Build a persistent interlinked Markdown knowledge wiki from ingested sources.
npx skills add https://github.com/ruiyangruiyi/hermes-agent --skill llm-wiki-ruiyangruiyi
Please help me install this Agent Skill. Skill: llm-wiki Source: https://github.com/ruiyangruiyi/hermes-agent/tree/main/skills/research/llm-wiki Command: npx skills add https://github.com/ruiyangruiyi/hermes-agent --skill llm-wiki-ruiyangruiyi
This Skill solves the problem of repeatedly answering questions by re-deriving knowledge from scratch by building a persistent, interlinked Markdown knowledge base that stays current over time.
Tell the agent: create a new wiki in the folder you choose and ingest these sources: a few links or files, then ask it to propose the first set of entity and concept pages to organize the knowledge.
High-intent search queries and answers about installing and using this skill.
To build a persistent knowledge wiki, ingest articles, papers, and transcripts into an Obsidian-compatible directory. The system extracts entities and concepts, enforcing Markdown frontmatter and cross-linking to compile interlinked understanding instead of re-deriving it.
Maintaining a Markdown knowledge base without duplicates requires an index catalog that enforces backlinks and schema conventions. The system performs deduplication against existing index entries to prevent contradictions and redundant work.
Yes, you can use an interlinked wiki as a RAG alternative by querying its compiled structure. The system answers questions using previously extracted entities and concepts, reusing compiled understanding rather than re-discovering knowledge from raw sources.
You audit a Markdown wiki by running lint and drift checks. The system enforces auditability via logs and raw sha256 drift checks, flagging broken links, missing index entries, and low-confidence or contested claims.
Yes, this knowledge base tool works with Obsidian-compatible directory structures. It organizes raw sources, entity pages, concept pages, comparisons, and query results using standard Markdown with enforced frontmatter and cross-linking.
To ingest URLs and PDFs into an interlinked Markdown wiki, point the agent to your sources and configured WIKI_PATH. The system processes raw inputs, extracts entities, and proposes initial concept pages to organize the knowledge.
shawnpetrosConvert URLs, PDFs, markdown, and text into wikilinked vault pages.
byriderLint Obsidian wikis for orphans, dead links, and frontmatter gaps.
cxnaiveIngest raw sources into a persistent interlinked markdown knowledge base.
Simon-Copilot-StudioIngest sources into an interlinked markdown knowledge base with cross-links.
