메뉴
Semantic memory search across all agent memories and conversation history. Use BEFORE answering questions about prior work, decisions, dates, people, preferences, projects, or past conversations. Also use when asked "do you remember", "what did we discuss", "when did we", etc.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Double-model verification gate before declaring a build/research/refactor "done". Runs a fresh Anthropic (Claude) review AND an independent OpenAI/Azure critic against the stated goal + criteria, then reconciles. Use before announcing completion of medium/major builds, refactors, major fixes, research deliverables, frontend work, or trade-decision rigor — and on demand via /verify. Skip for small Q&A and trivial edits.
Record and retrieve Architecture Decision Records — log a decision's context, options, rationale, and tradeoffs, then list/search them. Use when making a non-trivial design or architecture decision, choosing between tools/approaches, or asked 'why did we do it this way?'
Queue an external action (Telegram message, shell command, GitHub comment, PR merge, file write) for the user's explicit approval before it runs. Use when you want to take an outward-facing or irreversible action that needs sign-off first.
Run a structured multi-position debate over an analytical question, spawning sub-agents to argue each option and counter confirmation bias. Use when comparing options or tradeoffs — 'which is better', 'should we', 'what's the risk', 'evaluate', 'compare options'.
Ingest documents (URLs, local files, PDFs) into a searchable local knowledge base and query stored knowledge. Use when ingesting or storing documents, searching previously stored knowledge, or building research context.
Collect macro market and economic-calendar data (yfinance + FairEconomy API) into a SQLite DB and generate a formatted macro briefing for Telegram. Use when producing a macro/markets briefing or collecting macro market data.
| name | memory-search |
| description | Semantic memory search across all agent memories and conversation history. Use BEFORE answering questions about prior work, decisions, dates, people, preferences, projects, or past conversations. Also use when asked "do you remember", "what did we discuss", "when did we", etc. |
You have a vector memory search system that indexes:
ALWAYS search before answering about:
# Basic search
node --experimental-sqlite ~/.claude-agent/scripts/memory-search.cjs --search "your query here"
# Filter by source (memory files only, sessions only, cross-agent only)
node --experimental-sqlite ~/.claude-agent/scripts/memory-search.cjs --search "query" --source memory
node --experimental-sqlite ~/.claude-agent/scripts/memory-search.cjs --search "query" --source session
node --experimental-sqlite ~/.claude-agent/scripts/memory-search.cjs --search "query" --source cross-agent
# Filter by agent
node --experimental-sqlite ~/.claude-agent/scripts/memory-search.cjs --search "query" --agent kite
node --experimental-sqlite ~/.claude-agent/scripts/memory-search.cjs --search "query" --agent argus
# More results
node --experimental-sqlite ~/.claude-agent/scripts/memory-search.cjs --search "query" --limit 15
# JSON output (for parsing)
node --experimental-sqlite ~/.claude-agent/scripts/memory-search.cjs --search "query" --json
Each result shows:
memory (your files), session (conversation transcripts), cross-agent (Kite/Poe/Argus)Higher scores = more relevant. Results above 0.3 are usually meaningful.
The index updates automatically via cron (every 30 min). To force a reindex:
# Incremental (only changed files — fast)
node --experimental-sqlite ~/.claude-agent/scripts/memory-search.cjs --index --incremental
# Full reindex (re-embeds everything — slower, costs API calls)
node --experimental-sqlite ~/.claude-agent/scripts/memory-search.cjs --index
OPENAI_API_KEY in environment~/.claude-agent/data/memory.sqlite