This skill should be used when the user asks "how should I...", "what's the best approach...", "do you remember...", "why did we...", mentions "last time", "before", "we discussed", or when stuck after investigation. Searches conversation history using claude-mem 3-layer workflow.
From menpx claudepluginhub baleen37/bstack --plugin bstackThis skill uses the workspace's default tool permissions.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Search conversation history to find past decisions, patterns, and failed approaches before reinventing.
Search before reinventing. Searching costs nothing; reinventing or repeating mistakes costs everything.
After understanding the task:
When stuck:
Historical signals:
Don't search first:
ALWAYS follow this workflow to save 10x tokens:
mcp__plugin_claude-mem_mcp-search__search
query, limit, dateStart, dateEndmcp__plugin_claude-mem_mcp-search__timeline
query or anchor, depth_before, depth_aftermcp__plugin_claude-mem_mcp-search__get_observations
ids (required array)NEVER fetch full details without filtering first.
{ query: "authentication" }