LLM Wiki — Build a Compounding Knowledge Base with LLMs
v1.0.0Manage a living Markdown knowledge base by ingesting sources, updating entity, concept, and synthesis pages, and linking insights with explicit relationships.
⭐ 0· 20·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description match the SKILL.md: it is an agent-facing workflow for ingesting sources and maintaining a Markdown/Obsidian-style wiki. There are no unrelated environment variables, binaries, or install steps requested.
Instruction Scope
All runtime instructions refer to local vault paths (source/, wiki/, schema/) and file-level operations (create/update/index/log). This is appropriate, but the skill explicitly delegates ownership of the wiki layer to the LLM, meaning the agent will create, update, link, deduplicate, and archive multiple files. Users should expect broad write activity in the specified directories and should ensure that permission/backup practices match that expectation.
Install Mechanism
No install spec or code files are present (instruction-only). This minimizes install-time risks because nothing is downloaded or written to disk by an installer.
Credentials
The skill declares no required environment variables, credentials, or config paths. The SKILL.md does not instruct the agent to access secrets or unrelated system configuration.
Persistence & Privilege
always:false (default) and autonomous invocation is allowed (the platform default). Autonomous invocation combined with broad write access to the wiki directory means the agent can make changes without interactive confirmation unless the user configures otherwise — this is expected but worth noting as a behavioral/operational risk to manage.
Assessment
This skill is coherent and does what it says: it will read files from a source/ directory and write and maintain many Markdown files under wiki/. Before installing, back up your vault (use git or another backup), run the skill first on a small test vault, and review diffs so you can inspect what the agent writes. If you want stricter control, require the agent to ask for confirmation before renames/overwrites or disable autonomous invocation for this skill. Do not give it credentials or broader filesystem access beyond the directories you intend it to manage. If sensitive data exists in your sources, consider sanitizing or keeping it out of the vault used with this skill.Like a lobster shell, security has layers — review code before you run it.
latestvk97fbd76mgjb5xvnnp2cw689x184p0fv
License
MIT-0
Free to use, modify, and redistribute. No attribution required.