Symbol memory
Use when working in Python repositories that already use `@symbol(...)` and `.symbol_memory` artifacts. Build or validate first, navigate with symbol ids, and respect the manual relation graph.From its SKILL.md
npx -y skills add Madikhan33/Symbol --skill symbol-memoryAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
- runs commandsInstructs the agent to run 7 commands, including `symbol-memory build .` and 6 more.
SKILL.md
1.3 KB, 219 tokens by cl100k_base, as published. Nobody here has run it
Symbol Memory
Use this skill when a Python project already uses symbol_memory annotations and generated artifacts.
Rules
- Build or validate before trusting symbol memory data.
- Prefer
find,relations, andopenbefore broad repository grep. - Treat
.symbol_memory/as generated output unless the user explicitly asks to inspect artifacts. - Do not invent relations. Links come only from manual
r=[...]. - If a symbol is not annotated, do not assume it exists in symbol memory.
- Rebuild after edits that move, add, remove, or renumber annotated symbols.
Core Workflow
symbol-memory build .
symbol-memory validate .
symbol-memory list --project-root .
symbol-memory find QUERY --project-root .
symbol-memory show ID --project-root .
symbol-memory relations ID --project-root .
symbol-memory open ID --project-root .
Response Behavior
- Prefer symbol ids, exact paths, and exact line ranges.
- Surface validation errors before relying on stale artifacts.
- Use raw text search only after symbol-memory navigation is exhausted.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.