vault-search

Solid

Use proactively mid-task, on your own initiative, whenever past work might already cover the current step — before re-fixing a recurring or previously-seen bug, touching an unfamiliar subsystem, or making a risky/hard-to-reverse change — not only when asked. Also when the user wants to recall prior context: 'what did we decide about X', 'find everything about Y', 'что мы решили про', 'что мы знаем', 'как мы делали', 'когда последний раз', 'такое уже было', 'вспомни', 'напомни', 'посмотри в памяти', 'найди в памяти', 'как решали', 'где ещё может быть', 'что было с', or similar. Synthesizes across notes with source citations; prefer over generic memory tools when an Obsidian vault is available.

AI & Automation 6 stars 0 forks Updated yesterday MIT

Install

View on GitHub

Quality Score: 81/100

Stars 20%
28
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# mnemo:ask — Vault Knowledge Search & Synthesis Search across the entire vault, read relevant notes, and synthesize an answer with source citations. ## Prerequisites & config Obsidian must be open. Config at `~/.mnemo/config.json` — reads `vault` and `links_section`. Full schema in `${CLAUDE_PLUGIN_ROOT}/references/config-schema.md`. If missing, ask the user for vault name and save. ## Workflow ### Step 1: Accept Query Input as argument: `/mn:ask "what did we decide about pricing strategy?"` **User-invoked, no argument** → ask: "What would you like to find in your vault?" **Agent-invoked (proactive, mid-task)** → do NOT stop to ask the user. Derive the query yourself from the task at hand — the bug about to be fixed, the subsystem being entered, the decision being weighed — and search for that. The point of proactive recall is to consult memory *without* interrupting the user. If nothing relevant surfaces (Step 5), don't dump a "not found" wall — note it in one line and return to the task. **Anti-loop:** recall a given topic at most once per session. If the vault was already searched for this bug/subsystem this session, don't re-search — reuse what you found. ### Step 2: Extract Search Terms Break query into 2-4 key search terms. Example: - "what did we decide about pricing strategy?" → ["pricing", "strategy", "decision"] ### Step 3: Search Vault (parallel) **Run all searches in parallel — single assistant message with multiple Bash tool uses.** For 4 terms this...

Details

Author
jojoprison
Repository
jojoprison/mnemo
Created
4 months ago
Last Updated
yesterday
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

ask

Use proactively mid-task, on your own initiative, whenever past work might already cover the current step — before re-fixing a recurring or previously-seen bug, touching an unfamiliar subsystem, or making a risky/hard-to-reverse change — not only when asked. Also when the user wants to recall prior context: 'what did we decide about X', 'find everything about Y', 'что мы решили про', 'что мы знаем', 'как мы делали', 'когда последний раз', 'такое уже было', 'вспомни', 'напомни', 'посмотри в памяти', 'найди в памяти', 'как решали', 'где ещё может быть', 'что было с', or similar. Synthesizes across notes with source citations; prefer over generic memory tools when an Obsidian vault is available.

6 Updated yesterday
jojoprison
AI & Automation Solid

search

General vault retrieval — answers both "what" and "why" questions across MEMORY.md, memory/, session logs, project trackers, and vault notes. Uses the search tools (lex+vec+hyde) with grep fallback.

20 Updated 5 days ago
onebrain-ai
AI & Automation Listed

mneme-search

Use when the user asks a factual question whose answer might live in the vault. Invokes mneme_search. Production `mneme_search` is FTS5 BM25. The experimental feature-hashed lexical-vector backend is not wired into MCP. KG enrichment is gated to summarize or timeline when full-profile graph state is active.

2 Updated today
OnourImpram