skills/insights/SKILL.md
Surface findings, trends, and patterns from calls, emails, and deals. Use when user says "what are prospects saying", "common objections", "conversation trends", "field intelligence", "what patterns", or asks about aggregate conversation insights. Do NOT use for deal-level win/loss analysis — use /octave:wins-losses instead.
npx skillsauth add octavehq/lfgtm insightsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Surface insights from your sales conversations—objections, pain points, questions, and what's resonating. Learn from the field to improve your library and messaging.
/octave:insights [--type <finding-type>] [--period <time-range>]
--type <type> - Focus on specific finding type (objections, pain-points, questions, competitors, value-props)--period <range> - Time range (today, week, month, quarter, custom)--segment <name> - Filter by segment--persona <name> - Filter by persona--company <domain> - Filter by company/octave:insights # Overview of recent insights
/octave:insights --type objections # Top objections
/octave:insights --type pain-points --period month # Pain points this month
/octave:insights --persona "CTO" # Insights from CTO conversations
/octave:insights --company acme.com # Insights from Acme conversations
When the user runs /octave:insights:
If no options provided, show an overview:
What insights would you like to explore?
1. Overview - Summary across all finding types
2. Objections - What objections are prospects raising?
3. Pain Points - What problems are prospects mentioning?
4. Questions - What are prospects asking about?
5. Competitors - Which competitors are coming up?
6. Value Props - Which value props are resonating?
7. Custom - Specific filters
Your choice (or just ask a question):
Use the MCP tools to gather data:
For Overview:
# Get recent events
list_events({
eventTypes: ["CALL_TRANSCRIPT", "EMAIL_SENT", "EMAIL_REPLY_RECEIVED"],
dateRange: { start: "<30 days ago>", end: "<today>" },
limit: 50
})
# Get finding aggregates
list_findings({
extractionTypes: [
"CALL_EXTERNAL_OBJECTIONS",
"CALL_EXTERNAL_BUSINESS_PROBLEMS",
"CALL_EXTERNAL_QUESTIONS_OR_CONFUSION_ABOUT_OFFERING",
"CALL_EXTERNAL_COMPETITORS_TO_OUR_OFFERING",
"CALL_INTERNAL_VALUE_PROP_PRESENTATIONS"
],
dateRange: { start: "<30 days ago>", end: "<today>" },
groupBy: "extractionType",
limit: 100
})
For Specific Type (e.g., Objections):
list_findings({
extractionTypes: ["CALL_EXTERNAL_OBJECTIONS", "EMAIL_OBJECTION"],
dateRange: { start: "<period start>", end: "<period end>" },
limit: 50
})
With Persona/Segment Filter:
list_findings({
extractionTypes: ["<types>"],
entityMatches: {
personaOIds: ["<persona_oId>"]
},
limit: 50
})
See overview-output.md for the overview output template.
See objections-output.md for the objection-type output template.
When user wants to see specific events:
get_event_detail({
eventOId: "<event_oId>"
})
Present the full context:
EVENT DETAILS: Call with John Smith (Acme Corp)
===============================================
Date: January 15, 2026
Duration: 32 minutes
Participants:
- Internal: Sarah (AE), Mike (SE)
- External: John Smith (VP Ops), Lisa Chen (Director)
Matched Persona: VP Operations
Matched Playbook: Enterprise Efficiency
---
KEY FINDINGS
Objections Raised:
• [12:34] John: "Your pricing is 2x what we're paying now for our current solution"
→ Response: Sarah mentioned ROI payback period
Pain Points Acknowledged:
• [08:15] John: "We're spending 20 hours a week on manual data entry"
→ Matches persona pain point ✓
• [15:42] Lisa: "The biggest issue is data not syncing between systems"
→ Consider adding to persona
Questions Asked:
• [18:20] John: "How long does implementation typically take?"
• [22:05] Lisa: "Do you integrate with Salesforce?"
Competitor Mentioned:
• [25:30] John: "We looked at [Competitor] last year but didn't move forward"
Value Props Delivered:
• [10:15] Sarah: "Customers typically see 80% reduction in manual work"
→ Positive response from John
---
[View full transcript] (uses get_event_detail with includeTranscript: true)
If user wants to update library based on insights:
Based on this insight, I recommend:
Update Persona: VP Operations
Add pain point: "Data silos causing manual reconciliation work"
Add objection: "Pricing compared to current solution"
Update Playbook: Enterprise Efficiency
Add objection handling: "Pricing 2x current solution"
Response: "Let's look at total cost of ownership including the 20 hours/week
your team spends on manual work. At $X/hour, that's $Y annually..."
Apply these updates?
1. Yes, update both
2. Update persona only
3. Update Motion ICP narrative only
4. Let me customize first
5. Skip
If yes, use update_entity to apply.
| Type | Description | Extraction Types |
|------|-------------|------------------|
| objections | Pushback and concerns raised | CALL_EXTERNAL_OBJECTIONS, EMAIL_OBJECTION |
| pain-points | Problems prospects mention | CALL_EXTERNAL_BUSINESS_PROBLEMS, EMAIL_PAIN_POINT |
| questions | Questions asked about offering | CALL_EXTERNAL_QUESTIONS_OR_CONFUSION_ABOUT_OFFERING, EMAIL_QUESTION |
| competitors | Competitor mentions | CALL_EXTERNAL_COMPETITORS_TO_OUR_OFFERING, EMAIL_COMPETITOR_MENTION |
| value-props | Value props that resonated | CALL_INTERNAL_VALUE_PROP_PRESENTATIONS, EMAIL_VALUE_PROP |
| use-cases | Use cases discussed | CALL_INTERNAL_USE_CASES_BROUGHT_UP, EMAIL_USE_CASE |
| proof-points | Proof points referenced | CALL_INTERNAL_PROOF_POINTS, EMAIL_PROOF_POINT |
list_events - Search events with filterslist_findings - Aggregate findings across eventsget_event_detail - Get detailed event info with transcript/contentget_entity - Get persona / segment / competitor / objection detailslist_motions / list_motion_icps / find_motion_icp - Pull the Motion ICP narrative (Target ICP overview, Operating landscape, Strategic narrative, Pains and consequences, Benefits and impacts, Methodology, References) for persona × segment contextsearch_knowledge_base - Find related library contentupdate_entity - Apply suggested updates to library entities (personas, segments, objections, etc.)update_motion_playbook - Edit Motion ICP narrative sections (Strategic narrative, Benefits and impacts, Pains and consequences) with field-informed refinementsNo Events Found:
No events found for the specified period.
This could mean:
- No calls/emails have been synced yet
- The date range is too narrow
- Filters are too restrictive
Try:
- Expanding the date range
- Removing filters
- Check that your CRM/email integration is connected in Octave
No Findings Extracted:
Events found but no findings extracted yet.
Findings are extracted automatically when events are processed. Recent events may still be processing.
Check back in a few minutes, or view raw events instead.
/octave:analyzer - Analyze specific conversations in depth/octave:wins-losses - Focus on deal outcomes/octave:audit - Ensure library captures field learnings/octave:library - Update library with insights/octave:battlecard - Competitive intelligence from conversation data/octave:icp-refine - Use conversation patterns to refine ICP/octave:enablement - Turn field insights into team enablement materialstools
Capture a brand's visual design system from its website and build a reusable component kit. Walks key pages on a domain (screenshots + HTML via the Octave scrape tool), derives design tokens (colors, type, spacing, radius, shadow), and produces a minimal component library (buttons, cards, headers, stats, tables, badges, hero, footer) as a self-contained HTML reference plus CSS tokens. Use when the user says "get brand components", "capture the brand", "build a component kit for <domain>", "make outputs look like <company>", or wants other skills to generate on-brand HTML for a target company.
tools
Define, run, and manage multi-step GTM workflows with human-in-the-loop execution. Use when user says "run a workflow", "show workflows", "create a workflow", "automate this process", or references workflow-based tasks.
development
Analyze won and lost deals for patterns, insights, and actionable learnings. Use when user says "win/loss analysis", "why did we lose", "deal patterns", "win themes", or asks about deal outcome trends. Do NOT use for visual HTML reports — use /octave:win-loss-report instead.
development
Generate visual win/loss analysis reports as self-contained HTML with CSS-based charts and data visualizations. Use when user says "win/loss report", "deal report", "visual analysis", or wants a formatted HTML version of deal outcome analysis. Do NOT use for text-based deal analysis — use /octave:wins-losses instead.