home / skills / onewave-ai / claude-skills / conversation-archaeologist

conversation-archaeologist skill

safe

This skill mines past Claude conversations to build a living user manual that informs all other skills with style, goals, and patterns.

npx playbooks add skill onewave-ai/claude-skills --skill conversation-archaeologist

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

1.9 KB

---
name: conversation-archaeologist
description: Mine ALL past Claude conversations to build a living 'User Manual About You'. Extract writing style, business context, goals, preferences, and patterns. Make all other skills smarter with context.
---

# Conversation Archaeologist
Mine ALL past Claude conversations to build a living 'User Manual About You'. Extract writing style, business context, goals, preferences, and patterns. Make all other skills smarter with context.

## Instructions

You are a master conversation analyst and profile builder. Use conversation_search and recent_chats tools to mine hundreds of past conversations. Extract patterns in: writing style, business context, recurring problems, stated goals, preferences, pet peeves, domain expertise, relationship dynamics, and decision-making patterns. Create a comprehensive, living profile that other skills can reference for personalized outputs. Update this profile automatically as new conversations occur.

### Output Format

```markdown
# Conversation Archaeologist Output

**Generated**: {timestamp}

---

## Results

[Your formatted output here]

---

## Recommendations

[Actionable next steps]

```

### Best Practices

1. **Be Specific**: Focus on concrete, actionable outputs
2. **Use Templates**: Provide copy-paste ready formats
3. **Include Examples**: Show real-world usage
4. **Add Context**: Explain why recommendations matter
5. **Stay Current**: Use latest best practices for meta

### Common Use Cases

**Trigger Phrases**:
- "Help me with [use case]"
- "Generate [output type]"
- "Create [deliverable]"

**Example Request**:
> "[Sample user request here]"

**Response Approach**:
1. Understand user's context and goals
2. Generate comprehensive output
3. Provide actionable recommendations
4. Include examples and templates
5. Suggest next steps

Remember: Focus on delivering value quickly and clearly!

Overview

This skill builds a living "User Manual About You" by mining all past Claude conversations. It synthesizes writing style, business context, goals, preferences, and recurring patterns into a structured profile that other skills can consume. The profile updates automatically as new conversations arrive to keep personalization current.

How this skill works

The skill searches historical and recent chats, extracts signals across messages, and normalizes them into profile fields like tone, common vocabulary, priorities, and decision triggers. It generates a concise, machine-readable profile plus human-friendly summaries and actionable recommendations. Other skills call this profile to adapt language, suggestions, and workflows to the user.

When to use it

Before generating customer-facing content to match the user's voice and tone
When automating workflows that must respect the user's priorities and constraints
During onboarding of new AI skills to provide immediate personalization
For periodic audits to surface shifts in goals, pain points, or preferences

Best practices

Run a full historical scan initially, then schedule incremental updates after each session
Prioritize high-confidence signals (explicit statements, repeated phrases) over single observations
Separate stable attributes (values, role) from transient states (current projects)
Provide both machine-readable fields and short human summaries for transparency
Respect privacy: expose only aggregated, relevant insights and allow opt-out

Example use cases

Adjust email drafts to the user's habitual greeting, signature style, and formality level
Surface next-best actions based on recurring business goals and past decisions
Customize coaching prompts to match the user's preferred feedback style and rhythm
Filter and prioritize task suggestions by known constraints like time zone or capacity
Detect and flag evolving goals so other skills can propose aligned templates

FAQ

How often does the profile update?

Initial build uses all past conversations; incremental updates run after each new chat or on a scheduled cadence you configure.

What kinds of signals are extracted?

Writing style, tone, recurring vocabulary, stated goals, business context, preferences, pet peeves, decision patterns, and domain expertise indicators.

Can I control what the skill stores or shares?

Yes. The skill supports filters and opt-outs so you can limit which conversations contribute and which profile fields are exposed to other skills.