user-convo-summary
Summarize a Warp user's agent mode conversation history to understand how they use Warp. Use when asked to profile, summarize, or investigate what a specific user has been doing in agent mode (e.g., "summarize agent mode usage for user@example.com", "what has this user been using Warp for?", "get conversation info for this user").
Source facts
- Repository
- warpdotdev/fraud-detection-agent-oss
- Last source activity
- July 6, 2026 at 02:29
- Detected SKILL.md language
- English
- Stars
- 1
- Forks
- 1
Install options
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Review the source files
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Showing SKILL.md
SKILL.md
Source instructions · Read-only preview- name
- user-convo-summary
- description
- Summarize a Warp user's agent mode conversation history to understand how they use Warp. Use when asked to profile, summarize, or investigate what a specific user has been doing in agent mode (e.g., "summarize agent mode usage for user@example.com", "what has this user been using Warp for?", "get conversation info for this user").
# User Conversation Summary
Summarize a user's agent mode history from their email address.
## Schema config
The `bq` queries below use the **default** logical mapping: project `YOUR_GCP_PROJECT`,
`core_user_facts` (dataset `prod`) and `agent_mode_messages_ugc` (dataset
`prod_ugc`). Replace them with your physical names from
`config/schema.json` (see `SCHEMA.md`).
## Step 1: Look Up user_id
```bash
bq query --use_legacy_sql=false --format=csv \
"SELECT user_id FROM \`YOUR_GCP_PROJECT.prod.core_user_facts\`
WHERE user_email = '[USER_EMAIL]' LIMIT 1"
```
## Step 2: Fetch Recent Conversations
```bash
bq query --use_legacy_sql=false --format=csv \
"SELECT conversation_id, message_type, timestamp_utc, msg_content
FROM `YOUR_GCP_PROJECT.prod_ugc.agent_mode_messages_ugc`
WHERE user_id = '[USER_ID]'
ORDER BY timestamp_utc DESC
LIMIT 500"
```
Key `message_type` values:
- `user` — the user's prompt (text at `msg_content` JSON path `$.query`)
- `assistant` — what the agent responded/did
## Step 3: Analyze
- Extract `user` messages (prompt via `JSON_EXTRACT_SCALAR(msg_content, '$.query')`) to understand what the user asked
- Extract `assistant` messages to see what the agent did
- Group by `conversation_id` to understand conversation flow
- Look for patterns in topics, projects, and workflows
## Step 4: Write Summary
Write 1–2 paragraphs capturing:
- Primary use cases and topics
- Key tools/workflows leveraged
- Engagement patterns (conversation length, frequency, iterative vs. one-shot)
- Notable preferences or recurring patterns
View on GitHub