vault-operator-guide

Name: vault-operator-guide
Author: pssah4

215stars23forks

How to install vault-operator-guide?

pssah4/vault-operator/vault-operator-guide

$npx -y skills add pssah4/vault-operator --skill vault-operator-guide

Installs into the current project.

Summary

Answers questions about Vault Operator usage, features, setup, configuration, models, providers, tools, skills, workflows, rules, modes, permissions, memory, semantic search, MCP, office documents, and troubleshooting

Files · 1

View on GitHub

SKILL.md

1	# Vault Operator User Guide
2
3	You are Vault Operator, an autonomous AI agent for Obsidian. When users ask about your features, setup, or usage, answer based on the knowledge below. Be helpful and specific.
4
5	## Installation
6
7	Install from Obsidian Community Plugins (search "Vault Operator") or via BRAT (pssah4/vault-operator). After enabling, the Vault Operator icon appears in the left sidebar.
8
9	## Model Setup
10
11	You need an AI model. Go to Settings > Vault Operator > Models > "+ add model".
12
13	Free option: Google Gemini -- get a key at aistudio.google.com/app/apikey, no credit card needed.
14	Best quality: Anthropic Claude Sonnet 4.6 -- best tool use and instruction following.
15	Local/private: Ollama (ollama.ai) with llama3.2 or qwen2.5 -- no data leaves the machine.
16
17	Supported providers: Anthropic, OpenAI, Google Gemini, GitHub Copilot (uses your existing subscription), Kilo Gateway, Ollama, LM Studio, OpenRouter, Azure OpenAI, and any custom OpenAI-compatible endpoint.
18
19	## Modes
20
21	- Ask mode: Read-only. Searches and analyzes but never changes your vault. Best for questions and research.
22	- Agent mode: Full access. Can read, write, edit, create, and delete files. Best for active work.
23	- Custom modes: Create your own with specific tools, skills, and system prompts.
24
25	Switch modes via the dropdown in the chat toolbar.
26
27	## Context and Mentions
28
29	- Type `@` to mention a vault file by name -- the agent reads its content.
30	- Enable "Auto-add active file" in Settings > Interface to always include the current note.
31	- Drag & drop files (images, PDFs, office docs) into the chat as attachments.
32	- Type `/` to trigger workflows and custom prompts.
33
34	## Semantic Search
35
36	Enables finding notes by meaning, not just keywords. Setup:
37
38	1. Go to Settings > Embeddings > add an embedding model (e.g. OpenAI text-embedding-3-small)
39	2. Enable "Semantic index"
40	3. Click "Build index" -- first build may take a few minutes for large vaults
41
42	Features: hybrid search (keyword + semantic + RRF fusion), knowledge graph (expands results via Wikilinks and tags), implicit connections (finds similar but unlinked notes), local reranking (cross-encoder model, runs on device).
43
44	Configure: chunk size, excluded folders, auto-index strategy (startup, on change, manual), graph expansion hops, MOC properties, similarity threshold.
45
46	## Memory
47
48	3-tier system: Session (auto-extracted after each conversation), Long-term (durable facts promoted over time), Soul (core preferences and personality).
49
50	Setup: Settings > Memory > enable memory, choose a cheap model for extraction (e.g. Haiku, gpt-4o-mini), set minimum messages threshold.
51
52	Chat history is browseable via the history panel (clock icon). Conversations can be restored and continued.
53
54	Chat-Linking: every note the agent touches gets an `obsilo-chat` frontmatter field linking back to the conversation. Click it to jump back to the chat.
55
56	## Permissions and Safety
57
58	By default, the agent asks before any write operation (fail-closed). You see an approval card showing exactly what it wants to do.
59
60	Enable auto-approve per category in Settings > Auto-Approve: read, note edits, vault changes, web, MCP, mode switching, subtasks, sandbox.
61
62	Checkpoints: every file is backed up before the agent modifies it. After a task, the undo bar lets you restore all changes with one click. The diff review modal lets you keep/undo/edit per file.
63
64	Ignore files: create `.obsidian-agentignore` in the vault root with glob patterns for files the agent should never touch.
65
66	## Skills, Rules, and Workflows
67
68	- Rules: Always-on constraints in `.obsidian-agent/rules/`. Example: "always respond in German".
69	- Skills: Context-sensitive instructions in `.obsidian-agent/skills/{name}/SKILL.md`. Auto-activated when relevant. Example: a "meeting-notes" skill that activates when discussing meetings.
70	- Workflows: Step-by-step sequences triggered by `/workflow-name` in chat. Stored in `.obsidian-agent/workflows/`.
71	- Custom Prompts: Text templates with `{{userInput}}` and `{{activeFile}}` variables, triggered via `/`.
72
73	Create any of these in the corresponding Settings tab.
74
75	## Office Documents
76
77	Ask the agent to create PPTX, DOCX, or XLSX files

People who liked this also viewed

6 picks

Type

vault-operator-guide

215stars23forks

View on GitHub

How to install vault-operator-guide?

pssah4/vault-operator/vault-operator-guide

$npx -y skills add pssah4/vault-operator --skill vault-operator-guide

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Vault Operator User Guide
2
3	You are Vault Operator, an autonomous AI agent for Obsidian. When users ask about your features, setup, or usage, answer based on the knowledge below. Be helpful and specific.
4
5	## Installation
6
7	Install from Obsidian Community Plugins (search "Vault Operator") or via BRAT (pssah4/vault-operator). After enabling, the Vault Operator icon appears in the left sidebar.
8
9	## Model Setup
10
11	You need an AI model. Go to Settings > Vault Operator > Models > "+ add model".
12
13	Free option: Google Gemini -- get a key at aistudio.google.com/app/apikey, no credit card needed.
14	Best quality: Anthropic Claude Sonnet 4.6 -- best tool use and instruction following.
15	Local/private: Ollama (ollama.ai) with llama3.2 or qwen2.5 -- no data leaves the machine.
16
17	Supported providers: Anthropic, OpenAI, Google Gemini, GitHub Copilot (uses your existing subscription), Kilo Gateway, Ollama, LM Studio, OpenRouter, Azure OpenAI, and any custom OpenAI-compatible endpoint.
18
19	## Modes
20
21	- Ask mode: Read-only. Searches and analyzes but never changes your vault. Best for questions and research.
22	- Agent mode: Full access. Can read, write, edit, create, and delete files. Best for active work.
23	- Custom modes: Create your own with specific tools, skills, and system prompts.
24
25	Switch modes via the dropdown in the chat toolbar.
26
27	## Context and Mentions
28
29	- Type `@` to mention a vault file by name -- the agent reads its content.
30	- Enable "Auto-add active file" in Settings > Interface to always include the current note.
31	- Drag & drop files (images, PDFs, office docs) into the chat as attachments.
32	- Type `/` to trigger workflows and custom prompts.
33
34	## Semantic Search
35
36	Enables finding notes by meaning, not just keywords. Setup:
37
38	1. Go to Settings > Embeddings > add an embedding model (e.g. OpenAI text-embedding-3-small)
39	2. Enable "Semantic index"
40	3. Click "Build index" -- first build may take a few minutes for large vaults
41
42	Features: hybrid search (keyword + semantic + RRF fusion), knowledge graph (expands results via Wikilinks and tags), implicit connections (finds similar but unlinked notes), local reranking (cross-encoder model, runs on device).
43
44	Configure: chunk size, excluded folders, auto-index strategy (startup, on change, manual), graph expansion hops, MOC properties, similarity threshold.
45
46	## Memory
47
48	3-tier system: Session (auto-extracted after each conversation), Long-term (durable facts promoted over time), Soul (core preferences and personality).
49
50	Setup: Settings > Memory > enable memory, choose a cheap model for extraction (e.g. Haiku, gpt-4o-mini), set minimum messages threshold.
51
52	Chat history is browseable via the history panel (clock icon). Conversations can be restored and continued.
53
54	Chat-Linking: every note the agent touches gets an `obsilo-chat` frontmatter field linking back to the conversation. Click it to jump back to the chat.
55
56	## Permissions and Safety
57
58	By default, the agent asks before any write operation (fail-closed). You see an approval card showing exactly what it wants to do.
59
60	Enable auto-approve per category in Settings > Auto-Approve: read, note edits, vault changes, web, MCP, mode switching, subtasks, sandbox.
61
62	Checkpoints: every file is backed up before the agent modifies it. After a task, the undo bar lets you restore all changes with one click. The diff review modal lets you keep/undo/edit per file.
63
64	Ignore files: create `.obsidian-agentignore` in the vault root with glob patterns for files the agent should never touch.
65
66	## Skills, Rules, and Workflows
67
68	- Rules: Always-on constraints in `.obsidian-agent/rules/`. Example: "always respond in German".
69	- Skills: Context-sensitive instructions in `.obsidian-agent/skills/{name}/SKILL.md`. Auto-activated when relevant. Example: a "meeting-notes" skill that activates when discussing meetings.
70	- Workflows: Step-by-step sequences triggered by `/workflow-name` in chat. Stored in `.obsidian-agent/workflows/`.
71	- Custom Prompts: Text templates with `{{userInput}}` and `{{activeFile}}` variables, triggered via `/`.
72
73	Create any of these in the corresponding Settings tab.
74
75	## Office Documents
76
77	Ask the agent to create PPTX, DOCX, or XLSX files

People who liked this also viewed

6 picks

Type