Scan an AgentMail inbox for newsletter signals

Newsletter monitor

by gooseworks-ai · MIT license · ★ 1,220 on GitHub · updated Sep 21

Scan an AgentMail inbox for newsletter signals using configurable keyword campaigns. Extracts matched keywords, context snippets, and company mentions from incoming emails.

---
name: newsletter-monitor
description: >
  Scan an AgentMail inbox for newsletter signals using configurable keyword
  campaigns. Extracts matched keywords, context snippets, and company mentions
  from incoming emails. Use for monitoring accounting industry newsletters
  for buying signals like acquisitions, migrations, and staffing news.
---

# Newsletter Monitor

Scan an AgentMail inbox for newsletter signals using configurable keyword campaigns. Designed for monitoring accounting industry newsletters for buying signals like acquisitions, Sage Intacct migrations, staffing challenges, and technology adoption.

## Quick Start

```bash
# Set your API key
export AGENTMAIL_API_KEY="your_key_here"

Overview

Scan an AgentMail inbox for newsletter signals using configurable keyword campaigns. Designed for monitoring accounting industry newsletters for buying signals like acquisitions, Sage Intacct migrations, staffing challenges, and technology adoption.

Manual install (npx, ZIP)

Claude Codenpx skills add gooseworks-ai/goose-skills --skill newsletter-monitor -g -a claude-code

Claude Code (manual)

mkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/gooseworks-ai/goose-skills/tar.gz/615c685f34f8 \
  | tar -xz -C ~/.claude/skills --strip-components=4 goose-skills-615c685f34f8/skills/monitoring/composites/newsletter-monitor

Windows (PowerShell)

New-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/e58e0367747a905e557b/newsletter-monitor.zip" -OutFile "$env:TEMP\newsletter-monitor.zip"; Expand-Archive "$env:TEMP\newsletter-monitor.zip" -DestinationPath "$HOME\.claude\skills" -Force

Claude.ai / desktopDownload the ZIP and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md2.7 KB
skill.meta.json316 B
config/1 file · 858 B
scripts/1 file · 14.5 KB

Read the files here

gooseworks-ai/615c6854 files

SKILL.md

Show the full text77 lines

newsletter-monitor/SKILL.md77 lines · 2.7 KB

PreviewCode

Outline

RawView on GitHub

Quick Start

# Set your API key
export AGENTMAIL_API_KEY="your_key_here"

# Scan inbox with all campaigns (summary view)
python3 skills/newsletter-monitor/scripts/scan_newsletters.py --output summary

# Scan specific campaign, last 7 days
python3 skills/newsletter-monitor/scripts/scan_newsletters.py --campaign acquisitions --days 7 --output summary

# JSON output for downstream processing
python3 skills/newsletter-monitor/scripts/scan_newsletters.py --output json --limit 50

Dependencies

pip3 install agentmail python-dotenv

Configuration

Keyword campaigns are defined in config/campaigns.json. Each campaign has a description and a list of keywords for case-insensitive substring matching.

Built-in campaigns:

acquisitions - CPA firm M&A activity
sage_intacct - Sage Intacct migration and implementation signals
staffing - Accounting talent and staffing challenges
technology - Accounting technology adoption

CLI Options

Flag	Description	Default
`--campaign NAME`	Run only a specific campaign	All campaigns
`--days N`	Only scan emails from last N days	No limit
`--keywords "a,b,c"`	Custom keywords (overrides campaigns)	Use campaigns.json
`--output json\|summary`	Output format	`json`
`--inbox ADDRESS`	Override inbox address	`AGENTMAIL_INBOX` env or `[email protected]`
`--limit N`	Max messages to fetch	`100`

Output

JSON mode (default)

Returns an array of matched messages with:

message_id, from, subject, date
matched_campaigns - which campaigns triggered
matched_keywords - specific keywords found
context_snippets - 200-char window around each match
companies_mentioned - capitalized multi-word phrases near matches

Summary mode

Human-readable report showing matched emails grouped by campaign with snippets and detected companies.

Downstream Skills

When newsletter signals are found, chain to:

company-contact-finder - look up contacts at mentioned companies
accounting-news-monitor - combine with direct news monitoring for fuller signal coverage

1	---
2	name: newsletter-monitor
3	description: >
4	Scan an AgentMail inbox for newsletter signals using configurable keyword
5	campaigns. Extracts matched keywords, context snippets, and company mentions
6	from incoming emails. Use for monitoring accounting industry newsletters
7	for buying signals like acquisitions, migrations, and staffing news.
8	---
9
10	# Newsletter Monitor
11
12	Scan an AgentMail inbox for newsletter signals using configurable keyword campaigns. Designed for monitoring accounting industry newsletters for buying signals like acquisitions, Sage Intacct migrations, staffing challenges, and technology adoption.
13
14	## Quick Start
15
16	```bash
17	# Set your API key
18	export AGENTMAIL_API_KEY="your_key_here"
19
20	# Scan inbox with all campaigns (summary view)
21	python3 skills/newsletter-monitor/scripts/scan_newsletters.py --output summary
22
23	# Scan specific campaign, last 7 days
24	python3 skills/newsletter-monitor/scripts/scan_newsletters.py --campaign acquisitions --days 7 --output summary
25
26	# JSON output for downstream processing
27	python3 skills/newsletter-monitor/scripts/scan_newsletters.py --output json --limit 50
28	```
29
30	## Dependencies
31
32	```
33	pip3 install agentmail python-dotenv
34	```
35
36	## Configuration
37
38	Keyword campaigns are defined in `config/campaigns.json`. Each campaign has a description and a list of keywords for case-insensitive substring matching.
39
40	Built-in campaigns:
41	- acquisitions - CPA firm M&A activity
42	- sage_intacct - Sage Intacct migration and implementation signals
43	- staffing - Accounting talent and staffing challenges
44	- technology - Accounting technology adoption
45
46	## CLI Options
47
48	\| Flag \| Description \| Default \|
49	\|------\|-------------\|---------\|
50	\| `--campaign NAME` \| Run only a specific campaign \| All campaigns \|
51	\| `--days N` \| Only scan emails from last N days \| No limit \|
52	\| `--keywords "a,b,c"` \| Custom keywords (overrides campaigns) \| Use campaigns.json \|
53	\| `--output json\\|summary` \| Output format \| `json` \|
54	\| `--inbox ADDRESS` \| Override inbox address \| `AGENTMAIL_INBOX` env or `[email protected]` \|
55	\| `--limit N` \| Max messages to fetch \| `100` \|
56
57	## Output
58
59	### JSON mode (default)
60
61	Returns an array of matched messages with:
62	- `message_id`, `from`, `subject`, `date`
63	- `matched_campaigns` - which campaigns triggered
64	- `matched_keywords` - specific keywords found
65	- `context_snippets` - 200-char window around each match
66	- `companies_mentioned` - capitalized multi-word phrases near matches
67
68	### Summary mode
69
70	Human-readable report showing matched emails grouped by campaign with snippets and detected companies.
71
72	## Downstream Skills
73
74	When newsletter signals are found, chain to:
75	- company-contact-finder - look up contacts at mentioned companies
76	- accounting-news-monitor - combine with direct news monitoring for fuller signal coverage
77