Kgskill — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Kgskill (Plugin) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
An LLM-maintained personal knowledge graph. Incrementally build a structured wiki of markdown files — reading sources, extracting knowledge, updating pages, and keeping everything connected.
Based on the LLM Wiki pattern by Andrej Karpathy.
MyKG provides tools for AI agents to maintain a persistent knowledge base:
Three-layer architecture:
# 1. Install the skill
mkdir -p ~/.opencode/skills/mykg
cp SKILL.md ~/.opencode/skills/mykg/SKILL.md
# 2. Install commands
mkdir -p ~/.config/opencode/command
cp commands/*.md ~/.config/opencode/command//plugin marketplace add https://github.com/Ethics03/kgskill
/plugin install mykg@kgskillnpx skills add https://github.com/Ethics03/kgskill.git# Copy skills into your .claude folder
cp -r skills/ ~/.claude/skills/
# Copy commands
mkdir -p ~/.claude/commands
cp commands/*.md ~/.claude/commands/The skill and commands are platform-agnostic markdown files. Adapt for your agent:
SKILL.md) — Load as system instructions or contextcommands/*.md) — Register as slash commandsThe commands are shell scripts wrapped in markdown — extract the bash sections and adapt to your platform.
/kg-init [path] # Create new KG
/kg-setup # Configure existing KG/kg-init ~/MyKGCreates:
MyKG/
├── index.md
├── log.md
├── Active.md
├── AGENTS.md
├── raw/
│ ├── articles/
│ ├── papers/
│ └── transcripts/
└── wiki/
├── entities/
├── concepts/
├── synthesis/
└── comparisons//kg-ingest raw/articles/my-article.mdThe LLM will:
/kg search <term> # Search wiki pages
/kg recent # Recent changes
/kg entities # List entities
/kg concepts # List concepts/kg-project research-paper-x "Research on quantum computing"Creates project-specific workspace with custom SKILL.md.
| Command | Description |
|---|---|
/kg-setup | Configure KG path |
/kg-init [path] | Initialize new KG |
/kg-project <name> | Create project workspace |
/kg-ingest <source> | Ingest source into wiki |
/kg-lint | Health check wiki |
/kg recent | Recent changes |
/kg search <term> | Search wiki |
/kg entities | List entity pages |
/kg concepts | List concept pages |
/kg active | Current focus items |
KG path resolved in order:
MYKG_PATH environment variable~/.config/mykg/config file~/MyKG, ~/Dev/Obsidian/MyKGRead source → extract knowledge → update wiki:
Search wiki → synthesize answer → cite sources:
[[citations]]Health check the wiki:
kgskills/
├── .claude-plugin/plugin.json # Claude Code plugin manifest
├── SKILL.md # Universal skill
├── commands/ # Slash commands
├── skills/mykg/ # Plugin skill entry (symlink to SKILL.md)
├── templates/kg-init/ # New KG scaffold
├── project-templates/init/ # New project scaffold
└── docs/
├── concepts.md
└── examples.mdLoaded once. Teaches the agent:
Loaded per-project. Contains:
Example:
MyKG/
├── index.md
├── raw/
├── wiki/
├── ProjectA/
│ ├── SKILL.md # "Research paper on X"
│ ├── raw/papers/
│ └── wiki/
└── ProjectB/
├── SKILL.md # "Reading The Lord of the Rings"
├── raw/chapters/
└── wiki/Install skills from kepano/obsidian-skills for enhanced mykg workflows:
| Skill | Benefit |
|---|---|
obsidian-markdown | Correct wikilink, frontmatter, and callout syntax when writing wiki pages |
obsidian-cli | Open and search notes directly when the KG lives in an Obsidian vault |
defuddle | Clean markdown extraction from URLs when ingesting web sources |
This pattern is inspired by Andrej Karpathy's approach to knowledge management. His insight was that knowledge bases should be living artifacts that grow with you — not static repositories that rot.
The insight: LLMs are great at the tedious work — touching 15 files in one pass, maintaining consistency, updating cross-references. They don't get bored.
I extended this with project-specific customization. A research project needs different entity types than reading a novel. The two-tier skill system lets each project have its own domain model while sharing the universal infrastructure.
This is for people who want a knowledge base that grows with them — that compounds knowledge rather than just storing it.
Credit: The core structure and philosophy come from Karpathy's work. I adapted it with the two-tier skill system for project-specific customization.
MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.