undefined-ui/second-brain-os / skills/second-brain-chat-import
second-brain-chat-import
VerifiedTriage an exported chat history into what to ingest, what to archive and what to delete, with a privacy pass first. Use this skill when the user has exported their Claude or ChatGPT history, asks to import old conversations, or asks what in their chat archive is worth keeping. Do NOT use for ingesting a single pasted conversation, or for any material the user has not explicitly asked to bring into the vault.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.1 KB |
SKILL.md
View on GitHub---
name: second-brain-chat-import
description: >-
Triage an exported chat history into what to ingest, what to archive and what
to delete, with a privacy pass first. Use this skill when the user has exported
their Claude or ChatGPT history, asks to import old conversations, or asks what
in their chat archive is worth keeping. Do NOT use for ingesting a single
pasted conversation, or for any material the user has not explicitly asked to
bring into the vault.
---
# Import chat history
Chat history is the most underrated source a person owns and the most sensitive.
It records their reasoning, not just facts, and it also records things they would
not want in a file that gets synced, committed and backed up.
## Core rule
Privacy pass before triage, triage before ingestion. Never ingest an export
wholesale.
## Workflow
1. **Convert** with `scripts/chat_export_to_md.py` into one file per
conversation, filtering out short exchanges.
2. **Privacy pass.** List conversations touching health, money, other people's
private information, or confidential work. The user decides; you delete
nothing on your own.
3. **Triage the rest** into three piles: worth ingesting (they worked something
out, decided something, or got an explanation that landed), worth archiving
in `raw/`, and delete.
4. **Report the lists.** Move nothing yet.
5. **On approval, ingest** the first pile, with the instruction that these are
the user's own thinking: build pages around what they were working out and
what they concluded, not around the assistant's explanations.
## Output format
```
Converted: <n> conversations (<n> skipped as too short)
Privacy review needed: <n>
<title> - <why>
Worth ingesting: <n>
<title> - <what it worked out>
Archive only: <n>
Delete suggested: <n>
```
## Calibration
Expect roughly nine in ten conversations to be throwaway lookups. A triage that
recommends ingesting most of the export has not filtered.
Record dates on every page. A position from two years ago is not a current
belief, and the vault has to be able to tell the difference.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |