get-earthquake-feed

usgs.gov/get-earthquake-feed-luuaup · updated May 21, 2026

MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.

$browse install usgs.gov/get-earthquake-feed-luuaup
0 commentsdiscussion
summary

Fetch recent earthquakes from the USGS Earthquake Hazards Program (summary feed, FDSN query, or single event ID) and return them as normalized structured JSON with magnitude, location, depth, intensity, alert level, tsunami flag, significance, status, and canonical event URL.

skill.md
name
get-earthquake-feed
title
USGS Earthquake Feed
description
>- Fetch recent earthquakes from the USGS Earthquake Hazards Program (summary feed, FDSN query, or single event ID) and return them as normalized structured JSON with magnitude, location, depth, intensity, alert level, tsunami flag, significance, status, and canonical event URL.
website
usgs.gov
category
geoscience
tags
- earthquakes - usgs - geojson - fdsn - seismic - geoscience - public-api
source
'browserbase: agent-runtime 2026-05-18'
updated
'2026-05-18'
recommended_method
api
alternative_methods
- method: browser rationale: >- The earthquake.usgs.gov web UI (map, list, and per-event pages) is a thin client over the same GeoJSON the API returns. Browser scraping would re-derive the same fields at ~100x the cost and latency, and the JSON API has no auth, no anti-bot, and permissive CORS. Only fall back to browser when the API is unreachable for network-policy reasons on the calling side.
verified
false
proxies
false

USGS Earthquake Feed

Purpose

Fetch recent earthquakes from the USGS Earthquake Hazards Program and return them as normalized, structured JSON. Supports four input shapes — a canonical summary-feed URL, a {magnitude, period} bucket, an FDSN query (bounding box / radius / time range / magnitude / depth / event-type / alert / review-status), or a single USGS event ID — and emits one row per event with magnitude, place, origin time, lat/lon, depth, intensity, alert level, tsunami flag, significance, status, event type, and the canonical eventpage URL. Read-only.

When to Use

  • Building a real-time / near-real-time earthquake monitor over a region or magnitude threshold.
  • Backfilling a historical catalog for a bounding box or epicenter radius.
  • Looking up a single event's full detail by USGS event ID (us7000abcd, nc73831706, etc.).
  • Replacing screen-scraping of earthquake.usgs.gov/earthquakes/map/ — the underlying GeoJSON is the same data the map is rendered from, and it is faster, structurally typed, and free.
  • Cross-checking another seismic source (EMSC, JMA, GEOFON) against the canonical USGS reading.

Workflow

The USGS Earthquake Hazards Program publishes two stable, public, no-auth HTTP surfaces that return GeoJSON: the Earthquake Catalog summary feeds (CDN-cached, fixed pre-built buckets, updated ~1 min) and the FDSN Event Service (parameterized query, updated continuously). The web UI at earthquake.usgs.gov/earthquakes/map/ and the per-event pages at earthquake.usgs.gov/earthquakes/eventpage/{id} are thin clients over these endpoints — always hit the API directly. No API key, no cookies, no Referer, no User-Agent gating beyond a "please identify your client" courtesy convention. CORS is permissive; no residential proxy needed.

Pick the correct endpoint for the input shape, fetch GeoJSON, then map features[*].properties + features[*].geometry.coordinates + features[*].id to the normalized row schema in Expected Output.

1. Direct summary-feed URL passthrough

If the caller hands you a URL that already matches https://earthquake.usgs.gov/earthquakes/feed/v1.0/summary/{magnitude}_{period}.geojson, fetch it as-is. No transformation. Validate that {magnitude} ∈ {significant, 4.5, 2.5, 1.0, all} and {period} ∈ {hour, day, week, month} before sending — anything else is a 404.

2. {magnitude, period} bucket → summary feed

Build the URL by template:

https://earthquake.usgs.gov/earthquakes/feed/v1.0/summary/{magnitude}_{period}.geojson

Valid combinations are the Cartesian product of the two enums, so there are exactly 20 summary feeds. significant_hour, 4.5_day, 2.5_week, 1.0_month, all_hour, etc. These are pre-built and CDN-cached; they are the fastest path when the bucket fits.

3. Bounding box / radius / arbitrary filter → FDSN Event Service

GET https://earthquake.usgs.gov/fdsnws/event/1/query
    ?format=geojson
    &starttime=2026-05-11T00:00:00Z
    &endtime=2026-05-18T00:00:00Z
    &minlatitude=32.0&maxlatitude=42.0
    &minlongitude=-125.0&maxlongitude=-114.0
    &minmagnitude=2.5
    &orderby=time
    &limit=2000

Bounding box uses the four min/max{latitude,longitude} params; antimeridian-crossing boxes are supported via minlongitude < -180 or maxlongitude > 180. Radius search uses latitude=<lat>&longitude=<lon>&maxradiuskm=<km> (or maxradius=<deg>) with optional minradiuskm / minradius. Combine with any of the time / magnitude / depth / event-type / alert / review-status / pagination filters listed in Supported FDSN parameters below.

The FDSN service caps a single response at 20,000 features; if the caller's filter could exceed that, set limit and paginate with offset (1-based, default 1). Use orderby=time-asc for forward pagination so newly-arrived events don't shift the offset.

4. Single event ID → detail GeoJSON

GET https://earthquake.usgs.gov/fdsnws/event/1/query?eventid={id}&format=geojson

Returns a single Feature (not a FeatureCollection — the type is "Feature" and there is no features[] array). The shape is otherwise identical to a summary-feed feature, plus a properties.products object containing every contributed scientific product (origin, phase-data, shakemap, dyfi, losspager, focal-mechanism, moment-tensor, finite-fault, …). For the row schema in Expected Output, you only need the top-level properties + geometry + id; the products block is optional enrichment.

eventid is what USGS calls the event's authoritative id (e.g. us7000abcd, nc73831706, ci40624479). Non-authoritative aliases are listed in properties.ids (a comma-padded string like ,us7000abcd,at00rxxxxx,) — any of them will resolve via the same endpoint.

5. Map GeoJSON → row schema

For each feature (or the single feature in step 4), build a row:

event_id       = feature.id
magnitude      = feature.properties.mag                            # number, may be null
mag_type       = feature.properties.magType                        # "Mw" | "Md" | "Ml" | "Mb" | "mww" | "mb" | ...
place          = feature.properties.place                          # "5km W of Volcano, Hawaii"
origin_time    = new Date(feature.properties.time).toISOString()   # epoch ms → ISO 8601 UTC
updated_time   = new Date(feature.properties.updated).toISOString()
latitude       = feature.geometry.coordinates[1]
longitude      = feature.geometry.coordinates[0]
depth_km       = feature.geometry.coordinates[2]                   # km positive down; may be < 0 for shallow
felt_count     = feature.properties.felt                           # DYFI report count, integer | null
cdi            = feature.properties.cdi                            # Community Decimal Intensity 0-10 | null
mmi            = feature.properties.mmi                            # Modified Mercalli Instrumental 0-10 | null
alert_level    = feature.properties.alert                          # "green" | "yellow" | "orange" | "red" | null
tsunami_flag   = feature.properties.tsunami === 1                  # 0 / 1 → boolean
significance   = feature.properties.sig                            # integer 0..1000
status         = feature.properties.status                         # "automatic" | "reviewed"
event_type     = feature.properties.type                           # "earthquake" | "quarry blast" | "explosion" | "ice quake" | "rock burst" | "sonic boom" | "nuclear explosion" | "mine collapse" | "other event"
event_url      = feature.properties.url                            # canonical eventpage URL on earthquake.usgs.gov

Coordinate order is [lon, lat, depth_km] — GeoJSON spec. Swapping lat/lon is the most common bug. Depth is km positive down; very shallow events can report negative values (event above the WGS84 reference surface — usually a calibration artifact, occasionally a real shallow explosion).

Supported FDSN parameters

Pass-through these to /fdsnws/event/1/query — document every one in the skill's parameter surface so callers don't reinvent them:

ParamTypeNotes
formatenumgeojson (use this), xml (QuakeML), csv, text, kml, quakeml. Default xml. Always send format=geojson — it's the only format the row mapper above is calibrated for.
starttimeISO 8601UTC. Default = current time − 30 days.
endtimeISO 8601UTC. Default = present.
updatedafterISO 8601Filter to events whose record was updated after this instant (good for incremental polls).
minlatitude, maxlatitudefloat (-90..90)Bounding box.
minlongitude, maxlongitudefloat (-360..360)Bounding box. Antimeridian: allowed to exceed ±180 on one side.
latitude, longitudefloatCenter for radius search. Required together.
maxradiusfloat (degrees, 0..180)Radius search, degrees.
maxradiuskmfloat (km, 0..20001.6)Radius search, kilometers. Use this unless you have a reason for degrees.
minradius / minradiuskmfloatInner radius (annulus search).
mindepth, maxdepthfloat (km)Depth range, km positive down. Allowed range ≈ -100..1000.
minmagnitude, maxmagnitudefloatInclusive bounds.
magnitudetypestringFilter to a specific mag type (Mw, mww, Mb, Ml, Md, …). Default = any.
eventtypestringearthquake, quarry blast, explosion, ice quake, mining explosion, nuclear explosion, rock burst, sonic boom, mine collapse, other event. Default = any.
reviewstatusenumautomatic or reviewed. Omit for both.
alertlevelenumgreen, yellow, orange, red.
mincdifloatFilter by Community Internet Intensity (DYFI).
minmmifloatFilter by instrumental Modified Mercalli.
minfeltintFilter by DYFI report count.
minsig, maxsigint (0..1000)PAGER/origin significance score.
producttypestringFilter to events that have a specific product attached (e.g. shakemap, dyfi, losspager, moment-tensor, focal-mechanism, finite-fault, phase-data).
contributorstringNetwork code of the contributing seismic network (us, ak, ci, nc, nn, hv, pr, uu, uw, …).
catalogstringCatalog name (us, ak, ci, …). Subtly different from contributor — see gotcha below.
eventidstringSingle-event lookup (mutually exclusive with the filter surface).
includealloriginsboolInclude all contributed origin solutions in products (detail mode).
includeallmagnitudesboolSame for magnitudes.
includesupersededboolInclude superseded products in detail responses.
includedeletedboolInclude deleted events (false by default; rarely useful).
orderbyenumtime (default, newest first), time-asc, magnitude (largest first), magnitude-asc.
limitint (1..20000)Page size.
offsetint (≥ 1, 1-based)Page offset. Default 1.
jsonerrorboolWhen true, return error responses as JSON instead of the default HTML/text. Always send jsonerror=true so error parsing is deterministic.

The full canonical reference is at https://earthquake.usgs.gov/fdsnws/event/1/ (with an interactive form at …/event/1/) and the FDSN-WS spec at https://www.fdsn.org/webservices/.

Site-Specific Gotchas

  • GeoJSON coordinate order is [lon, lat, depth_km] — not [lat, lon]. Most common bug; latitude is coordinates[1]. Depth is coordinates[2], km positive down; the very rare negative depth is "above the WGS84 reference" (calibration artifact or shallow explosion), not malformed data — pass it through.
  • properties.time and properties.updated are epoch milliseconds, not seconds and not ISO strings. new Date(p.time) works directly in JS; in Python use datetime.fromtimestamp(p.time/1000, tz=timezone.utc). Treating it as seconds yields years like 1970.
  • properties.mag and properties.magType can be null — most commonly on quarry blast / mining explosion / nuclear explosion event types and on extremely new automatic locations where a magnitude solution hasn't been computed yet. Don't assume non-null; emit null downstream.
  • mag is a single contributor's preferred magnitude — the FDSN service returns one origin's mag in the summary, but USGS may publish multiple magnitude solutions per event (Mw, Mww, Mb, mb, Ml, Md). For a single event, &eventid=...&includeallmagnitudes=true returns the full set under properties.products["origin"][*].properties and properties.products["moment-tensor"][*]. The summary feeds and bulk FDSN queries only carry the preferred one.
  • status: "automatic" events get revised. Anything in the first 5-15 minutes after origin is status=automatic and the magnitude, depth, and even the location can shift by tens of km / 0.5+ mag units when a human analyst reviews it (typically minutes to hours later, sometimes a day or two for small events). If you care about ground truth, only emit status=reviewed rows, or re-poll with &updatedafter=<lastSeen> and re-emit changed events.
  • type is not always earthquake. The FDSN catalog also publishes quarry blasts, mine collapses, sonic booms, ice quakes, rock bursts, and nuclear/chemical explosions. The all_* summary feeds and unfiltered FDSN queries include them. If the caller wants only natural earthquakes, send eventtype=earthquake — filtering client-side works too but wastes bandwidth.
  • **significance score (sig)** is USGS's PAGER + felt + magnitude heuristic, integer 0..1000. The significant_*summary feeds correspond tosig ≥ 600`. Don't conflate with magnitude.
  • alert (PAGER alert level) is rare. It's only populated for events large enough to trigger a PAGER loss estimate (roughly M5.5+ globally, lower in populated areas). Most events have alert: null. The four valid non-null values are green, yellow, orange, red (lowercase strings).
  • tsunami: 1 is a flag, not a forecast. USGS sets it when the event meets the regional tsunami-warning-center notification criteria (typically M ≥ 7.0 + shallow + offshore). It does not mean a tsunami occurred or was forecast. Authoritative tsunami information comes from NOAA/PTWC/NTWC, not this field. Surface the boolean honestly.
  • felt (DYFI report count) lags origin by minutes to hours. Brand-new events almost always show felt: null even when they're widely felt; the field populates as users submit "Did You Feel It?" reports. Re-poll the event 1 hr later if felt_count matters.
  • cdi vs mmicdi is the Community Decimal Intensity derived from DYFI reports (crowdsourced, lags origin); mmi is the Modified Mercalli Intensity derived from ShakeMap instrumental + interpolation (lags ~15-60 min after origin, only computed for events that trigger ShakeMap, roughly M ≥ 3.5 in CA / M ≥ 4.5 globally). Either or both may be null; they are not interchangeable.
  • net + code is a stable composite id, separate from the authoritative id. id = net + code in the common case (us + 7000abcd = us7000abcd), but events that are reassigned to a different authoritative network keep their old id and the new network's code in properties.ids (a comma-padded string). The eventid query param accepts any id in properties.ids.
  • catalog vs contributor distinction: contributor is the seismic network that submitted an origin solution; catalog is the network whose origin USGS chose as authoritative. They are usually equal but can differ — e.g. an event in Northern California where nc (Northern California Seismic System) is authoritative may also be contributed by us (USGS National Earthquake Information Center). Filtering by contributor=us will miss events authoritatively assigned to a regional network. Prefer catalog= for "events authoritatively from this network" and omit both for "all events in the region regardless of who reports them."
  • -360 ≤ longitude ≤ 360 for antimeridian-crossing bounding boxes. A box covering Fiji / New Zealand / the Aleutians needs e.g. minlongitude=170&maxlongitude=200 (or -190 to -160); the service handles the wrap.
  • 20,000-feature hard cap per FDSN response. Anything past that returns an error. Paginate with limit + offset, and use orderby=time-asc (oldest first) for forward incremental polls so newly-arrived events append at the tail rather than shifting all offsets.
  • Summary feeds are CDN-cached ~60s. A query that just ran one second ago and a query that runs now may return the same response from the CDN. For ≤ 1-minute latency, hit the FDSN service directly with starttime=<now − N minutes>.
  • FDSN time query precision is seconds (UTC). Sub-second starttime values are silently truncated. Don't rely on millisecond windowing.
  • includesuperseded=true returns every revision of every origin/magnitude product, including ones that were later retracted. Don't enable it unless you specifically want revision history; for current-state queries it inflates the response 3-10×.
  • jsonerror=true is opt-in. Without it, an invalid parameter returns an HTTP 400 with a plain-text or HTML body that's painful to parse programmatically. Always send jsonerror=true.
  • No auth, no API key, no rate limit headers — but be polite: send a meaningful User-Agent (e.g. your-org/1.0 ([email protected])), and don't burst > 5-10 req/s sustained against the FDSN service. The Earthquake Catalog summary feeds are CDN-fronted and tolerate much higher rates because they're static-by-URL.
  • No CORS preflight issues. Access-Control-Allow-Origin: * on both endpoints; safe to call from a browser-side fetch with no proxy.
  • detail URL on summary-feed features points to the per-event GeoJSON (…/fdsnws/event/1/query?eventid=<id>&format=geojson), not to the human-facing event page. The human-facing URL is properties.url (…/earthquakes/eventpage/<id>). Don't conflate.
  • Event URLs are stable. https://earthquake.usgs.gov/earthquakes/eventpage/<id> will redirect to the current authoritative id if <id> is a superseded alias.

Expected Output

Two distinct response shapes — collection (summary feed or FDSN query) and single event.

Collection response

{
  "source": "summary_feed",
  "feed_id": "significant_week",
  "feed_url": "https://earthquake.usgs.gov/earthquakes/feed/v1.0/summary/significant_week.geojson",
  "fetched_at": "2026-05-18T14:32:11.812Z",
  "generated_at": "2026-05-18T14:31:00.000Z",
  "count": 7,
  "events": [
    {
      "event_id": "us7000abcd",
      "magnitude": 5.2,
      "mag_type": "mww",
      "place": "5km W of Volcano, Hawaii",
      "origin_time": "2026-05-18T11:14:32.430Z",
      "updated_time": "2026-05-18T11:48:01.120Z",
      "latitude": 19.4106,
      "longitude": -155.2741,
      "depth_km": 4.8,
      "felt_count": 312,
      "cdi": 5.1,
      "mmi": 4.6,
      "alert_level": "green",
      "tsunami_flag": false,
      "significance": 612,
      "status": "reviewed",
      "event_type": "earthquake",
      "event_url": "https://earthquake.usgs.gov/earthquakes/eventpage/us7000abcd"
    }
  ]
}

For an FDSN query response, source is "fdsn_query", feed_id is omitted, and the query string is echoed as query_url. Add next_offset when the response equals limit (signals possible pagination).

Single-event response

{
  "source": "fdsn_event_detail",
  "event_id": "us7000abcd",
  "fetched_at": "2026-05-18T14:32:11.812Z",
  "event": {
    "event_id": "us7000abcd",
    "magnitude": 5.2,
    "mag_type": "mww",
    "place": "5km W of Volcano, Hawaii",
    "origin_time": "2026-05-18T11:14:32.430Z",
    "updated_time": "2026-05-18T11:48:01.120Z",
    "latitude": 19.4106,
    "longitude": -155.2741,
    "depth_km": 4.8,
    "felt_count": 312,
    "cdi": 5.1,
    "mmi": 4.6,
    "alert_level": "green",
    "tsunami_flag": false,
    "significance": 612,
    "status": "reviewed",
    "event_type": "earthquake",
    "event_url": "https://earthquake.usgs.gov/earthquakes/eventpage/us7000abcd",
    "ids": ["us7000abcd", "at00rxxxxx", "hv73450123"],
    "contributor": "us",
    "catalog": "us",
    "products_available": ["origin", "phase-data", "shakemap", "dyfi", "losspager", "moment-tensor", "focal-mechanism"]
  }
}

Error / empty / not-found shapes

// FDSN query with valid params but zero matching events — NOT an error
{ "source": "fdsn_query", "count": 0, "events": [], "query_url": "..." }

// Single-event lookup, id does not exist
{ "source": "fdsn_event_detail", "event_id": "us0000bogus", "error": "event_not_found" }

// Caller-supplied bad combination (e.g. invalid magnitude bucket, mutually exclusive params)
{ "error": "invalid_parameters", "detail": "magnitude must be one of [significant, 4.5, 2.5, 1.0, all]" }

// FDSN service returned a hard error (with jsonerror=true)
{ "error": "fdsn_error", "http_status": 400, "detail": "<usgs error text>" }
how to use get-earthquake-feed

How to use get-earthquake-feed on Cursor

AI-first code editor with Composer

1

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

  • Cursor installed and configured on your development machine
  • Node.js version 16.0+ with npm package manager (verify with node --version)
  • Active project directory or workspace where you want to add get-earthquake-feed
2

Execute installation command

Execute the skills CLI command in your project's root directory to begin installation:

$browse install usgs.gov/get-earthquake-feed-luuaup

The skills CLI fetches get-earthquake-feed from GitHub repository usgs.gov/get-earthquake-feed-luuaup and configures it for Cursor.

3

Select Cursor when prompted

The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:

◆ Which agents do you want to install to?
│ ── Universal (.agents/skills) ── always included ────
│ • Amp
│ • Antigravity
│ • Cline
│ • Codex
│ ●Cursor(selected)
│ • Cursor
│ • Windsurf
4

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/get-earthquake-feed

Reload or restart Cursor to activate get-earthquake-feed. Access the skill through slash commands (e.g., /get-earthquake-feed) or your agent's skill management interface.

Security & Verification Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.

List & Monetize Your Skill

Submit your Claude Code skill and start earning

GET_STARTED →

Use Cases

Task Automation & Efficiency

Automate repetitive workflows and reduce manual effort

Example

Generate reports, summarize documents, draft communications

Save 3-5 hours per week on routine tasks

Knowledge Enhancement

Learn new skills, understand complex topics, get expert guidance

Example

Explain concepts, provide examples, suggest learning resources

Accelerate learning and skill development by 2x

Quality Improvement

Enhance output quality through reviews, suggestions, and refinements

Example

Review drafts, suggest improvements, catch errors

Improve work quality by 30-40% with less effort

Implementation Guide

Prerequisites

  • Claude Desktop or compatible AI client with skill support
  • Clear understanding of task or problem to solve
  • Willingness to iterate and refine outputs

Time Estimate

15-45 minutes depending on use case complexity

Installation Steps

  1. 1.Install skill using provided installation command
  2. 2.Test with simple use case relevant to your work
  3. 3.Evaluate output quality and relevance
  4. 4.Iterate on prompts to improve results
  5. 5.Integrate into regular workflow if valuable

Common Pitfalls

  • Expecting perfect results without iteration
  • Not providing enough context in prompts
  • Using skill for tasks outside its intended scope
  • Accepting outputs without review and validation

Best Practices

✓ Do

  • +Start with clear, specific prompts
  • +Provide relevant context and constraints
  • +Review and refine all outputs before using
  • +Iterate to improve output quality
  • +Document successful prompt patterns

✗ Don't

  • Don't use without understanding skill limitations
  • Don't skip validation of outputs
  • Don't share sensitive information in prompts
  • Don't expect skill to replace human judgment

💡 Pro Tips

  • Be specific about desired format and style
  • Ask for multiple options to choose from
  • Request explanations to understand reasoning
  • Combine AI efficiency with human expertise

When to Use This

✓ Use When

Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.

✗ Avoid When

Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.

Learning Path

  1. 1Familiarize yourself with skill capabilities and limitations
  2. 2Start with low-risk, non-critical tasks
  3. 3Progress to more complex and valuable use cases
  4. 4Build expertise through regular use and experimentation

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.842 reviews
  • Aisha Rahman· Dec 28, 2024

    Solid pick for teams standardizing on skills: get-earthquake-feed is focused, and the summary matches what you get after install.

  • Ava Iyer· Dec 24, 2024

    Keeps context tight: get-earthquake-feed is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Hassan Martinez· Dec 20, 2024

    Registry listing for get-earthquake-feed matched our evaluation — installs cleanly and behaves as described in the markdown.

  • William Farah· Nov 15, 2024

    get-earthquake-feed has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • Hassan Khan· Nov 11, 2024

    get-earthquake-feed reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Ava Okafor· Nov 11, 2024

    I recommend get-earthquake-feed for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Sakshi Patil· Nov 7, 2024

    Solid pick for teams standardizing on skills: get-earthquake-feed is focused, and the summary matches what you get after install.

  • Chaitanya Patil· Oct 26, 2024

    I recommend get-earthquake-feed for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • William Flores· Oct 6, 2024

    get-earthquake-feed fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

  • Noor Thomas· Oct 2, 2024

    get-earthquake-feed is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

showing 1-10 of 42

1 / 5