메뉴
Find related notes via semantic search and weave links. Stage 4 of the processing pipeline.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when investigating an agent-harness CLI's internals (Claude Code, codex, opencode, or similar): extracting the system prompt or tool descriptions, finding what code path produces a specific UI message, decoding minified function names or Rust symbols, understanding undocumented config keys, or otherwise spelunking a shipped binary (or its pinned source) to figure out how the tool actually behaves.
Use when about to lock in a non-trivial or hard-to-reverse decision, fire AskUserQuestion to offload a call, proceed on your own preferred option, or assert something is done / found / tested / fixed / "that's how it works" — especially when the basis is memory, the handoff, the first framing, or an unchecked assumption rather than something verified this session. Also invoked as /gut-check. Use even when you feel confident; confidence is the symptom, not the all-clear.
Obsidian vault mechanics - wiki links, .obsidian/ config, daily notes, plugins. Use when working with Obsidian vaults or structured markdown.
Analyze an enriched note and route to the best vault destination. Stage 3 of the processing pipeline.
Diagnose and fix LSP setup for the current project's detected ecosystems (Rust, TypeScript, Ruby). Use when the SessionStart hook nudged about a missing LSP plugin, when the env isn't ready (no `bundle install`, no `cargo build`, missing server binary), when LSP calls are failing, or when the user invokes `/actually-lsp-doctor` directly. Walks the per-ecosystem state machine, reports what's missing, then runs the fix.
Use when structuring prose so readers can skim it - drafting or restructuring READMEs, docs, PR or issue bodies, design docs, RFCs, or any long-form text where a wall of prose hides the structure. Also use when explicitly asked to make something scannable or skimmable, convert prose to a list, surface a buried list, fix a wall of text, or decide whether bullets or prose fit. Strong signal: text with parallel sentence shapes, contrast markers ("that's distinct from", "versus"), bolded terms followed by colons, or an embedded "X, Y, and Z" series. Composes with prose-clarity skills (concision) and voice skills (personality) rather than replacing them. Skip for source code and for casual one-line replies where formatting reads as overkill.
| name | connect |
| description | Find related notes via semantic search and weave links. Stage 4 of the processing pipeline. |
| allowed-tools | ["Read(~/.claude/vaults/**/*.md)","Write(~/.claude/vaults/**/*.md)","Edit(~/.claude/vaults/**/*.md)","Bash(which:qmd)","Bash(qmd:query *)","Bash(qmd:collection list)","Bash(qmd:get *)","Bash(qmd:status)"] |
Find related notes via semantic search (qmd) and weave forward/backward links.
See references/pipeline.md for stage definitions and status flow.
See references/connecting.md for the connection discovery algorithm.
A routed note with status: routed.
Check qmd availability:
which qmd
If not available, log "Skipped connections: qmd not available", set status: connected, and return.
Extract query terms from the note's title and body
Run semantic search:
qmd query "{terms}" -c {collection} -n 15 --json
Filter and rank per references/connecting.md:
If candidates found, present to human (when called by orchestrator):
For selected connections:
## Related section to the note with wiki-linksUpdate status to connected
## Related section added (if connections found)status: connected