A
aliasunder/vault-onboarding
Give your AI agents persistent memory and session continuity in your Obsidian vault — a conversational…
View on GitHub ↗Link checked 2026-11-12 · HTTP 200 · opens the vendor's own site
Install & config
Client config (built from the install command this repo gives)
{
"mcpServers": {
"aliasunder-vault-onboarding": {
"command": "npx",
"args": ["skills"]
}
}
}Parsed from the README we fetched on 2026-11-03; we have not executed it.
command/args come from the install command the repository states. When it is ambiguous, the project README wins.
VS Code (.vscode/mcp.json - the key is servers)
{
"servers": {
"aliasunder-vault-onboarding": {
"command": "npx",
"args": ["skills"]
}
}
}Same server, but VS Code keeps it under <code>servers</code>.
Claude Code (command line)
claude mcp add --transport stdio aliasunder-vault-onboarding -- npx skills
Claude Code does not read a config file; add the server with this command.
Key names differ by client: Clients & CLI
- Star count
- 2 ★ · aliasunder/vault-onboarding · read from the GitHub search API · (checked 2026-11-13 20:00:50)
- Source
- read directly from its GitHub page · type: open-source project
- Harvest history
- first seen 2026-11-04 · last seen 2026-11-14 · seen 11× · listed by 1 sources
- Score
- score 103 · 2 ★ · 1 sources · repo
- Install
npx skills
FAQ (answers come from our records)
How do I install it?
The repository provides this install command:
npx skills. It comes from the repository itself; we cannot guarantee it runs as-is in your client.Who is it for?
We filed it under these tags: Agent 技能. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
aliasunder/vault-onboarding；first catalogued 2026-11-04；last seen 2026-11-14。There is no official certification or quality rating here — we record sources and dates only.# vault-onboarding
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
Bootstrap an agent collaboration system into an Obsidian vault — memory, protocols, task boards, and per-client instruction files via a conversational interview.
> In development — not yet released. The implementation is merged and in validation; a first GitHub release follows once testing passes. See Status.
Works with Claude Code, Cowork, claude.ai, Perplexity, Cursor, GitHub Copilot, and many more.
## Installing
bash
npx skills add aliasunder/vault-onboarding
## What it does
A single conversational interview scaffolds everything you need for structured AI agent collaboration in your Obsidian vault:
Memory files — About Me/ files that give agents persistent knowledge about who you are, what you prefer, and how you work
Session protocol — structured start and end rituals so agents maintain continuity across sessions
Task boards — 5-lane Kanban boards for tracking work with AI agents
Generated skills — session-start, session-end, remember, and project-role skills tailored to your actual vault structure
Client instruction files — generated for each AI tool you use, in the right format for each client's loading contract
Every component is optional. Start with just instruction files (agents know your name and preferences), add memory when you want persistence, add boards when you want task tracking, add the session protocol when you want full continuity.
## How it works
The skill runs a branching interview — it asks what you need and scaffolds only that:
1. Calibration — which AI tools you use, what kind of work you do
2. Identity — name, timezone, how you want agents to work with you
3. Vault setup — detect or create an Obsidian vault
4. Organization — project folders, People/, Reference/, vault conventions (tags, linking, schemas)
5. Memory — About Me/ files seeded with your answers
6. Tasks — Kanban boards with 5 lanes
7. Protocol — session start/end sequences, generated skills
8. Client setup — instruction files for each of your AI tools
9. Verification — walk through everything, test it works
The interview is resumable — stop mid-onboarding and pick up where you left off next session. Resumability begins once the vault checkpoint exists (after the vault-setup phase); answers given before that live only in the conversation.
## Standalone or with vault-cortex
Works without vault-cortex using native file tools. With vault-cortex connected, the generated skills unlock remote access, hybrid search, and semantic memory recall.
## Status
vault-onboarding is in active development and not yet released. The full implementation — interview flow, reference files, asset templates, generated skills — is merged (PR #1) and now in validation. The install command works, but treat it as pre-release until testing passes and a first GitHub release is cut.
> In development — not yet released. The implementation is merged and in validation; a first GitHub release follows once testing passes. See Status.
Works with Claude Code, Cowork, claude.ai, Perplexity, Cursor, GitHub Copilot, and many more.
## Installing
bash
npx skills add aliasunder/vault-onboarding
## What it does
A single conversational interview scaffolds everything you need for structured AI agent collaboration in your Obsidian vault:
Memory files — About Me/ files that give agents persistent knowledge about who you are, what you prefer, and how you work
Session protocol — structured start and end rituals so agents maintain continuity across sessions
Task boards — 5-lane Kanban boards for tracking work with AI agents
Generated skills — session-start, session-end, remember, and project-role skills tailored to your actual vault structure
Client instruction files — generated for each AI tool you use, in the right format for each client's loading contract
Every component is optional. Start with just instruction files (agents know your name and preferences), add memory when you want persistence, add boards when you want task tracking, add the session protocol when you want full continuity.
## How it works
The skill runs a branching interview — it asks what you need and scaffolds only that:
1. Calibration — which AI tools you use, what kind of work you do
2. Identity — name, timezone, how you want agents to work with you
3. Vault setup — detect or create an Obsidian vault
4. Organization — project folders, People/, Reference/, vault conventions (tags, linking, schemas)
5. Memory — About Me/ files seeded with your answers
6. Tasks — Kanban boards with 5 lanes
7. Protocol — session start/end sequences, generated skills
8. Client setup — instruction files for each of your AI tools
9. Verification — walk through everything, test it works
The interview is resumable — stop mid-onboarding and pick up where you left off next session. Resumability begins once the vault checkpoint exists (after the vault-setup phase); answers given before that live only in the conversation.
## Standalone or with vault-cortex
Works without vault-cortex using native file tools. With vault-cortex connected, the generated skills unlock remote access, hybrid search, and semantic memory recall.
## Status
vault-onboarding is in active development and not yet released. The full implementation — interview flow, reference files, asset templates, generated skills — is merged (PR #1) and now in validation. The install command works, but treat it as pre-release until testing passes and a first GitHub release is cut.
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/aliasunder-vault-onboarding/)
- Source
- github · https://github.com/aliasunder/vault-onboarding
- Browse by field
- Agent skills
- Traction
- 2 ★
- added
- today
More like this
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.