pp-usgs-earthquakes
Every USGS earthquake feed and event query in one terminal, with offline SQLite cache, agent-native output, and a... Trigger phrases: `any recent earthquakes`, `earthquakes near`, `aftershocks of`, `USGS earthquake feed`, `M5 earthquake`, `tsunami earthquake`, `swarm detection`, `use usgs-earthquakes`, `run usgs-earthquakes`.
What this skill does
<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/other/usgs-earthquakes/SKILL.md,
regenerated post-merge by tools/generate-skills/. Hand-edits here are
silently overwritten on the next regen. Edit the library/ source instead.
See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->
# USGS Earthquakes — Printing Press CLI
## Prerequisites: Install the CLI
This skill drives the `usgs-earthquakes-pp-cli` binary. **You must verify the CLI is installed before invoking any command from this skill.** If it is missing, install it first:
1. Install via the Printing Press installer. It defaults binaries to `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows:
```bash
npx -y @mvanhorn/printing-press-library install usgs-earthquakes --cli-only
```
2. Verify: `usgs-earthquakes-pp-cli --version`
3. Ensure the reported install directory is on `$PATH` for the agent/runtime that will invoke this skill.
If the `npx` install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.3 or newer):
```bash
go install github.com/mvanhorn/printing-press-library/library/other/usgs-earthquakes/cmd/usgs-earthquakes-pp-cli@latest
```
If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds.
## When to Use This CLI
Reach for this CLI any time an agent needs to answer questions about USGS earthquakes — recent activity, historical search, single-event detail, aftershock sequences, regional comparisons, or live monitoring. It is the right choice when speed matters (offline SQLite cache), when output must be agent-friendly (--json, --select, --compact, --csv on every command), or when the workflow spans multiple events that the raw FDSN API would require stitching together. Not the right choice for non-USGS seismic networks (IRIS event service, EMSC) or for waveform/station data — those need an FDSN station-service client like obspy.
## When Not to Use This CLI
Do not activate this CLI for requests that require creating, updating, deleting, publishing, commenting, upvoting, inviting, ordering, sending messages, booking, purchasing, or changing remote state. This printed CLI exposes read-only commands for inspection, export, sync, and analysis.
## Unique Capabilities
These capabilities aren't available in any other tool for this API.
### Real-time monitoring
- **`watch`** — Long-running poll of a USGS summary feed with deduplication against the local store. Invokes an optional shell hook per new event for custom alerting.
_Reach for this when you want a long-running monitor over USGS earthquakes without writing a polling loop. Pluggable shell hook means it composes with notify-send, Slack curl, paging systems, anything._
```bash
usgs-earthquakes-pp-cli watch --min-magnitude 5 --notify "echo {id}: {place}" --interval 60s
```
### Cross-event analysis
- **`aftershocks`** — Show events within R km and T days after a mainshock, ordered by time. Local SQLite haversine query with FDSN fallback when uncached.
_Reach for this any time you have a mainshock event ID and need to see what came after. The single-call alternative is dozens of /query invocations stitched in jq._
```bash
usgs-earthquakes-pp-cli aftershocks us7000abcd --radius-km 100 --days 30 --min-mag 3.0 --json
```
- **`swarm-detect`** — Detect time-space clusters in the local earthquake store. Grid-bucket clustering finds foreshock/aftershock sequences, volcanic swarms, and induced seismicity hotspots.
_Reach for this when monitoring a volcano, fault zone, or fracking region for unusual clustering. The output names each cluster with center, count, peak magnitude, and time range._
```bash
usgs-earthquakes-pp-cli swarm-detect --bbox -122.5,46.5,-121.5,47.5 --window 7d --min-events 10 --cluster-radius-km 20 --json
```
- **`compare`** — Side-by-side comparison of two regions or two time periods. Returns parallel columns with counts, max magnitude, and total seismic energy.
_Reach for this when answering 'is region A more active than region B?' or 'is this region quieter than it used to be?'. Outputs delta percentages and energy ratios._
```bash
usgs-earthquakes-pp-cli compare --region-a -122.5,37.5,-122.0,37.9 --region-b -118.5,33.8,-118.0,34.2 --window 30d --json
```
### Agent-native output
- **`brief`** — Agent-ready briefing for a single earthquake: magnitude, place, PAGER alert, DYFI felt count, ShakeMap MMI, tsunami status, and product inventory.
_Reach for this in newsroom or Slack contexts where you need a one-event summary an editor or downstream agent can drop straight into copy. Includes the USGS event-page URL._
```bash
usgs-earthquakes-pp-cli brief us7000abcd --format markdown
```
- **`top`** — Rank recent events by composite editorial score: significance × alert weight × felt count × tsunami flag. Default window 24h, limit 10.
_Reach for this when you need 'the events that matter right now' rather than 'all events by magnitude'. The composite score promotes felt + PAGER + tsunami over raw magnitude._
```bash
usgs-earthquakes-pp-cli top --window 24h --limit 10 --score composite --json
```
### Local state that compounds
- **`changes`** — Diff since the last sync: what events appeared, what events had magnitudes/depths/alerts revised, what events were retracted. Tracks USGS solution revisions over time. Returns 'no revisions recorded yet' until at least two sync runs have completed.
_Reach for this when a previously-automatic event might have just been reviewed by an analyst (revising magnitude or alert), or to answer 'what's new since I last looked?'_
```bash
usgs-earthquakes-pp-cli changes --since 24h --type revised --min-mag-delta 0.3 --json
```
- **`decode-id`** — Parse a USGS event ID into its source network code, sequence, and operator name. Joins the cached contributors dictionary for the network display name.
_Reach for this when you see an opaque USGS event ID (e.g. nc73947885, ak0202xyz) and need to know which network reported it before reading the data._
```bash
usgs-earthquakes-pp-cli decode-id us7000abcd
```
## Command Reference
**catalogs** — USGS earthquake source catalogs (ANSS contributors and processing centers)
- `usgs-earthquakes-pp-cli catalogs` — List all source catalogs known to the FDSN Event service (XML response)
**contributors** — USGS earthquake data contributors
- `usgs-earthquakes-pp-cli contributors` — List all data contributors known to the FDSN Event service (XML response)
**events** — Search and retrieve earthquakes from the USGS FDSN Event service
- `usgs-earthquakes-pp-cli events count` — Count events matching the given filter, without returning event data (fast precheck before a full search)
- `usgs-earthquakes-pp-cli events get` — Fetch a single earthquake event by USGS event ID (e.g. us7000abcd)
- `usgs-earthquakes-pp-cli events search` — Search the USGS earthquake catalog with full FDSN parameter coverage
**feeds** — Pre-built GeoJSON earthquake summary feeds (updated every minute by USGS)
- `usgs-earthquakes-pp-cli feeds <feed>` — Fetch a named GeoJSON summary feed. Use one of: significant_{hour|day|week|month}, 4.5_{hour|day|week|month},...
**metadata** — FDSN Event service metadata: enumerated values for every parameter
- `usgs-earthquakes-pp-cli metadata` — Show enum dictionaries for catalogs, contributors, event types, product types, and magnitude types
### Finding the right command
When you know what you want to do but not which command does it, ask the CLI directly:
```bash
usgs-earthquakes-pp-cli which "<capability in your own words>"
```
`which` resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code `0` means at least one mRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.