Chat History Import

Trust Score 88/100

Import and normalize external chat exports (ChatGPT, Claude, Telegram, Slack) into OpenClaw's archive and generate staged daily memory and MEMORY.md candidates

triggers:import chat historychat exportbackfill historynormalize archivedistill memory

GitHub SKILL.md

What it does

This skill ingests external chat export packages (ChatGPT, Claude, Telegram Desktop, Slack, JSON/JSONL logs), normalizes them into OpenClaw's conversation-archive JSONL format, validates the resulting archive, and stages distilled daily memory plus MEMORY.md candidates for human review. Scripts handle deterministic tasks (inspect, normalize, validate, write artifacts); the model-driven steps focus on semantic distillation of daily memory and long-term memory candidates.

When to use it

Use when you need to backfill historical chat records into an OpenClaw workspace, create audit-ready daily memory for past dates, or generate MEMORY.md candidates from exported chat archives. Ideal for migrations, compliance audits, or recovering historical conversations.

What's included

Scripts: parsing, normalization and validation helpers (packaged with the skill repo)
References: archive schema and memory distillation prompts explained in the SKILL.md body
Instructions: step-by-step workflow covering inspect → normalize → validate → build review checklist → distill daily memory → stage MEMORY.md candidates (do not apply without review).

Compatible agents

Works with agents that can run Python scripts and model-assisted review (Claude/Code, Gemini CLI, Codex-style agents that support script execution and file I/O).

Audit Summary

Chat history import skill for normalizing ChatGPT, Claude, Telegram, and Slack exports into OpenClaw's archive format. Six scripts: two library modules (archive_contract, normalize_import internals) and four CLI tools. archive_contract.py and build_review_checklist.py ran cleanly; the remaining four require input arguments and exited with usage errors as expected. No security concerns found — no network calls, no credential handling, no destructive operations. Well-documented SKILL.md with clear workflow, guardrails, and format detection.

Watch Out

Scripts require input arguments (path, payload) — they are pipeline tools, not runnable standalone
normalize_import.py imports from archive_contract module — both must be in same directory or PYTHONPATH
Telegram import requires --peer-id flag which isn't obvious from SKILL.md's workflow section

Notes

Thorough and well-architected skill. The SKILL.md is exceptionally detailed with clear triggers, multi-step workflow, format detection logic, and explicit guardrails. Scripts are production-quality Python with type hints and good error handling. No security issues detected.

Information

Repository: openclaw-chat-history-import
Stars: 139

Trust Score

Overall88

Security95

Code Quality82

Architecture80

Usefulness78

Related Skills

Caveman Compress

Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.

Unitree Robot Controller

Control and command Unitree robots (GO1/GO2/G1/H1) via OpenClaw: initialization, basic motion commands, and sensor integrations.

Smalltalk MCP

Connects an LLM (Claude/OpenAI/etc.) to a live Smalltalk (Squeak/Cuis) image over MCP for browsing, evaluating and modifying Smalltalk code.

Cross-Project Analytics

Query local, privacy-safe cross-project analytics to report on agent, skill, hook, and team performance; replay sessions and estimate token costs.

tgcli — Telegram CLI

Command-line Telegram client (pure Rust, no TDLib) for syncing, searching, sending messages, managing chats and running daemon mode; suitable for scripts and LL

Go Data Structures

Authoritative guidance on choosing and using Go built-in and standard-library data structures, with practical best practices for slices, maps, arrays, container

Claude Code (Clawdbot)

Wrapper to run the local Claude Code CLI in headless or interactive (tmux) modes for code analysis, refactors, tests, and structured output.

Anthropic Security Basics

Practical security practices for Anthropic Claude integrations: API key management, input validation, prompt-injection defenses, and output scanning.

Back to Skills