obsidian-project-memory

Maintains an Obsidian knowledge base for research projects using scripts and agent synthesis.

Updated Oct 7, 2022
One-click install
npx skills add https://github.com/tamagusko/linux-cfg --skill obsidian-project-memory-tamagusko
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: obsidian-project-memory
Source: https://github.com/tamagusko/linux-cfg/tree/main/dotfiles/claude/skills/obsidian-project-memory
Command: npx skills add https://github.com/tamagusko/linux-cfg --skill obsidian-project-memory-tamagusko

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Research projects accumulate scattered notes, experiment logs, paper summaries, and results across a repository, making it hard to keep a durable, organized knowledge base in Obsidian without manual upkeep or MCP-based plugins. ## Core Features & Use Cases - Filesystem-first vault management: Detects, bootstraps, syncs, and archives a compact vault structure (Hub, Plan, Knowledge, Papers, Experiments, Results, Writing, Daily) via the deterministic project_kb.py script, with no MCP, API keys, or REST plugins required. - Agent-driven synthesis: Imports existing repositories by having an agent read key sources and write durable notes, following a Papers -> Experiments -> Results -> Writing promotion pipeline. - Knowledge CRUD rules: Enforces one canonical note per durable object, archive-by-default deletion, and bilingual (English/Chinese) note generation. - Use Case: A researcher with a machine learning repository asks to import it into Obsidian; the skill bootstraps the vault, synthesizes a project overview and experiment map, and keeps daily notes and results synchronized on subsequent turns. ## Quick Start Ask the assistant to import this research repository into my Obsidian vault and keep the project memory and daily notes synchronized.

Frequently Asked Questions about obsidian-project-memory

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I import an existing research repository into Obsidian?

Run the detect command to check binding, then bootstrap the vault structure with project_kb.py. For repositories with substantial documents, use agent-first import: an agent reads key sources like README, plans, and analysis reports, then writes synthesized durable notes into Knowledge, Experiments, and Results.

How do I keep Obsidian project notes synchronized with my repository?

Use the sync command with scope auto to refresh the hub note, plan note, project memory, and daily notes from repository state. Sync handles deterministic state only; interpreting experimental meaning or promoting findings to durable notes remains an agent task.

Does this Obsidian workflow require MCP or API keys?

No. The skill is explicitly filesystem-first and agent-driven, requiring no MCP servers, API keys, REST plugins, or .base artifacts. All state management runs through a local Python script operating on Markdown files.

Where should experiment results go in an Obsidian research vault?

Stable findings go to Results/ as canonical notes, while complete internal experiment round reports go to Results/Reports/ using the naming contract YYYY-MM-DD--experiment-line--round--purpose. Raw or exploratory output stays in Daily/ until it stabilizes.

Can Obsidian notes be generated in Chinese instead of English?

Yes. Set note_language to zh-CN in the project registry, pass --note-language zh-CN during bootstrap, or set the OBSIDIAN_NOTE_LANGUAGE environment variable. Section updates remain compatible with both English and Chinese headings.

What happens when I delete a note from the knowledge base?

Deletion requests are treated as archive by default: the note moves to Archive/ and direct links in the hub, plan, and index notes are repaired. Permanent purge only happens when you explicitly ask for it.