From oh-my-obsidian
Searches an Obsidian vault for past decisions, troubleshooting history, and project knowledge when the user asks about previous work or how something was done. Supports keyword, type-aware, and catalog search.
How this skill is triggered — by the user, by Claude, or both
Slash command
/oh-my-obsidian:recallThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
You should proactively activate this skill when the user asks questions that imply they need
You should proactively activate this skill when the user asks questions that imply they need historical context about the project — past decisions, previous implementations, resolved issues, or any knowledge that should exist in the team's Obsidian vault.
Check Environment
Verify $OBSIDIAN_VAULT is set and the directory exists.
If not set, inform the user and suggest running /oh-my-obsidian:setup.
Search Strategy
session-catalog.json first for fast in-memory
keyword matching. If matches have generated documents, read those .md files for excerpts.
If matches have no documents yet, show catalog metadata (date, firstUserMessage, tools).
node "$PLUGIN_ROOT/plugins/oh-my-obsidian/scripts/vault-ops.mjs" recall --query "<query>"
The recall helper automatically uses the catalog when available.type:decision or type:troubleshooting for more precise matching.
Type mapping: 세션기록→session-log, 의사결정→decision, 트러블슈팅→troubleshooting, 회의록→meeting-notesgrep -ril "keyword1\|keyword2" "$OBSIDIAN_VAULT" --include="*.md"
Search across both layers:
Result Processing
Output Format
📋 회상 결과
[의사결정] YYYY-MM-DD — 제목 (type: decision)
> 관련 내용 발췌...
[트러블슈팅] YYYY-MM-DD — 제목 (type: troubleshooting)
> 관련 내용 발췌...
Integration After presenting recalled context, proactively connect it to the user's current question. "이전에 X라고 결정했는데, 현재 상황에서도 동일하게 적용할까요?"
npx claudepluginhub hongdangmoo49/oh-my-obsidian --plugin oh-my-obsidianSearches an Obsidian vault for prior knowledge, past decisions, and accumulated learnings, surfacing relevant notes before answering from general knowledge. Uses index-first retrieval with fallback content search.
Searches sayou workspace for past decisions, research, notes via structured path/frontmatter, content grep, and semantic search. Useful for recalling prior workspace knowledge.
Implements 3-layer memory search workflow to recall past work, decisions, errors, and project history token-efficiently via layered functions.