メニュー
Save the current work session to persistent memory for future context. Summarizes accomplishments, tracks files modified, and stores learnings for cross-session continuity.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/iagocavalcante/claude-turbo-search --skill rememberコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Download the persistent memory database from your self-hosted dashboard into the current repo. Use after cloning a repo on a new machine to restore accumulated sessions, knowledge, facts, and embeddings for RAG/context.
Manually upload the persistent memory database to your self-hosted dashboard. Useful after directly running add-fact or add-knowledge — for normal session work, /remember already auto-pushes.
Interactive TUI knowledge graph viewer for the persistent memory database.
SKILL.md を表示中
SOC 職業分類に基づく
| name | remember |
| description | Save the current work session to persistent memory for future context. Summarizes accomplishments, tracks files modified, and stores learnings for cross-session continuity. |
Summarize the current work session and save it to persistent memory for future context.
When the user invokes /remember, you should:
First, check if there's an activity log from this session:
REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || echo "$PWD")
ACTIVITY_FILE="$REPO_ROOT/.claude-memory/activity.log"
if [ -f "$ACTIVITY_FILE" ]; then
cat "$ACTIVITY_FILE"
fi
Review what was accomplished in this conversation:
When writing summaries, facts, or knowledge entries, follow these rules to maximize information density:
The system automatically compresses text at write time (normalizing dates, stripping filler), but writing clean summaries upfront produces better results.
Create a concise summary (2-3 sentences) that captures:
Identify:
Use the memory-db.sh script to save:
PLUGIN_DIR="${PLUGIN_DIR:-$HOME/claude-turbo-search}"
MEMORY_SCRIPT="$PLUGIN_DIR/memory/memory-db.sh"
# Initialize if needed
"$MEMORY_SCRIPT" init
# Save session
"$MEMORY_SCRIPT" add-session \
"YOUR_SUMMARY_HERE" \
'["file1.ts", "file2.ts"]' \
'["Read", "Edit", "Bash"]' \
"topic1, topic2, topic3"
If during the session you learned something important about the codebase that should be remembered:
For code area knowledge:
"$MEMORY_SCRIPT" add-knowledge \
"src/auth" \
"Authentication module using JWT tokens with refresh token rotation" \
"Tokens expire in 15min, refresh tokens in 7 days"
For project facts:
"$MEMORY_SCRIPT" add-fact "Uses PostgreSQL with Prisma ORM" "architecture"
"$MEMORY_SCRIPT" add-fact "All API routes require authentication except /health" "convention"
Before clearing the activity log, calculate and persist token metrics for this session:
PLUGIN_DIR="${PLUGIN_DIR:-$HOME/claude-turbo-search}"
MEMORY_SCRIPT="$PLUGIN_DIR/memory/memory-db.sh"
REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || echo "$PWD")
ACTIVITY_FILE="$REPO_ROOT/.claude-memory/activity.log"
if [ -f "$MEMORY_SCRIPT" ] && [ -f "$ACTIVITY_FILE" ]; then
# Get the session ID just saved (most recent)
SESSION_ID=$("$MEMORY_SCRIPT" recent 1 2>/dev/null | grep -o '"id":[0-9]*' | head -1 | grep -o '[0-9]*')
if [ -n "$SESSION_ID" ]; then
SEARCHES=$(grep -c "SEARCH:" "$ACTIVITY_FILE" 2>/dev/null || echo "0")
READS=$(grep -c "|Read|" "$ACTIVITY_FILE" 2>/dev/null || echo "0")
EDITS=$(grep -c "|Edit|" "$ACTIVITY_FILE" 2>/dev/null || echo "0")
"$MEMORY_SCRIPT" add-token-metrics "$SESSION_ID" "$SEARCHES" "$READS" "$EDITS" 2>/dev/null || true
fi
fi
This step is non-blocking — if memory-db.sh is unavailable or fails, the session save still succeeds.
If the user has configured a personal web dashboard with memory-db.sh config set, sync the updated database to it:
"$MEMORY_SCRIPT" push 2>/dev/null || true
This step is non-blocking — failures are silent. When no remote is configured, push exits with a clear error that we discard. When a remote is configured, the gzipped database is uploaded so the dashboard reflects this session immediately.
See docs/plans/web-sync.md for the dashboard architecture and web/README.md for deploy instructions.
After saving, clear the activity log:
ACTIVITY_FILE="$REPO_ROOT/.claude-memory/activity.log"
[ -f "$ACTIVITY_FILE" ] && rm "$ACTIVITY_FILE"
Report what was saved:
Saved to memory:
- Summary: [your summary]
- Topics: [topics]
- Files: [count] files tracked
Memory now contains [X] sessions. Use /memory-stats to see details.
Saved to memory:
- Summary: Implemented JWT authentication with refresh token rotation. Added middleware for protected routes and updated user model with token fields.
- Topics: auth, jwt, middleware, tokens, security
- Files: 4 files tracked
Memory now contains 12 sessions.
If the user wants to add specific knowledge or facts, they can say:
Ask clarifying questions if the summary scope is unclear.