Persona Distiller
by Roy Yuen
Extract structured, evidence-backed AI persona profiles from historical chat logs, emails, and documents.
- Build digital twins from historical communication archives
- Generate system prompts for agents based on real expert behavior
- Extract professional communication styles from messy chat logs
$5
· or 25 creditsSecure checkout via Stripe
Included in download
- Build digital twins from historical communication archives
- Generate system prompts for agents based on real expert behavior
- Ready for Codex CLI).
- Includes example output and usage patterns
Sample input
Analyze these Spanish architectural reviews and Slack threads to distill a technical persona profile. Focus on decision-making patterns and communication style.
Sample output
CORE ROLE: Technical Architect DECISION POSTURE: Prefers 'boring' tech; prioritizes maintainability over speed. STYLE: Terse, bulleted lists, technical metaphors. EVIDENCE: "No point in a rewrite if the debt stays." (Spanish original: "No tiene sentido reescribir si la deuda sigue.")
Persona Distiller
by Roy Yuen
Extract structured, evidence-backed AI persona profiles from historical chat logs, emails, and documents.
$5
· or 25 creditsSecure checkout via Stripe
Included in download
- Build digital twins from historical communication archives
- Generate system prompts for agents based on real expert behavior
- Ready for Codex CLI).
- Includes example output and usage patterns
- Instant install
Sample input
Analyze these Spanish architectural reviews and Slack threads to distill a technical persona profile. Focus on decision-making patterns and communication style.
Sample output
CORE ROLE: Technical Architect DECISION POSTURE: Prefers 'boring' tech; prioritizes maintainability over speed. STYLE: Terse, bulleted lists, technical metaphors. EVIDENCE: "No point in a rewrite if the debt stays." (Spanish original: "No tiene sentido reescribir si la deuda sigue.")
About This Skill
What it does
The Persona Distiller transforms raw historical data—email threads, chat logs, and documents—into structured, evidence-backed AI persona specifications. It moves beyond simple "mimicry" by systematically separating stable traits from temporary context, ensuring you capture the authentic essence of a subject's decision-making and communication style without including noise or private data.
Why use this skill
Prompting an AI to "write like this person" often results in generic, superficial imitations or "AI sludge." This skill provides a rigorous analytical framework that identifies repeated patterns in reasoning, communication posture, and boundary-setting. It is ideal for developers building digital twins, specialized customer support agents, or automated executive assistants that need to maintain a consistent professional voice.
What the output looks like
The result is a high-density English persona profile (regardless of the source language) containing specific sections for Decision Posture, Reasoning Style, and Interaction Patterns. Crucially, it includes a "Confidence" score and "Open Gaps" section, so you know exactly where the data was insufficient to make a strong inference.
Supported Evidence
- Multi-turn conversation archives (Slack, Discord, WhatsApp)
- Professional email corpora and internal memos
- Authored articles, whitepapers, and technical documentation
Use Cases
- Build digital twins from historical communication archives
- Generate system prompts for agents based on real expert behavior
- Extract professional communication styles from messy chat logs
- Anonymize personality traits for reusable AI templates
Known Limitations
- Requires high-volume corpora for high-confidence scores.
- Risk of over-indexing on recent or outlier documents.
- Cannot infer private context not present in the provided text.
How to Install
mkdir -p ~/.claude/skills && curl -sL https://www.agensi.io/api/install/persona-distiller -o /tmp/persona-distiller.zip && unzip -o /tmp/persona-distiller.zip -d ~/.claude/skills && rm /tmp/persona-distiller.zipFree skills install directly. Paid skills require purchase - use the download button above after buying.
Reviews
No reviews yet - be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
Early access skill
Be the first to review this skill.
Only users who have downloaded or purchased this skill can leave a review.
Security Scanned
Passed automated security review
Permissions
No special permissions declared or detected
Compatible with SKILL.md-compatible agents (e.g., Codex CLI).
Frequently Asked Questions
Learn More About AI Agent Skills
More Premium Skills
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.
ai-automation-qa-pack
Professional QA & UAT documentation generator for AI automation agencies and complex agent deployments.
Bounty Security Pattern Master Library — 399 Vulnerability Patterns
A premium library of 399 vulnerability patterns and DeFi attack vectors for AI-driven bug hunting and security audits.
Multi-Agent Orchestration Master Library
Transform Claude Code into a coordinated multi-agent system. Battle-tested tmux orchestration patterns, YAML task queues, event-driven communication, and parallel worker management for 8+ agents.