Claude Agent Skill · by Supermemoryai

Super Search

Install Super Search skill for Claude Code from supermemoryai/claude-supermemory.

Install
Terminal · npx
$npx skills add https://github.com/supermemoryai/claude-supermemory --skill super-search
Works with Paperclip

How Super Search fits into a Paperclip company.

Super Search drops into any Paperclip agent that handles this kind of work. Assign it to a specialist inside a pre-configured PaperclipOrg company and the skill becomes available on every heartbeat — no prompt engineering, no tool wiring.

S
SaaS FactoryPaired

Pre-configured AI company — 18 agents, 18 skills, one-time purchase.

$27$59
Explore pack
Source file
SKILL.md46 lines
Expand
---name: super-searchdescription: Search your coding memory. Use when user asks about past work, previous sessions, how something was implemented, what they worked on before, or wants to recall information from earlier sessions.allowed-tools: Bash(node:*)--- # Super Search Search Supermemory for past coding sessions, decisions, and saved information. ## How to Search Run the search script with the user's query and optional scope flag: ```bashnode "${CLAUDE_PLUGIN_ROOT}/scripts/search-memory.cjs" [--user|--repo|--both] "USER_QUERY_HERE"``` ### Scope Flags - `--both` (default): Search both personal session and project memories across team members in parallel- `--user`: Search personal/user memories across sessions- `--repo`: Search project/repo memories across team members ## Examples - User asks "what did I work on yesterday":   ```bash  node "${CLAUDE_PLUGIN_ROOT}/scripts/search-memory.cjs" "work yesterday recent activity"  ``` - User asks "how did we implement auth" (project-specific):   ```bash  node "${CLAUDE_PLUGIN_ROOT}/scripts/search-memory.cjs" --repo "authentication implementation"  ``` - User asks "what are my coding preferences":  ```bash  node "${CLAUDE_PLUGIN_ROOT}/scripts/search-memory.cjs" --user "coding preferences style"  ``` ## Present Results The script outputs formatted memory results with timestamps and relevance scores. Present them clearly to the user and offer to search again with different terms if needed.