Run a self-evolving markdown second brain with COG
Use COG to onboard a markdown-based second brain with agent skills for braindumps, briefs, reviews, research, product work, and verifier-backed workflows.
npx skills add agentskillexchange/skills --skill run-a-self-evolving-markdown-second-brain-with-cog
Use COG Second Brain when an agent should help operate a personal or team knowledge system stored as markdown files, Git history, and optional Obsidian views. The workflow starts with onboarding, then gives the agent skills for braindumps, daily briefs, URL capture, weekly reviews, knowledge consolidation, product and engineering artifacts, people CRM updates, and closed-loop verification. The boundary is an agentic second-brain operating system with explicit markdown files, role packs, workers, and verifier skills, not a generic note app, database, productivity product, or isolated prompt pack.
What this skill actually does
Inputs and prerequisites: Git, a markdown-reading or skill-aware agent runtime such as Claude Code, Cursor, Kiro, Gemini CLI, or Codex; optional Obsidian.
Setup notes: Clone https://github.com/huytieu/COG-second-brain, open the folder in the chosen agent runtime, and ask the agent to run onboarding. Claude Code uses .claude/skills, Kiro uses .kiro/powers, Gemini CLI uses .gemini commands and skills, and other agents can follow AGENTS.md.
Source and verification boundary: use https://github.com/huytieu/COG-second-brain as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.