Individual skill
mini-context-graph
A persistent, compounding knowledge base combining Karpathy's LLM Wiki pattern with a structured knowledge graph. Ingest documents once — the LLM writes wiki pages, extracts entities/relations into the graph, and stores raw content for evidence retrieval. Knowledge accumulates and cross-references; it is never re-derived from scratch.
skills/mini-context-graph/SKILL.md
Source commit edbecfa9099c4addae1f500cca1ac067204b30fd
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 4, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 40,864
- Repository last updated
- Nov 6, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai Repository topic
- github-copilot Repository topic
- prompt-engineering Repository topic
- hacktoberfest Repository topic
- agent-skills Repository topic
- agents Repository topic
- awesome Repository topic
- custom-agents Repository topic
- writing Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 8,168 bytesSKILL.mdcore · 8,168 bytesSKILL.mdcore · 8,168 bytesSKILL.mdcore · 8,168 bytesSKILL.mdcore · 8,168 bytesSKILL.mdcore · 8,168 bytesSKILL.mdcore · 8,168 bytesSKILL.mdcore · 8,168 bytesreferences/ingestion.mddoc · 5,161 bytesreferences/lint.mddoc · 4,235 bytesreferences/ontology.mddoc · 3,238 bytesreferences/retrieval.mddoc · 4,399 bytesscripts/config.pyruns · 893 bytesscripts/contextgraph.pyruns · 11,794 bytesscripts/template_agent_workflow.pyruns · 6,708 bytesscripts/tools/__init__.pyruns · 0 bytesscripts/tools/documents_store.pyruns · 5,849 bytesscripts/tools/graph_store.pyruns · 6,163 bytesscripts/tools/index_store.pyruns · 2,821 bytesscripts/tools/ontology_store.pyruns · 4,953 bytesscripts/tools/retrieval_engine.pyruns · 1,601 bytesscripts/tools/wiki_store.pyruns · 9,635 bytes
Read excerpt
# Mini Context Graph Skill
## The Core Idea
Standard RAG re-discovers knowledge from scratch on every query. This skill is different:
1. **Wiki layer** — The LLM writes and maintains persistent markdown pages (summaries, entity pages, topic syntheses). Cross-references are already there. The wiki gets richer with every ingest.
2. **Graph layer** — Entities and relations are extracted once and stored as a navigable knowledge graph. BFS traversal answers structural queries without re-reading sources.
3. **Raw source layer** — Original documents are stored immutably with chunks. Provenance links tie every graph node and edge back to the exact text that supports it.
> The LLM writes; the Python tools handle all bookkeeping.
---
