{"id":21013,"plugin_id":"plugins_6aabe06db7f08191823dcc1de0a081e3","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:16:44.373Z","digest":"bed56d88e9a26434c1176015442c92eeaa93131eaa9edc4482b8052b544d2b81","against":null,"payload":{"description":"Analyze a public company's customer economics, competitive advantages, unit economics, and reinvestment runway for a long-term equity research dossier.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":248}],"name":"equity-business","skill_md_contents":"---\nname: equity-business\ndescription: Analyze a public company's customer economics, competitive advantages, unit economics, and reinvestment runway for a long-term equity research dossier.\n---\n\n# Business quality and durable compounding\n\nExplain how this business earns cash, why customers continue buying, and what can sustain or erode per-share economics over 5–10 years. Read the [operating contract](../../references/operating-contract.md), use the approved industry map and plan, and select relevant [sector lenses](../../references/sector-lenses.md). In standalone work, state the investigation procedure before executing.\n\n## Investigation\n\n1. Reconstruct the revenue engine by segment: customer, purchasing decision, volume, price, mix, retention, distribution, and cash collection. Identify who ultimately funds demand. Distinguish contractual obligations from cancelable orders, trials, installed capacity, and management's pipeline.\n2. Test each alleged advantage through an economic mechanism and observable evidence. For switching costs, examine renewal behavior and migration alternatives; for scale, incremental cost advantage; for network effects, customer benefit from participation versus subsidies or multihoming. Market share, brand familiarity, patents, and high gross margins are clues, not sufficient proof of a moat.\n3. Analyze cohorts or unit economics where disclosures permit. Separate price increases from unit growth and gross retention from expansion. Include service, acquisition, maintenance, working-capital, and replacement costs that the reported unit contribution excludes. Flag selection bias when only mature or successful cohorts are disclosed. Do not manufacture cohort data from aggregate figures.\n4. Assess the reinvestment runway: where additional capital can earn attractive incremental returns, how much can be deployed, and how long the opportunity lasts. Distinguish acquisition-led growth from organic improvement. Reconcile historical returns with asset write-downs, acquired goodwill, expensed intangibles, or unusual utilization before extrapolating them.\n5. Model competitive response and decay. Examine substitutes, customer concentration, supply dependence, demand pull-forward, capacity additions, and technological displacement. Include a credible case where the industry grows but shareholder economics weaken. Trace relevant tangents to specific operating assumptions.\n\n## Decision discipline\n\nKeep business quality separate from price attractiveness. A durable franchise can be an unattractive security at an excessive price; a weak franchise can appear cheap because its cash generation is declining. Do not assign a terminal growth rate merely because management cites a large addressable market. Treat absent disclosure as uncertainty, and identify the feasible evidence that would resolve it.\n\n## Deliverable and handoff\n\nApply the [evidence standard](../../references/evidence-standard.md). Return the business mechanism, supported advantage/erosion claims, customer and unit-economics table, reinvestment constraints, strongest counterevidence, and 5/7/10-year operating assumption ranges where supportable. Link claim IDs, units, definitions, and source locations. Handoff revenue, margin, reinvestment, and competitive-fade drivers to valuation; flag accounting questions for financial review. State confidence reasons and complete/conditional status. Finish when the material business drivers are supported or explicitly unresolved, without selecting the final winner.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}