earnings-previewlisted
Install: claude install-skill agentii-ai/agentii-investment-intelligence
## Preflight
```bash
# Tier 1: agentii-office MCP (recommended)
OFFICE_BACKEND="mcp"
curl -s -o /dev/null -w "%{http_code}" --max-time 2 https://mcp.agentii.ai/office/mcp/health 2>/dev/null || echo "UNREACHABLE"
# Tier 2: Python+LibreOffice local fallback
if [ "$OFFICE_BACKEND" = "unreachable" ]; then
python3 -c "import openpyxl; import pptx" 2>/dev/null && OFFICE_BACKEND="python" || echo "DEPS_MISSING"
fi
# Tier 3: OfficeCLI single-binary fallback
if [ "$OFFICE_BACKEND" = "unreachable" ]; then
officecli --version 2>/dev/null && OFFICE_BACKEND="officecli" || echo "OFFICECLI_MISSING"
fi
if [ "$OFFICE_BACKEND" = "unreachable" ]; then
echo "AGENTII_OFFICE_UNREACHABLE: No office backend available."
echo "Options: (a) set AGENTII_API_KEY, (b) pip install openpyxl python-pptx, (c) install OfficeCLI"
fi
```
**Agent Call Tracing**: The first tool you call will return a `_run_id` in its result. On every subsequent tool call, include HTTP header `X-Agentii-Trace: agent={skill_name}; parent={caller_name}; instance={instance_label}`. The MCP server will inject run_id, depth, and user_id automatically. When spawning parallel sub-agents of the same type, assign each a unique instance label (e.g., equity-research-1, equity-research-2). See `contracts/x-agentii-trace-header.md` for the full contract.
## Triggers
- generate earnings preview deck
- build earnings preview presentation
- create quarterly earnings slides
- earnings preview pptx
- earnings summary presentation
- consens