npx claudepluginhub iamtouchskyer/memex --plugin memexThis skill uses the workspace's default tool permissions.
You have access to a Zettelkasten memory system via the `memex` CLI. Before starting this task, search your memory for relevant prior knowledge.
Saves distilled insights from completed coding tasks to Zettelkasten memory via memex CLI. Use after code changes, architecture, debugging, or problem-solving.
Retrieves project memory for user queries via three-step fallback: ROOT.md topics triage, frontmatter manifest LLM selection from weekly/monthly notes, qmd search. Use when past knowledge may apply.
Stores and retrieves persistent notes via basic-memory CLI with semantic search, context building for topics, and recent activity listing across sessions.
Share bugs, ideas, or general feedback.
You have access to a Zettelkasten memory system via the memex CLI. Before starting this task, search your memory for relevant prior knowledge.
Three equivalent interfaces — use whichever your environment supports:
| CLI (memex in PATH) | Plugin CLI fallback (Claude Code) | MCP tool (VSCode / Cursor) |
|---|---|---|
memex read index | node ~/.claude/plugins/cache/cc-plugins/memex/*/dist/cli.js read index | memex_read with slug index |
memex search <q> | node ~/.claude/plugins/cache/cc-plugins/memex/*/dist/cli.js search <q> | memex_search with query arg |
memex read <slug> | node ~/.claude/plugins/cache/cc-plugins/memex/*/dist/cli.js read <slug> | memex_read with slug arg |
memex search (no args) | node ~/.claude/plugins/cache/cc-plugins/memex/*/dist/cli.js search | memex_search with no args |
Resolution order: Try memex in PATH first. If not found, define a shell function and use it:
memex() { node $HOME/.claude/plugins/cache/cc-plugins/memex/*/dist/cli.js "$@"; }
If both CLI approaches fail, use MCP tools.
The rest of this skill uses memex CLI syntax for brevity.
digraph recall {
"Task received" -> "memex read index";
"memex read index" -> "Index exists?" [shape=diamond];
"Index exists?" -> "Scan index for relevant concepts/slugs" [label="yes"];
"Index exists?" -> "Fallback: generate 2-3 search queries" [label="no"];
"Scan index for relevant concepts/slugs" -> "memex read <card>" ;
"Fallback: generate 2-3 search queries" -> "memex search <query>";
"memex search <query>" -> "Review summaries";
"Review summaries" -> "Relevant cards found?" [shape=diamond];
"Relevant cards found?" -> "memex read <card>" [label="yes"];
"Relevant cards found?" -> "More queries to try?" [label="no"];
"memex read <card>" -> "See [[links]] in content";
"See [[links]] in content" -> "Links worth following?" [shape=diamond];
"Links worth following?" -> "memex read <linked-card>" [label="yes"];
"Links worth following?" -> "Enough context?" [label="no"];
"memex read <linked-card>" -> "See [[links]] in content";
"Enough context?" -> "More queries to try?" [label="no"];
"More queries to try?" -> "Generate new query" [label="yes"];
"Generate new query" -> "memex search <query>";
"More queries to try?" -> "Summarize findings, proceed with task" [label="no"];
"Enough context?" -> "Summarize findings, proceed with task" [label="yes"];
}
Run memex read index first. The index is a curated concept → card mapping (Luhmann's Schlagwortregister). It's much smaller than all cards combined and gives you the best entry points.
If the index doesn't exist yet (card not found), fall back to Step 2.
memex read them directly.memex search <keyword> for each.When you read a card and see [[links]] in the prose, decide if they're worth following. If yes, memex read <linked-slug>.
When you have enough context, summarize your findings and proceed with the task.
memex search. Following a [[link]] from there is hop 1, etc.memex read calls. If you've read 20 cards, stop immediately.memex read index first — it's the fastest path to relevant cards