# Newsletter signal scanner Human Guide

## What This Is For
Turn your newsletter subscriptions into a structured intelligence feed. It gives the agent a clearer input/output frame for email marketing: what context to ask for, what decisions to make, and what usable artifact to return.

Use this as a human-readable version of the Newsletter signal scanner agent skill. It is meant for marketers, operators, founders, and other non-coders who want the workflow without reading agent-specific implementation instructions.

## When To Use This
- Use this when you need a repeatable process for newsletter signal scanner.
- Use this when the task needs judgment, examples, constraints, or a clear output format rather than a one-off prompt.
- Use this when you want to hand an AI assistant enough context to produce a usable marketing artifact.

## When Not To Use This
- Do not use this when you only need a quick factual answer.
- Do not use this when the work depends on private data you cannot share with the assistant.
- Do not use this as a replacement for legal, compliance, financial, or medical review.

## What You Need Before Starting
- The goal or business outcome you want.
- The audience, customer segment, or market context.
- Any source material the assistant should respect, such as notes, briefs, examples, URLs, or brand guidance.
- Constraints such as tone, length, channel, deadline, region, or approval requirements.
- A clear definition of what a good final answer should look like.

## Step-By-Step Workflow
1. State the job clearly: "Use the Newsletter signal scanner guide to help me with..."
2. Add context: audience, goal, offer, channel, source material, and constraints.
3. Ask the assistant to identify missing inputs before producing the final output.
4. Have the assistant follow the skill-specific guidance below.
5. Review the result against the final checklist and ask for revisions where needed.

## Skill-Specific Guidance
- "Monitor industry newsletters for competitor mentions"
- "Alert me when newsletters mention [topic] or [company]"
- "What are newsletters writing about this week in our space?"
- "Set up newsletter monitoring for [client]"
- Which newsletters should be subscribed to and monitored? (List names or URLs)
- If unknown, ask: "What 3-5 newsletters does your ICP read?" — then use `sponsored-newsletter-finder` to discover others.
- Which AgentMail inbox should receive them? (Or should we create a new one?)
- Competitor names to track (e.g., "Clay", "Apollo", "Outreach")
- ICP pain-language terms to track (e.g., "outbound struggling", "pipeline dried up", "SDR ramp")
- Market shift terms (e.g., "AI SDR", "agent-led growth", "GTM engineer")
- Your brand name (to catch mentions)
- Digest delivery: Slack channel, email, or markdown file? (default: markdown file)

## Decision Points And Nuance
The original skill emphasizes: When to Use, Phase 0: Intake, Newsletters to Monitor, Keyword Campaigns, Output, Phase 1: Scan Inbox, Phase 2: Apply Keyword Campaigns, Phase 3: Extract Signal Snippets, Phase 4: Output Format, Summary.

Use these questions to steer the work:
- What is the intended audience or buyer?
- What source material must be preserved?
- What should the assistant optimize for: clarity, persuasion, accuracy, speed, creativity, or conversion?
- What examples represent the desired quality bar?
- What should the assistant avoid?

## Common Mistakes
- Starting without a clear audience or goal.
- Asking for a final artifact before sharing examples or constraints.
- Accepting a generic first draft without checking it against the intended use.

## Copy-And-Paste Prompt
```text
Use the Newsletter signal scanner human guide.

My goal:
[Describe the business outcome]

Audience:
[Describe who this is for]

Context and source material:
[Paste notes, examples, links, or existing copy]

Constraints:
[Tone, length, channel, timeline, must-include items, must-avoid items]

Before producing the final output, ask me for any missing information that would materially improve the result.
```

## Final Checklist
- [ ] The output matches the original goal.
- [ ] The audience and context are reflected in the answer.
- [ ] Important constraints and source material were preserved.
- [ ] The assistant made the relevant decisions explicit.
- [ ] The final artifact is ready to use, review, or hand to the next person.

## Source
This guide was generated from the gooseworks-ai/goose-skills skill entry for `newsletter-signal-scanner`.

## Source Skill Notes
These notes preserve the nuance from the original skill. Use them as supporting reference when the workflow above feels too generic.

# Newsletter Signal Scanner

Turn your newsletter subscriptions into a structured intelligence feed. Monitors an AgentMail inbox for incoming newsletters, extracts signal-relevant content by keyword campaign, and delivers a weekly digest of what matters — competitor mentions, ICP pain language, market shifts, and emerging topics.

## When to Use

- "Monitor industry newsletters for competitor mentions"
- "Alert me when newsletters mention [topic] or [company]"
- "What are newsletters writing about this week in our space?"
- "Set up newsletter monitoring for [client]"

## Phase 0: Intake

### Newsletters to Monitor
1. Which newsletters should be subscribed to and monitored? (List names or URLs)
   - If unknown, ask: "What 3-5 newsletters does your ICP read?" — then use `sponsored-newsletter-finder` to discover others.
2. Which AgentMail inbox should receive them? (Or should we create a new one?)

### Keyword Campaigns
3. Competitor names to track (e.g., "Clay", "Apollo", "Outreach")
4. ICP pain-language terms to track (e.g., "outbound struggling", "pipeline dried up", "SDR ramp")
5. Market shift terms (e.g., "AI SDR", "agent-led growth", "GTM engineer")
6. Your brand name (to catch mentions)

### Output
7. Digest delivery: Slack channel, email, or markdown file? (default: markdown file)
8. Frequency: daily or weekly? (default: weekly)

Save campaign config to the current working directory as `newsletter-signals.json` (or user-specified path).

```json
{
  "inbox_id": "<agentmail_inbox_id>",
  "keyword_campaigns": {
    "competitors": ["Clay", "Apollo", "Outreach", "Salesloft"],
    "pain_language": ["pipeline is down", "outbound isn't working", "SDR ramp"],
    "market_shifts": ["AI SDR", "GTM engineer", "agent-led"],
    "brand_mentions": ["YourCompany", "yourcompany.com"]
  },
  "newsletters": [
    {"name": "Exit Five", "from_domain": "exitfive.com"},
    {"name": "The GTM Newsletter", "from_domain": "gtmnewsletter.com"}
  ],
  "output": {
    "format": "markdown",
    "path": "newsletter-signals-[DATE].md"
  }
}
```

## Phase 1: Scan Inbox

Use the AgentMail API (agentmail.dev) to fetch new emails from the monitored inbox:

```
Fetch emails from inbox <inbox_id> since <last_scan_date>
Filter to: known newsletter senders (match against newsletters config)
```

For each email:
- Extract subject, sender, date, full body text
- Strip HTML → plain text for analysis

## Phase 2: Apply Keyword Campaigns

For each newsletter email, scan for keyword matches:

```python
for email in emails:
    matches = {}
    for campaign, keywords in keyword_campaigns.items():
        found = []
        for keyword in keywords:
            if keyword.lower() in email.body.lower():
                # Extract context: 50 chars before + keyword + 50 chars after
                context = extract_context(email.body, keyword)
                found.append({"keyword": keyword, "context": context})
        if found:
            matches[campaign] = found
    email.signal_matches = matches