/tuned-context-installer

Tuned Context Installer

Six-stage pipeline to install customer-specific AI context

Bespoke TierUtility & Infrastructure

Overview

Turns raw customer documents (decks, call transcripts, ICP docs) into a four-layer tuned context stack that downstream skills load automatically. Safety model ensures no canonical files are touched until the operator explicitly approves.

What It Does

  • Converts PDF/DOCX/PPTX source documents into classified markdown corpus
  • Runs structured 5-section operator interview to build signal hypotheses
  • Extracts claims via typed extractors with anti-bias citation standards
  • Detects tensions (contradiction, time drift, scope drift) between sources
  • Publishes atomically to shared contexts only after operator approval

Inputs

  • Customer source documents (2+ distinct types)
  • Operator interview answers
  • Customer slug

Outputs

  • Four-layer context stack
  • Auto-load rule
  • Install audit log

Example

/tuned-context-installer

A new client sends their sales deck, two call transcripts, and an ICP doc. Run /tuned-context-installer, complete the interview, approve, and every downstream skill automatically loads that client's positioning and ICP.

Related Skills

/install-knowledge-os

Knowledge OS Installer

8-stage setup for a new Knowledge OS instance

/hypothesis

Hypothesis Builder

ICP data into testable outbound pain hypotheses

/produce-content

Produce Content

One idea into blog, newsletter, social, images

Deep Dives

Knowledge OS Guide

Ready to use /tuned-context-installer?

This skill ships with every Knowledge OS installation. Set up your system in 90 minutes.

View PricingAll 42 Skills

Built and maintained by Victor Sowers at STEEPWORKS