Octave Generate Skill
Generate GTM content using your Octave library context.
Usage
code
/octave:generate <type> [options]
Content Types
Email Sequences
code
/octave:generate email --to "<person>" --about "<topic>" [--persona "<persona>"] [--playbook "<playbook>"]
Example:
code
/octave:generate email --to "John Smith, VP Engineering at Acme" --about "reducing deployment time"
LinkedIn Messages
code
/octave:generate linkedin --to "<person>" --about "<topic>" [--type connection|inmail|follow-up]
Example:
code
/octave:generate linkedin --to "Sarah Chen, CTO" --about "DevOps automation" --type connection
Call Prep
code
/octave:generate call-prep --for "<person/company>" [--playbook "<playbook>"] [--focus "<topics>"]
Example:
code
/octave:generate call-prep --for "Meeting with Acme Corp engineering team" --focus "security, scalability"
General Content
code
/octave:generate content --type "<content-type>" --about "<topic>" [--persona "<persona>"]
Example:
code
/octave:generate content --type "objection handling" --about "pricing concerns" --persona "CFO"
Instructions
When the user runs /octave:generate:
- •
Parse the Request Identify:
- •Content type (email, linkedin, call-prep, content)
- •Target person/company if specified
- •Topic or context
- •Optional constraints (persona, playbook, etc.)
- •
Gather Context Before generating, collect relevant context using MCP tools:
For Email:
- •If person specified, use
find_personto get details - •If company specified, use
find_companyto get company info - •Use
search_knowledge_baseto get relevant messaging - •Match to appropriate persona and playbook
For LinkedIn:
- •Use
find_personto research the recipient - •Use
search_knowledge_basefor relevant talking points - •Consider connection context (mutual connections, shared interests)
For Call Prep:
- •Use
find_companyandfind_personfor attendee research - •Use
get_playbookif specified - •Use
search_knowledge_basefor relevant proof points and use cases
- •If person specified, use
- •
Generate Content Using MCP Tools
Call the tools directly (they're pre-loaded, no ToolSearch needed).
For Email Sequences:
codegenerate_email({ person: { firstName: "<first name>", lastName: "<last name>", email: "<email>", linkedInProfile: "<linkedin url>", companyName: "<company>", title: "<job title>" }, allEmailsContext: "<context for all emails>", allEmailsInstructions: "<instructions for all emails>", numEmails: 4 })For General Content:
codegenerate_content({ instructions: "<detailed instructions for content generation>", customContext: "<additional context>", person: { /* optional person details */ }, company: { /* optional company details */ } })For Call Prep:
codegenerate_call_prep({ person: { firstName: "<first name>", lastName: "<last name>", email: "<email>", linkedInProfile: "<linkedin url>", companyName: "<company>", jobTitle: "<job title>" }, meetingContext: "<meeting details and focus areas>" }) - •
Present Generated Content Format the output clearly with:
- •The generated content
- •Context used (persona, playbook, etc.)
- •Suggestions for customization
- •
Offer Refinement Options
- •"Would you like me to adjust the tone?"
- •"Should I add more proof points?"
- •"Want a version for a different persona?"
Tips
- •Provide as much context as possible for better results
- •Specify the persona if you know who you're targeting
- •Use
/octave:researchfirst if you need more info about the recipient
Examples
Quick Email
code
/octave:generate email --to "engineering leader" --about "reducing CI/CD pipeline time"
Detailed Email with Context
code
/octave:generate email --to "Mike Johnson, VP Eng at TechCorp (500 employees, Series B)" --about "improving developer productivity" --persona "Engineering Leader" --playbook "Enterprise DevOps"
Call Prep
code
/octave:generate call-prep --for "Discovery call with Acme Corp" --focus "security compliance, scalability"
Related Skills
- •
/octave:research- Research recipients before generating - •
/octave:library- Save successful messaging patterns back to library