Llm Wiki
Let your coding agent query pages, files, and the wikilink graph in the locally running LLM Wiki desktop app over its HTTP API.
Overview
LLM Wiki is an agent skill most often used in Build (also Idea research and Operate) that queries the user’s local LLM Wiki knowledge base via its HTTP API for search, reads, and graph navigation.
Install
npx skills add https://github.com/nashsu/llm_wiki_skill --skill llm-wikiWhat is this skill?
- Triggers only when the user explicitly names LLM Wiki, “my wiki”, 知识库, or a wiki project—not generic Obsidian/Notion not
- Read-only wiki operations plus optional source rescan to refresh indexed raw sources
- Standard JSON HTTP API—use curl, fetch, or requests; no SDK required
- Covers page search, file listing, content read, and knowledge-graph navigation for wiki/**.md and raw/sources/
- Treats the wiki as a private structured PKM graph the user has been curating
- Default local API endpoint documented at 127.0.0.1:19828
- Read-only operations except explicit source rescan
Adoption & trust: 3 installs on skills.sh; 59 GitHub stars; 3/3 security scanners passed (skills.sh audits); trending (+200% hot-view momentum).
What problem does it solve?
Your agent cannot see the structured pages and wikilinks you keep in LLM Wiki unless something calls the desktop app’s local API on your behalf.
Who is it for?
Solo builders who run the LLM Wiki desktop app and want agents to ground replies in that wiki—not Obsidian, Notion, or other note apps.
Skip if: Generic note search, cloud wikis without the local LLM Wiki app, or workflows where the user never names LLM Wiki or 知识库 explicitly.
When should I use this skill?
User explicitly names LLM Wiki, my wiki, 知识库/knowledge base, a wiki project ID, or asks for wiki search/graph/rescan—not generic other-note-app queries.
What do I get? / Deliverables
The agent returns answers, page content, and graph context from your LLM Wiki project, or triggers a source rescan when you ask to re-index raw files.
- Wiki search and page content excerpts
- Knowledge graph navigation results
- Rescan confirmation when re-index is requested
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Build because the skill is an agent integration that calls a local service while you ship product work, not a standalone research methodology. Integrations fits HTTP calls to 127.0.0.1:19828 for search, read, graph navigation, and optional source rescan.
Where it fits
Ask what your wiki already captured about a competitor before starting a new validation doc.
Pull the canonical API contract page from wiki/**.md while implementing an endpoint.
List files in a wiki project to see which raw sources were indexed for a prototype scope.
Search runbook pages after an incident to align the agent with your written procedures.
Cross-check release checklist pages stored in the wiki before tagging a version.
How it compares
Use this local HTTP integration instead of pretending the agent can read your PKM vault without a named LLM Wiki trigger.
Common Questions / FAQ
Who is llm-wiki for?
Indie builders and agent users who curate knowledge in the LLM Wiki desktop app and want coding agents to search and read that graph safely on localhost.
When should I use llm-wiki?
Use it in Build when implementing against wiki-stored specs, in Idea when asking what your wiki says about a market or topic, and in Operate when pulling runbooks—only after the user names LLM Wiki, my wiki, or 知识库.
Is llm-wiki safe to install?
It targets a local service and is read-only except rescan; review the Security Audits panel on this Prism page and restrict network use to your machine before enabling in production agent profiles.
SKILL.md
READMESKILL.md - Llm Wiki
# LLM Wiki Local API Skill Talk to the user's locally-running LLM Wiki app over its built-in HTTP API. This is a **standard JSON API** — call it directly with whatever HTTP tool is already in your environment (`curl`, `fetch`, `requests`, `http` middleware, etc.). No client library to install, no SDK to learn. Treat the wiki as a **private, structured knowledge base** the user has been curating: pages live as `wiki/**.md`, raw documents under `raw/sources/`, wikilinks form a graph. ## When to invoke Invoke **only** when the user is clearly referring to **LLM Wiki** specifically — by app name, by `wiki` framing, or by `知识库` framing. Concretely: - asks a question framed as "what does my **wiki** / my **knowledge base** / 我的**知识库** / **LLM Wiki** say about X" - asks to "search **my wiki** / **LLM Wiki** project / 我的**知识库** for X" - references a **wiki page** by stem / title and wants to read or cross-link - asks for the **wiki graph / 知识图谱 / wiki overview / wiki structure** - has just added or edited files under the LLM Wiki **source folder** and wants ingest re-run / **重新索引** - says "use **my wiki** for context" / "ground your answer in **my wiki**" / "check **my LLM Wiki**" - names a wiki project (by ID, by absolute path, or by `current`) **Do NOT invoke when the user says:** - "search **my notes**" without further qualification — likely Obsidian / Apple Notes / Notion / Logseq / Bear / etc. - "find in **my notebook**" — likely Jupyter / OneNote / Notability - "check **my Obsidian / Notion / Roam / Logseq vault**" — explicitly a different tool - "look up **my Anki / Readwise / Pocket**" — different tool - "search **my files / my Documents folder**" — generic filesystem, not the wiki - general world knowledge, current events, or anything the user clearly wants from the open web When in doubt about which knowledge tool the user means, ask: *"Do you mean your LLM Wiki specifically, or another tool?"* — don't silently call the LLM Wiki API on what might be an Obsidian vault. ## Quick start The whole API is plain HTTP + JSON. The fastest path: ```bash BASE=http://127.0.0.1:19828 TOKEN="${LLM_WIKI_API_TOKEN:-<paste-from-Settings>}" # 1. probe state — no auth needed curl -s $BASE/api/v1/health # 2. list projects curl -s -H "Authorization: Bearer $TOKEN" $BASE/api/v1/projects # 3. search curl -s -H "Authorization: Bearer $TOKEN" \ -H 'Content-Type: application/json' \ -d '{"query":"rope embedding","topK":5}' \ $BASE/api/v1/projects/current/search # 4. read a page curl -s -H "Authorization: Bearer $TOKEN" \ "$BASE/api/v1/projects/current/files/content?path=wiki/concepts/rope.md" ``` If you're writing TypeScript / JavaScript: ```ts const res = await fetch("http://127.0.0.1:19828/api/v1/projects/current/search", { method: "POST", headers: { "Authorization": `Bearer ${process.env.LLM_WIKI_API_TOKEN}`, "Content-Type": "application/json" }, body: JSON.stringify({ query: "rope embedding", topK: 5 }), }) const { results } = await res.json() ``` Python is the same shape — `urllib.request`, `requests`, `httpx`, whatever you already have. **Don't install anything new.** ## Auth model The API is **localh