Menu

Individual skill

llm-wiki

0upvotes

Maintain a persistent LLM wiki in Logseq or Obsidian. Subcommands - setup (one-time, creates the wiki), ingest a source into wiki pages, query the wiki, prune cold pages or stale L1 rules, lint, status, import existing notes.

SKILL.md

Read pinned source

Source commit 5fa5ee7d49a4346eeb1d92c1de7bf649e7654e91

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
168
Repository last updated
Nov 7, 2026
License
MIT

Observed agent integration: claude-code, codex

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# /llm-wiki - LLM Wiki

Persistent knowledge management powered by Claude Code. Maintains a structured wiki in Logseq or Obsidian using the L1/L2 cache architecture.

**Architecture: L1/L2 Cache Model**
- L1 = Claude Memory (auto-loaded): Rules, gotchas, identity, credentials
- L2 = Wiki (on-demand): Projects, workflows, research, deep knowledge

**Two cache mechanisms keep L2 precise as it grows:**
- **Hub-Index-Routing** — L1's auto-loaded memory index has no L2 counterpart by default. Each hub page
  carries an `### Index` of routing lines (one per child: `[[link]] -- description #tags`). `query`
  becomes two-stage: read the cheap hub indexes -> pick the 3 most relevant pages by description ->
  read only those full pages. This is the wiki's "page table / TLB" — no more grep-over-everything.
- **LRU-Demote** — `query` logs every page hit; `prune` evicts cold pages (no access in N months) from
Back to top