llm-wiki
v1.0.0Use when the user is working inside an Obsidian or markdown vault and wants to ingest sources, query accumulated knowledge, or maintain a Karpathy-style LLM...
⭐ 0· 14·0 current·0 all-time
byAGICaptain@javastarboy
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the SKILL.md behavior: building and maintaining a persistent LLM-written markdown wiki for an Obsidian-style vault. There are no unexpected binaries, env vars, or install steps requested that would be unrelated to the stated purpose.
Instruction Scope
The SKILL.md is an extensive policy/pattern for the agent to follow (ingest sources, write/maintain markdown pages, update cross-references). It does not itself request secrets or install tools, but it is intentionally open-ended about directory layout, tooling, and how the agent should access the user's vault. That openness means the agent will likely prompt for or expect filesystem access and write permission to the wiki directory; users should explicitly control and review any such access before granting it. The skill does not appear to instruct the agent to read unrelated system files or exfiltrate data.
Install Mechanism
Instruction-only skill with no install spec and no code files. This is the lowest-risk install model: nothing is downloaded or written by the skill itself during installation.
Credentials
No required environment variables, no credentials or config paths declared. The SKILL.md's operations (reading user-provided sources, writing wiki files) are consistent with not needing external API keys. If you later connect the agent to third-party services (syncing, plugins, or cloud backups), additional credentials would be expected then — but they are not requested here.
Persistence & Privilege
always:false and no install-time persistence. The skill does change the agent's active collaboration mode while loaded (per its own instruction), which is expected for an instruction-only skill. It does not request permanent platform-level privileges.
Assessment
This skill is essentially a large, opinionated prompt describing how to run an LLM-managed Obsidian wiki — it is coherent and doesn't request secrets or installs. Before using it, explicitly decide and control how the agent will access your vault: grant only the minimum filesystem permissions (or test on a copy), require the agent to ask for write/delete confirmation before modifying files, and maintain a version-controlled backup of your vault. If you plan to connect cloud sync, plugins, or external APIs later, treat those credentials separately and only provide them when you understand why they are needed. If you prefer the agent not to act autonomously on your files, disable autonomous execution or require explicit user approval for each ingest/update.Like a lobster shell, security has layers — review code before you run it.
latestvk97a9cgv66y18nr2pdx7n7r61h851ayw
License
MIT-0
Free to use, modify, and redistribute. No attribution required.