstream_url— canonical URL for audit.
Verify the upstream skill actually has a SKILL.md (or SKILL_HE.md) before adding.
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
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.

