Graph Extraction — Development skill for Claude Code
You are building a knowledge graph from a set of facts in a personal knowledge base.
How to install Graph Extraction
Installs to ~/.claude/skills/anmol-srv-sigil-graph-extraction/SKILL.md
mkdir -p ~/.claude/skills/anmol-srv-sigil-graph-extraction && curl -fsSL https://raw.githubusercontent.com/Anmol-Srv/sigil/HEAD/prompts/graph-extraction.md -o ~/.claude/skills/anmol-srv-sigil-graph-extraction/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Graph Extraction does
You are building a knowledge graph from a set of facts in a personal knowledge base. In a SINGLE pass you extract two things together:
- Entities — the distinct topics, concepts, technologies, systems, products, or named things the facts are about.
- Relationships — the directed connections between those entities that the facts assert.
Extracting both together keeps them consistent: every relationship's endpoints should be entities you also list.
Entities
- Extract 3-8 meaningfu
Alternatives in Development
- L Review Extract — Review Code for Extraction Opportunities 3k ★
- Zeroshot — Runs coding agents as a graph: one agent implements, independent agents review, failures go to repair, and not 1.9k ★
- Rb Refresh — Rebuild the repobrain project knowledge base after significant changes 1.3k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Default Extraction
You are extracting structured facts from a document in a personal knowledge base. Extract every discrete, atom
Extract Takes
You are a belief-extraction pass for a personal knowledge base. Your job is to
Extract Fact
Extract durable facts from this conversation (or recent Claude Code sessions) and add them to the knowledge qu
Audm Decision
You are comparing two facts from an organizational knowledge base. Decide if the NEW fact should be added as a
Flush Extract
You are a knowledge extraction agent. You will be given the full context of a Claude Code conversation session
Entity Extraction
Skill for extracting structured entities from source material — people, projects, technologies, decisions — an
Related Agents
Thinking Partner
Intellectual conversationalist who embodies the knowledge base as personal memory. Engages as an equal thinkin
Hermes Agent
Integration file for a Hermes-style personal agent system. Use when a Hermes deployment (a self-hosted assista
Extractor
Cheap structured extraction. Capabilities - extract, classify, summarise-single-source, structured-output. Use