Find agent skills by outcome

before asking

and specifies exact question to ask if needed

- Added soft length guidance per section (1–3 sentences

2–4 sentences

- Clarified that section 7 (Spot It In the Wild) covers only real-time

in-the-moment

- Supports X/Twitter

Facebook

length targets

structure

- No vague protective advice (e.g.

stay vigilant

- No hype

no scare tactics

Coding & Debugging

- After the codeblock

one short line is fine if clarification is needed

- Never force it. If it feels awkward

leave it out.

- Professional but plain tone — not corporate

not stiff

- Short paragraphs

no walls of text

- 3–5 hashtags at the end

kept on their own line

- Hashtags: 2–3 max

placed at the end

- No long paragraphs — short

punchy sentences only

- If a thread would help

offer 2–3 numbered tweets as an option

Marketing

After the Exposure Context section

offer the user the ability to share any of the three scams as a ready-to-post social media update.

When the user selects a scam and platform

generate the post using the rules below.

Want to share one of these scam alerts? I can format any of them as a ready-to-post for X/Twitter

Facebook

Data

- If no reliable data supports a rating

label the assessment as Qualitative Estimate.

After listing all three scams

include:

For each scam

include:

— Focus only on what is visible or testable in the moment: the message

call

— 3–5 sentences or bullets. Specific actions

specific reporting channels. Name them.

• Links

attachments