Skill All skills & plugins / Awesome Copilot skills (GitHub)
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.
- Type
- Skill
- Catalog
- Awesome Copilot skills (GitHub)
- Source
- github/awesome-copilot/skills/mini-context-graph (15 files scanned)
- Install and details
- Agent Skills Index entry
- License
- not stated in the folder or manifest (the repository license may apply)
- Signals
- Bundled scripts
Pre-approved tools
No allowed-tools or tools list in its SKILL.md, command or agent files, so the agent asks before using tools as usual.
Hooks
No hooks.
MCP servers and apps
None.
Bundled code
10 code files (Python):
mini-context-graph/scripts/config.pymini-context-graph/scripts/contextgraph.pymini-context-graph/scripts/template_agent_workflow.pyscripts/tools/__init__.pyscripts/tools/retrieval_engine.pyscripts/tools/documents_store.pyscripts/tools/ontology_store.pyscripts/tools/index_store.pyscripts/tools/wiki_store.pyscripts/tools/graph_store.py
Network calls
No HTTP or socket call pattern found in the code.
Starts other programs
No subprocess, exec or eval pattern found.
Credentials referenced
No key, token or secret environment variable found in code or MCP config.
Static scan of commit d75b418 on 2026-10-27. Signals are patterns found in the files, not a verdict: a network call can be the whole point of a skill. Read the linked lines before you decide. How the scan works.