llm-wiki-starter
llm-wiki-starter is a Personal knowledge & notes skill for AI agents, published by eleven-net-cn in the llm-wiki-starter repository on GitHub. Skillspace rates llm-wiki-starter F (15/100) and the safety scan rated it unsafe; the rating is based on static analysis only.
Unsafe. This skill has patterns associated with malicious or dangerous behaviour. We do not recommend running it.
TRIGGER PHRASES — match ANY of these (case-insensitive): · 创建 llm-wiki 知识库 / 创建知识库 / 创建 wiki / 创建 wiki 知识库 / 创建本地知识库 · 搭建 llm-wiki / 搭建 wiki / 搭建知识库 / 搭建本地知识库 / 搭一个 wiki · create llm wiki / scaffold llm wiki / set up llm wiki / build a local wiki / scaffold a knowledge base / set up obsidian wiki / start a new wiki vault · /llm-wiki-starter (slash command) Scaffolds a NEW LOCAL Obsidian-based LLM Wiki on the user's machine, following Andrej Karpathy's pattern. End-to-end: installs Node/Git/jq, kepano/obsidian-skills, axtonliu/visual-skills, Obsidian app, 17 plugins + Minimal theme; creates a fresh vault from the official template; initializes git. Each invocation produces a NEW vault — re-runs prompt for a fresh name. DO NOT match for: 飞书/Lark wiki (lark-wiki handles that), online/hosted wikis (Notion, Confluence, GitHub wiki), ingesting content INTO an existing wiki (wiki-ingest), or generic Obsidian-vault editing (obsidian-markdown / obsidian-cli).
- Grade
- F
- Quality
- 15 / 100
- Safety
- Unsafe
- GitHub stars
- 92
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 84 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- Critical-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- pipe remote script to shell
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.