Second Brain OS
Paste the following prompt into your AI chat to install this skill:
Follow https://skillhub.cn/install/skillhub.md and install @user_11d2869f/second-brain-os.
About this skill
Problem
Personal notes often become static archives: conclusions age, sources are unclear, prior work is not reused, and outputs do not flow back into the knowledge base. Second Brain OS treats local notes as an executable flywheel, where input is captured as assets and output drives the next iteration.
How it works
It runs an eight-stage loop: daily scans card lifecycle and maintains hot/warm/cold/expired tiers; before a task, search retrieves prior cases; after output, it requires deposit, review, mutate, and optional cleanup. Expired cards are archived and linked rather than deleted. Cards must carry source, confidence, and verification metadata; write and delete operations use audit logs and rollback constraints. A domain-aware router distributes queries across configured expert domains such as finance, AI, and law, reducing unrelated noise, with a fallback domain tracking missed matches.
Boundaries
The core workflow depends on a local directory and the bundled flywheel.py; it does not promise synchronization with external note apps. Star-chain visualization is a build-time snapshot, not real-time collaboration. Items without source or confidence are marked for review and still need human confirmation; retaining old knowledge can increase index and retrieval noise.
Use Cases
- Before starting a task, run the built-in search to retrieve prior cases and reuse proven paths instead of restarting.
- After depositing a script case, record a mutation with efficiency, capability, or network type to keep the compound ledger.
- Run daily scans to tier cards as hot, warm, cold, or expired and mark aging knowledge for cleanup.
- Configure finance, AI, or law domains with keywords so queries route to relevant shelves and reduce unrelated noise.
Best For
- Engineers maintaining local Markdown notes who want to tier old conclusions and mark expired cards.
- ML engineers reviewing AI workflows who need outputs backfilled as knowledge cards.
- Research assistants managing multi-domain shelves who want keyword-based domain retrieval.
- Independent developers keeping compound ledgers who require typed mutations for efficiency, capability, or network.
Related Skills
Search Huawei Cloud official docs and product pages to find ECS, OBS, RDS, CCE product specs, parameters, documentation, and API references without login.
OCR-based recognition for movie, train, flight, and event tickets in images or PDFs, extracting key fields into Markdown or JSON reports.
Turns notes, research, and meeting summaries into actionable next moves, plans, decisions, experiments, and decision-changing gaps.
A local wiki knowledge base manager that compiles raw documents into sourced, indexed Markdown pages with wikilinks, query support, and health checks.