Skip to content
TrustedSkillsbeta
Back to all skills

Conversation Archaeologist

Checked
onewave-ai·vlatest·other·MIT

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

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add onewave-ai/claude-skills --skill conversation-archaeologist -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

onewave-ai

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned onewave-ai/claude-skills at f317e08649.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
f317e08649
Manifest
conversation-archaeologist/SKILL.md
Scanned
1 file, 58 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

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.