Conversation Archaeologist

🌐Community
by onewave-ai · vlatest · Repository

Unearths forgotten details & context from past conversations to improve current interactions and provide richer, more informed responses.

Install on your platform

We auto-selected Claude Code based on this skill’s supported platforms.

1

Run in terminal (recommended)

terminal
claude mcp add conversation-archaeologist npx -- -y @trustedskills/conversation-archaeologist
2

Or manually add to ~/.claude/settings.json

~/.claude/settings.json
{
  "mcpServers": {
    "conversation-archaeologist": {
      "command": "npx",
      "args": [
        "-y",
        "@trustedskills/conversation-archaeologist"
      ]
    }
  }
}

Requires Claude Code (claude CLI). Run claude --version to verify your install.

About This Skill

The conversation-archaeologist skill transforms raw chat logs into structured, readable transcripts. It automatically detects speakers, assigns names or roles, and formats the output for clarity. This tool is ideal for cleaning up messy AI interactions or organizing complex dialogue histories.

When to use it

  • Converting unstructured chat exports from previous sessions into a clean document.
  • Analyzing long-form conversations where speaker identification is missing or ambiguous.
  • Preparing dialogue data for review, archiving, or further processing.
  • Extracting key insights from noisy logs by removing filler text and formatting errors.

Key capabilities

  • Automatic speaker detection and role assignment.
  • Conversion of raw text into structured transcript format.
  • Enhancement of readability through consistent styling.
  • Preservation of original conversation context while improving organization.

Example prompts

  • "Please act as a conversation archaeologist and reformat this messy chat log into a clear transcript with named speakers."
  • "Take the following raw dialogue and organize it so I can easily see who said what without any formatting issues."
  • "Extract the key points from this unstructured chat history and present them as a well-formatted conversation summary."

Tips & gotchas

Ensure the input text contains enough context for the agent to accurately infer speaker roles; vague logs may result in generic labels. For best results, provide clear markers or instructions if specific names should be assigned to participants.

Tags

🛡️

TrustedSkills Verification

Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.

Security Audits

Gen Agent Trust HubPass
SocketPass
SnykPass

Details

Version
vlatest
License
Author
onewave-ai
Installs
40

🌐 Community

Passed automated security scans.