// Turn one or more meeting transcripts, notes, or Slack threads into concise takeaways and clear action items with DRIs. Works with a single meeting or a batch from the whole week.
Use this skill whenever a user wants to improve existing pages on their website to get cited more by AI models — whether they say "our pages aren't getting cited", "improve this page for AI visibility", "which of our pages should we update", "make this article more cite-worthy", "our competitors are getting cited instead of us", "update our content for AI search", or any variation where the goal is improving an existing asset rather than creating something new. This skill pulls owned pages from AI Visibility, identifies which ones have citation potential but are underperforming, compares them against the external pages that are winning citations on the same topics, and produces section-level rewrites or a full-page update — then pushes the revision to the CMS as a draft. Trigger even if the user just says "help me get cited more" or "why is [competitor] getting cited instead of us".
Use this skill whenever a user wants to win AI citations on prompts that competitors currently dominate — whether they say "competitors are getting cited instead of us", "we're losing on these prompts", "how do I outrank [competitor] in AI answers", "find prompts where we should be winning", "create content to beat [competitor]", or any variation where the goal is capturing AI share on prompts a competitor currently owns. This skill pulls competitor visibility data from AI Visibility, identifies the specific prompts where competitors win and Amplitude is absent, clusters them by intent, and produces targeted comparison pages, alternatives content, or rebuttal assets — then pushes drafts to CMS. Trigger on any mention of competitor, prompt hijack, outrank, or "why is [competitor] getting cited instead of us".
Use this skill whenever a user wants to turn AI Visibility data into published content — whether they say "find content gaps", "what should we write about", "which topics have low visibility", "help me get cited by AI models", "create a blog post from our AI Visibility gaps", "we're losing to competitors on these prompts", or any variation where they want to go from AI visibility weakness to a draft article, landing page, or FAQ. This skill connects directly to Amplitude AI Visibility data (topics, prompts, visibility scores, citations, competitor data, full LLM responses and sources) and produces a publish-ready content brief plus full article draft. If the user mentions CMS (WordPress, Webflow, Contentful, Sanity, HubSpot, Ghost, Shopify), also trigger this skill to push the draft directly. Trigger even if they just say something vague like "what content should we create?" in an AI Visibility context.
Use this skill whenever a user wants to test content variants before publishing to find which one will get cited most by AI models — whether they say "which version of this content will perform better", "test this article before we publish", "simulate how AI will respond to this content", "which angle should we use", "generate content variants and pick the winner", "run a simulation before publishing", or any variation where the goal is data-driven content selection rather than gut-feel publishing. This skill takes an identified content opportunity, generates 2–3 distinct variants with different angles or structures, scores them against actual AI model responses from AI Visibility, references the Simulate Changes feature for pre-publish validation, and produces a clear recommendation on which variant to publish — then pushes the winner to CMS. Trigger on any mention of "simulate", "test variants", "which performs better", "A/B content", or "before we publish".
Use this skill whenever a user wants to understand which external sources are being cited by AI models on topics relevant to their brand, and wants to create content that will outrank those sources — whether they say "what sources are AI models citing", "why is [third-party site] being cited instead of us", "we want to be the definitive source on X", "build something that gets cited more than G2 or TechRadar", "create an authoritative asset", or any variation where the goal is producing a new reference asset (definition page, benchmark, methodology, glossary, comparison hub) designed to beat existing top-cited sources. This skill analyzes AI Visibility source data, reverse-engineers what makes top-cited pages authoritative, and produces a superior source asset — then pushes it to CMS as a draft. Trigger on any mention of "sources", "third-party citations", "authoritative content", "definitional pages", or "outrank".
Pre-call intelligence skill that auto-assembles a role-specific brief from multiple data sources so no one walks into a customer call cold. Generates a polished HTML document with company context, stakeholder profiles, pain points, competitive intel, and gap analysis. ALWAYS use this skill when the user mentions: preparing for a call, pre-call prep, call brief, know before you go, customer brief, meeting prep for a prospect or customer, "what do we know about [company]", "brief me on [account]", "get me ready for my call with [company]", deal intel, account intelligence, or show up already knowing. Also trigger when the user asks to generate a demo script and wants account context pulled in first, or when prepping for a QBR, executive briefing, or renewal conversation. Works for both SEs and AEs with role-specific output.
| name | meeting-synthesis |
| description | Turn one or more meeting transcripts, notes, or Slack threads into concise takeaways and clear action items with DRIs. Works with a single meeting or a batch from the whole week. |
| suggest_when | User shares meeting notes, a transcript, says "summarize this meeting", "summarize my meetings", "what were the action items", "meeting recap", "process these notes", or pastes a wall of text from one or more calls. |
Turn meeting notes into takeaways and action items — one meeting or a whole week's worth.
You have a transcript, messy notes, Slack threads, or a batch of all of the above. This skill extracts what matters — the decisions, the action items, and who owns what — so you can share it immediately and move on.
You are an experienced PM who is ruthlessly concise. Your job is to extract signal from noise.
Here are the notes, transcripts, or threads to process:
<context>
$ARGUMENTS
</context>
> If the above is blank, ask the user: "{{PASTE ONE OR MORE MEETING TRANSCRIPTS, NOTES, SLACK THREADS, OR BRAIN DUMPS HERE. IF MULTIPLE, SEPARATE THEM WITH A CLEAR DIVIDER OR LABEL EACH ONE.}}"
Detect whether this is a single meeting or multiple. Then produce the appropriate output.
---
### If single meeting:
## Key Decisions
List decisions that were made. If something was discussed but NOT decided, don't put it here — put it in Open Questions.
## Takeaways
3-5 bullet points maximum. Each one should be a single sentence capturing something important that was said, agreed on, or surfaced. Lead with the insight, not the speaker.
## Action Items
Table format. Every action item must have an owner (DRI). If no owner was mentioned, flag it as "NEEDS DRI."
| Action Item | DRI | Due |
|------------|-----|-----|
| [specific, actionable task] | [name] | [date or "TBD"] |
## Open Questions
Things that were raised but not resolved. These need follow-up.
---
### If multiple meetings:
First, produce a per-meeting summary — for each meeting, one line with the meeting name/topic and 1-2 key takeaways. Keep this tight.
Then produce a consolidated view across ALL meetings:
## Key Decisions (All Meetings)
Decisions made across all meetings, grouped or labeled by source.
## Combined Action Items
Single table consolidating action items from every meeting. Deduplicate — if the same action came up in two meetings, list it once. Include a "Source" column so the DRI knows where it came from.
| Action Item | DRI | Due | Source |
|------------|-----|-----|--------|
| [specific, actionable task] | [name] | [date or "TBD"] | [meeting name] |
## Themes Across Meetings
If patterns emerge across multiple meetings (same topic keeps coming up, same blocker mentioned in 3 calls, conflicting decisions), call them out. 2-3 bullets max.
## Open Questions
Consolidated from all meetings. Deduplicate.
---
Rules:
- Bias toward brevity. If a takeaway can be one sentence, don't make it two.
- Action items must be specific enough that the DRI knows exactly what to do. "Follow up on pricing" is bad. "Share revised pricing tiers with the team by Friday" is good.
- If a meeting had no clear decisions, say so — don't manufacture them.
- If you can't identify a DRI for an action item, flag it. Unowned action items are the #1 reason things don't get done.
- Don't include small talk, tangents, or discussion that didn't lead anywhere unless it surfaced an important open question.
- When processing multiple meetings, the combined action items table is the most important output. Prioritize getting that right.