Second Brain
Bootstrap a personal knowledge vault with CLAUDE.md and AGENTS.md so your coding agent follows fixed wiki rules instead of improvising structure.
Overview
Second-brain is an agent skill most often used in Build (also Operate, Idea) that generates vault-root CLAUDE.md and AGENTS.md from a wizard so agents maintain a personal wiki by fixed schema rules.
Install
npx skills add https://github.com/nicholasspisak/second-brain --skill second-brainWhat is this skill?
- Wizard-driven onboarding that fills CLAUDE.md and AGENTS.md placeholders at the vault root
- Embeds librarian/wiki-maintainer rules so agents never improvise page structure
- Injects full wiki-schema reference content from references/wiki-schema.md
- Generates 5–8 domain-specific suggested tags from the user’s topic description
- Single source of truth for vault name, domain description, and maintenance behavior
- Outputs 2 root agent config files: CLAUDE.md and AGENTS.md
- Wizard suggests 5–8 domain tags from the user’s topic
Adoption & trust: 1.7k installs on skills.sh; 387 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your notes pile up in the vault but agents freestyle folder and page structure, so nothing stays searchable or maintainable.
Who is it for?
Solo builders standing up or restructuring an Obsidian-style vault they want Claude or Codex to curate with explicit librarian rules.
Skip if: Teams that only need one-off summaries with no ongoing wiki maintenance or no willingness to follow a fixed schema.
When should I use this skill?
Starting or restructuring a personal knowledge vault and you want standardized CLAUDE.md/AGENTS.md plus wiki-schema-driven maintenance.
What do I get? / Deliverables
You get root-level agent configs with domain tags and embedded wiki schema so every future session compiles and maintains wiki pages the same way.
- CLAUDE.md at vault root
- AGENTS.md at vault root
- Domain-specific suggested tag list in config
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is build/agent-tooling because the skill’s main deliverable is vault-root agent config generated at setup. It wires Claude Code and Codex to a second-brain vault schema—not app code—so agent-tooling is the right primary subphase.
Where it fits
Run onboarding once to drop CLAUDE.md and AGENTS.md with wiki-schema at a new vault root.
Compile competitor and audience notes into schema-compliant wiki pages as you discover.
Reconcile drifted pages and tags using the embedded librarian rules during a monthly vault audit.
Treat product and architecture notes as first-class wiki pages agents update after each ship.
How it compares
Use instead of ad-hoc CLAUDE.md prompts that lack wiki-schema enforcement and onboarding placeholders.
Common Questions / FAQ
Who is second-brain for?
Indie builders and knowledge workers who use agent-assisted PKM and want vault-root configs that lock structure and maintenance behavior.
When should I use second-brain?
At vault setup in Build, when capturing research in Idea, or during Operate cleanup—whenever you need agents to follow wiki rules instead of improvising.
Is second-brain safe to install?
Review the Security Audits panel on this Prism page and inspect generated CLAUDE.md/AGENTS.md before granting broad vault access to any agent.
SKILL.md
READMESKILL.md - Second Brain
# Claude Code Agent Config Template This template generates a `CLAUDE.md` file at the vault root. ## Output File - **Filename:** `CLAUDE.md` - **Location:** Vault root ## Template The onboarding skill should generate a file with this structure, replacing all `{{placeholder}}` values with the user's wizard answers: --- # {{VAULT_NAME}} > {{DOMAIN_DESCRIPTION}} ## Suggested Tags {{DOMAIN_TAGS}} ## Knowledge Base Rules You are a librarian and wiki maintainer for a personal knowledge base. You read raw sources, compile them into structured wiki pages, and maintain the wiki over time. You never improvise structure — you follow these rules exactly. {{WIKI_SCHEMA}} ## Placeholder Definitions - `{{VAULT_NAME}}` — the vault name from wizard step 1 - `{{DOMAIN_DESCRIPTION}}` — the domain/topic from wizard step 3, formatted as a one-line description - `{{DOMAIN_TAGS}}` — a bullet list of 5-8 suggested tags relevant to the domain, generated by the LLM based on the domain description - `{{WIKI_SCHEMA}}` — the full contents of `references/wiki-schema.md`, starting from the `## Architecture` section # Codex Agent Config Template This template generates an `AGENTS.md` file at the vault root. ## Output File - **Filename:** `AGENTS.md` - **Location:** Vault root ## Template The onboarding skill should generate a file with this structure, replacing all `{{placeholder}}` values with the user's wizard answers: --- # {{VAULT_NAME}} > {{DOMAIN_DESCRIPTION}} ## Suggested Tags {{DOMAIN_TAGS}} ## Knowledge Base Rules You are a librarian and wiki maintainer for a personal knowledge base. You read raw sources, compile them into structured wiki pages, and maintain the wiki over time. You never improvise structure — you follow these rules exactly. {{WIKI_SCHEMA}} ## Placeholder Definitions - `{{VAULT_NAME}}` — the vault name from wizard step 1 - `{{DOMAIN_DESCRIPTION}}` — the domain/topic from wizard step 3, formatted as a one-line description - `{{DOMAIN_TAGS}}` — a bullet list of 5-8 suggested tags relevant to the domain, generated by the LLM based on the domain description - `{{WIKI_SCHEMA}}` — the full contents of `references/wiki-schema.md`, starting from the `## Architecture` section # Cursor Agent Config Template This template generates a `.cursor/rules/second-brain.mdc` file in the vault. ## Output File - **Filename:** `second-brain.mdc` - **Location:** `.cursor/rules/` (relative to vault root) ## Template The onboarding skill should create the `.cursor/rules/` directory if it doesn't exist, then generate a file with this structure, replacing all `{{placeholder}}` values with the user's wizard answers: --- --- description: Knowledge base librarian rules for {{VAULT_NAME}} globs: alwaysApply: true --- # {{VAULT_NAME}} > {{DOMAIN_DESCRIPTION}} ## Suggested Tags {{DOMAIN_TAGS}} ## Knowledge Base Rules You are a librarian and wiki maintainer for a personal knowledge base. You read raw sources, compile them into structured wiki pages, and maintain the wiki over time. You never improvise structure — you follow these rules exactly. {{WIKI_SCHEMA}} ## Placeholder Definitions - `{{VAULT_NAME}}` — the vault name from wizard step 1 - `{{DOMAIN_DESCRIPTION}}` — the domain/topic from wizard step 3, formatted as a one-line description - `{{DOMAIN_TAGS}}` — a bullet list of 5-8 suggested tags relevant to the domain, generated by the LLM based on the domain description - `{{WIKI_SCHEMA}}` — the full contents of `references/wiki-schema.md`, starting from the `## Architecture` section # Gemini CLI Agent Config Template This template generates a `GEMINI.md` file at the vault root. ## Output File - **Filename:** `GEMINI.md` - **Location:** Vault root ## Template The onboarding skill should generate a file with this structure, replacing all `{{placeholder}}` values with the user's wizard answers: --- # {{VAUL