Chat Lift
v1.0.1Import, search, and archive AI conversations from ChatGPT, Claude, and Gemini. Clean indexed formats, full-text search, static HTML archive. No server required.
⭐ 0· 242·1 current·1 all-time
byShadow Rose@theshadowrose
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the code and instructions. The code implements importers for ChatGPT/Claude/Gemini, converters to Markdown/HTML/JSON, local search, and static archive generation. No unrelated credentials, binaries, or services are requested.
Instruction Scope
SKILL.md instructs the agent to run local Python scripts on user-provided export files and to open generated static HTML. The instructions do not ask the agent to read unrelated system files, environment variables, or contact external endpoints. All runtime actions described are limited to parsing provided exports and writing local files.
Install Mechanism
No install spec; code is instruction-only/standalone Python scripts. The README and SKILL.md claim only Python 3.7+ stdlib is required and the code uses only stdlib modules — no downloads or external package installs are required.
Credentials
No environment variables, credentials, or config paths are required. The provided config_example.py is optional and local. There are no declared secrets or other sensitive environment access that would be out of proportion to a local archive tool.
Persistence & Privilege
The skill does not request always:true or other elevated platform privileges. It writes files only to its own archive directories (configurable) and does not modify other skills or system-wide agent settings.
Assessment
This package appears coherent and local-only, but review and follow these precautions before running: 1) Inspect the scripts yourself (they are small and human-readable) to confirm no unexpected network calls or subprocess execution. 2) Run the tool on a copy of your exported JSONs (not the originals) and keep backups, in case of accidental data loss or formatting changes. 3) If you have sensitive attachments or binary data, note this tool only processes text — attachments are ignored. 4) For very large archives, expect high memory usage (the project notes this limitation); consider splitting archives or using external tools for huge datasets. 5) Because the source/homepage is unknown, prefer running in a local/sandboxed environment if you are risk-averse.Like a lobster shell, security has layers — review code before you run it.
conversationvk975qvszexjzqabmjbrvgy2k8n82ja8platestvk975qvszexjzqabmjbrvgy2k8n82ja8ppromptingvk975qvszexjzqabmjbrvgy2k8n82ja8pqualityvk975qvszexjzqabmjbrvgy2k8n82ja8pupgradevk975qvszexjzqabmjbrvgy2k8n82ja8p
License
MIT-0
Free to use, modify, and redistribute. No attribution required.