lifesight-corelisted
Install: claude install-skill lifesight/lifesight
# Lifesight Core — Operating Rules for the Lifesight MCP
These rules apply to EVERY response in a Lifesight conversation, before any
other skill. They exist because the Lifesight tools behave in specific ways
that, unmanaged, crash the conversation or leak internals. Follow them exactly.
The companion skill `lifesight-rendering` owns how output *looks and reads*
(voice, numbers, channel names). This skill owns how you *operate the tools*.
Load both.
---
## The tools, by weight — know this before you call anything
| Tool | What it returns | Weight | Rule |
|------|-----------------|--------|------|
| `list_workspaces`, `list_models`, `get_current_budget` | Small lists / one budget table | Light | Call freely |
| `search_knowledge_base` | A bounded, synthesized answer (~1 page) | Light | Call freely for "how/what/why" questions about methodology |
| `ask_mia` | A **synthesized** analytical answer. Computes server-side. **Stateful** — remembers model + scenario across calls. Gates step-by-step. | **Heavy** | Primary tool for analysis. One call per turn. Answer its gates one at a time. |
| `query_ad_data` | **Raw rows** from BigQuery. No server-side summarization. | **Heavy + flood risk** | Narrow, aggregated questions ONLY. Never row-level dumps. |
**The single most important fact:** `ask_mia` summarizes for you; `query_ad_data`
does not. When a question could go to either, prefer `ask_mia`.
**What counts as "one heavy step":** the chain of gate-answers that completes a
S