Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →agentii-ai/sotp-valuation
Sum of the Parts valuation, segment-based valuation, conglomerate valuation, business segment analysis, breakup value, segment sum valuation, parts worth more than whole, hidden asset value
Passed 7 of 16 test cases with the skill, and 3 of 16 without it.
and 3 more in the full report
5 fixed5 passed either way14 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
How long should the Executive Summary section of the SOTP report be? An analyst drafted a 500-word narrative for the executive summary.
| Checked | Without skill | With skill |
|---|---|---|
| Enforces maximum limit of 200 words for Executive Summary section. | Missed | Passed |
The instructions your model reads when the skill loads.
Values each business segment independently and sums for total enterprise value. Essential for conglomerates (GE, MMM, HON), multi-segment tech (AMZN: AWS + Retail + Ads, GOOG: Search + Cloud + YouTube), and holding companies. SOTP often reveals "hidden value" when the market undervalues individual segments.
Run the canonical pre-flight sequence — MCP health probe, ticker resolution, workspace style.md override, memory load, and coverage check. See contracts/preflight.md.
Include the X-Agentii-Trace header on every tool call per contracts/x-agentii-trace-header.md.
| Parameter | Default | Notes |
|---|---|---|
| segment_discovery | statement_tree | Use get_statement_structure for segment identification |
| peer_multiples | sector | Apply sector-appropriate multiples per segment |
| include_corporate | true | Subtract corporate overhead, net debt |
unstructured_document_search — SOTP requires segment financials from XBRL (structured) AND segment narrative/business description from MD&A (unstructured) for appropriate multiple selection.
See contracts/retrieval.md for the canonical decision tree; skill-specific retrieval detail is in references/methodology.md.
test cases passed, vs 3 / 16 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.