Agent skill

Earthquake Watch

by mohitagw15856 in mohitagw15856/pm-claude-skills

Check recent earthquakes worldwide with zero API keys — USGS real-time GeoJSON feeds via curl, filtered by magnitude, region, and time window.

MITAuto-check passed

Install Earthquake Watch

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill earthquake-watch -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills earthquake-watch --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/earthquake-watch .claude/skills/earthquake-watch && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
earthquake-watch
GitHub stars
1.4k
Token cost
~1.2k tokens
SKILL.md length
573 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Check recent earthquakes worldwide with zero API keys — USGS real-time GeoJSON feeds via curl, filtered by magnitude, region, and time window.

  • Works in 5 steps: The feeds —… → Targeted queries beat feed-filtering for… → Magnitude bands, stated with every… → …
  • Asked was there an earthquake just now
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework: The Feed Matrix and… and Output Format, plus 3 more sections
  • Reaches earthquake.usgs.gov

What it does

Earthquake Watch is an agent skill from mohitagw15856/pm-claude-skills. Check recent earthquakes worldwide with zero API keys — USGS real-time GeoJSON feeds via curl, filtered by magnitude, region, and time window. Use when asked was there an earthquake just now, recent quakes near a place, any big earthquakes today, or monitor seismic activity somewhere. Produces the matching events with magnitude, depth, location and time, the felt/damage context bands, and the rerunnable command — with the official-guidance line safety questions require.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Asked was there an earthquake just now
  • Recent quakes near a place
  • Any big earthquakes today
  • Monitor seismic activity somewhere

Example prompts

  • “/earthquake-watch”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. The feeds — https://earthquake.usgs.gov/earthquakes/feed/v1.0/summary/{mag}_{window}.geojson where mag ∈ significant, 4.5, 2.5, 1.0, all…
  2. Targeted queries beat feed-filtering for specific regions: https://earthquake.usgs.gov/fdsnws/event/1/query?format=geojson&latitude=35.68&l…
  3. Magnitude bands, stated with every event: <3 rarely felt · 3–4 felt, no damage · 4–5 felt widely, minor damage possible near epicenter ·…
  4. Times get converted: feed times are epoch UTC; the answer speaks the user's local time ("14 minutes ago, 03:12 local").
  5. The safety line: for "should I worry / is a bigger one coming" — aftershock probabilities and tsunami assessments belong to official…

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • earthquake.usgs.gov

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Earthquake Watch loads about 1.2k tokens when it runs. Until then it costs about 123 tokens; SKILL.md has 573 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~123
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 573 words, ~1,201 tokens.

Download SKILL.mdSave it as .claude/skills/earthquake-watch/SKILL.md (or your agent's skills folder).
name
earthquake-watch
description
Check recent earthquakes worldwide with zero API keys — USGS real-time GeoJSON feeds via curl, filtered by magnitude, region, and time window. Use when asked was there an earthquake just now, recent quakes near a place, any big earthquakes today, or monitor seismic activity somewhere. Produces the matching events with magnitude, depth, location and time, the felt/damage context bands, and the rerunnable command — with the official-guidance line safety questions require.

Earthquake Watch Skill

"Did we just have an earthquake?" gets asked within seconds of every tremor, and the USGS answers globally in near-real-time over keyless HTTPS. This skill knows the feed matrix (magnitude threshold × time window), filters to the place actually asked about, and frames magnitudes honestly — a 4.5 under a city and a 6.0 under the ocean are different events, and depth is half the story. For anything safety-shaped, it points at official emergency guidance rather than improvising any.

What This Skill Produces

  • The events — matching quakes with magnitude, depth, location, and time (converted to the user's zone)
  • The context read — what that magnitude/depth typically means for feeling it and damage, as bands not predictions
  • The regional filter — the feed is global; the answer is about the place asked
  • The command — exact curl, rerunnable

Required Inputs

Ask for these if not provided:

  • Where — a place to filter around (the feeds are global; lat/lon of the place makes distance filtering honest)
  • The window — "just now" (past hour feed), today, this week
  • The threshold — significant-only vs. everything-they-can-feel (M2.5+) vs. research-grade (all)

Framework: The Feed Matrix and the Framing

  1. The feeds — https://earthquake.usgs.gov/earthquakes/feed/v1.0/summary/{mag}_{window}.geojson where mag ∈ significant, 4.5, 2.5, 1.0, all and window ∈ hour, day, week, month. "Just felt something" → 2.5_hour; "big ones today" → 4.5_day. Each feature: properties.mag, .place, .time (epoch ms), .url (event page), geometry.coordinates = [lon, lat, depth km].
  2. Targeted queries beat feed-filtering for specific regions: https://earthquake.usgs.gov/fdsnws/event/1/query?format=geojson&latitude=35.68&longitude=139.69&maxradiuskm=300&starttime=2026-07-17&minmagnitude=3 — the fdsnws endpoint takes radius, time, magnitude bounds directly.
  3. Magnitude bands, stated with every event: <3 rarely felt · 3–4 felt, no damage · 4–5 felt widely, minor damage possible near epicenter · 5–6 damage possible in built-up areas · 6–7 serious damage potential · 7+ major. Depth modifies everything: a shallow (<20km) M5 outfeels a 200km-deep M6 — say both numbers together.
  4. Times get converted: feed times are epoch UTC; the answer speaks the user's local time ("14 minutes ago, 03:12 local").
  5. The safety line: for "should I worry / is a bigger one coming" — aftershock probabilities and tsunami assessments belong to official agencies; link the event's USGS page and name the authoritative sources (national geological survey, tsunami warning centers) instead of improvising reassurance or alarm.
Show full SKILL.md (214 more words)Show less

Output Format

Earthquakes: [region] — [window]

[The direct answer: "Yes — M4.7, 22km deep, 38km NE of [place], 14 min ago" or "No M2.5+ events near [place] in the past [window]."]

Time (local)MagDepthLocationUSGS link

[Context band for the notable event(s) · aftershock/official-guidance line when safety is in the air]

Source: USGS real-time feeds · rerun: [exact curl] Informational — for safety decisions follow official emergency guidance, not this summary.

Quality Checks

  • The direct yes/no answer leads before any table
  • Depth appears next to magnitude on every quoted event
  • Times are converted to the user's local zone with the relative offset
  • Regional questions used radius filtering, not eyeballed global feeds
  • Safety-shaped questions route to official sources by name

Anti-Patterns

  • Do not answer from memory — seismicity is the definition of live data; fetch or hand over the command
  • Do not quote magnitude without depth — half the felt-intensity story
  • Do not predict aftershocks or all-clears — that's official-agency territory, linked not imitated
  • Do not present the global significant feed as "nothing near you" — filter by place before saying no
  • Do not dramatize small events or shrug at large ones — the bands calibrate the tone

Example Trigger Phrases

  • "Was there an earthquake just now?"
  • "Any recent quakes near Tokyo?"
  • "Were there any big earthquakes today?"
  • "Monitor seismic activity near me."

© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/earthquake-watch of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Earthquake Watch next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Earthquake Watch compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Earthquake Watch this skillmohitagw15856/pm-claude-skills1.4k—~1.2kAutomated safety check: PassMIT
Pp Usgs Earthquakesmvanhorn/printing-press-library2.1k—~4.4kAutomated safety check: NotesApache-2.0
OmniRoute API Keysdiegosouzapw/OmniRoute75k—~1.4kAutomated safety check: PassMIT
Watchgooseworks-ai/goose-skills1.2k1 repos~1.1kAutomated safety check: PassMIT
Canary Watchaffaan-m/ECC277k1 repos~770Automated safety check: PassMIT
Canary Watchaffaan-m/ECC276k—~405Automated safety check: PassMIT

Similar skills

  • Pp Usgs Earthquakes

    mvanhorn/printing-press-library

    Every USGS earthquake feed and event query in one terminal, with offline SQLite cache, agent-native output, and a...

    2.1k GitHub stars~4.4k tokensUpdated yesterday
    DatabasesAuto-check: notes
  • OmniRoute API Keys

    diegosouzapw/OmniRoute

    Documents the OmniRoute REST endpoints for creating, listing, updating, regenerating and deleting API keys, with per-key scopes, spending limits, expiry and device lists.

    75k GitHub stars~1.4k tokensUpdated today
    Backend & APIsAuto-check passed
  • Watch

    gooseworks-ai/goose-skills

    Watch a rendered video (whole file or specific ranges) at a chosen fidelity and emit a timestamp-keyed observation report.

    1.2k GitHub starsUsed in 1 repo~1.1k tokens
    Media & CreativeAuto-check passed
  • Canary Watch

    affaan-m/ECC

    A skill your agent uses to monitor and verify a deployed URL after releases — checks HTTP endpoints, SSE streams, static assets, console errors, and performance regressions after deploys, merges, or…

    277k GitHub starsUsed in 1 repo~770 tokens
    DevOps & CloudAuto-check passed
  • Canary Watch

    affaan-m/ECC

    このスキルを使用して、デプロイメント、マージ、または依存関係アップグレード後にデプロイされたURLの回帰を監視します. An agent skill from affaan-m/ECC.

    276k GitHub stars~405 tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Canary Watch

    affaan-m/ECC

    使用此技能在部署、合并或依赖升级后监控已部署的URL是否存在回归问题。

    276k GitHub stars~414 tokensUpdated yesterday
    DevOps & CloudAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated 2 days ago
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated 2 days ago
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed

Questions about Earthquake Watch

What does Earthquake Watch do?

Check recent earthquakes worldwide with zero API keys — USGS real-time GeoJSON feeds via curl, filtered by magnitude, region, and time window. Earthquake Watch is an agent skill from mohitagw15856/pm-claude-skills. Check recent earthquakes worldwide with zero API keys — USGS real-time GeoJSON feeds via curl, filtered by magnitude, region, and time window.

When should I use Earthquake Watch?

Earthquake Watch fits situations like: asked was there an earthquake just now; recent quakes near a place; any big earthquakes today; monitor seismic activity somewhere.

How do I install Earthquake Watch in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill earthquake-watch -a claude-code`. Or copy the skill folder (skills/earthquake-watch in mohitagw15856/pm-claude-skills) into .claude/skills/earthquake-watch in your project. Claude Code loads it when a task matches its description.

How do I install Earthquake Watch in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill earthquake-watch -a codex`. Or copy the skill folder (skills/earthquake-watch in mohitagw15856/pm-claude-skills) into .agents/skills/earthquake-watch in your project. Codex loads it when a task matches its description.

Can I use Earthquake Watch in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mohitagw15856/pm-claude-skills --skill earthquake-watch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/earthquake-watch, .gemini/skills/earthquake-watch, .github/skills/earthquake-watch and .opencode/skills/earthquake-watch in your project.

What does Earthquake Watch need to run?

SKILL.md names no scripts, command-line tools or credentials: Earthquake Watch is instructions for the agent only.

Does Earthquake Watch access the network?

SKILL.md names 1 domain. In commands or code: earthquake.usgs.gov; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Earthquake Watch safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Earthquake Watch use?

Earthquake Watch is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Earthquake Watch use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Earthquake Watch?

Skills that share tags, products or a category with Earthquake Watch: Pp Usgs Earthquakes (mvanhorn/printing-press-library, 2.1k stars), OmniRoute API Keys (diegosouzapw/OmniRoute, 75k stars), Watch (gooseworks-ai/goose-skills, 1.2k stars) and Canary Watch (affaan-m/ECC, 277k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Earthquake Watch?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.