sector-overview
Sector overview, TAM estimation, competitive concentration HHI, regulatory landscape, industry analysis, market size analysis, sector trends, industry structure, market growth rate, sector profitability
Install
npx skills add https://github.com/agentii-ai/agentii-investment-intelligence/tree/main/plugins/vertical-plugins/industry-analysis/skills/agentii/sector-overview
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install agentii-ai-agentii-investment-intelligence@llmmart
git clone https://github.com/agentii-ai/agentii-investment-intelligence.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole agentii-ai/agentii-investment-intelligence collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
sector-overview
Triggers
- Sector overview
- TAM estimation
- competitive concentration HHI
- regulatory landscape
- industry analysis
- market size analysis
- sector trends
- industry structure
- market growth rate
- sector profitability
Defaults
| Parameter | Default Value | Rationale |
|---|---|---|
| ticker | (required) | Stock symbol to analyze |
| lookback_quarters | 4 | Standard lookback for this skill type |
Methodology
1. Retrieval Scope
This skill operates with retrieval_scope: unstructured_document_search. It performs unstructured document search at scale via the three-layer retrieval protocol (Layer 1→2→2.5→3), escalating to read_source_deep_outline only when lightweight labels cannot disambiguate pages, plus structured XBRL where needed.
2. Retrieval Strategy
Follows the retrieval strategy decision tree in contracts/retrieval.md. Primary branch: (b)/(c) Unstructured Query via the three-layer protocol. Resolve the canonical ticker first (exact → fuzzy alias → share-class) before any data call.
3. Temporal Scope
Default lookback: 4 fiscal quarter(s); maximum: 12. The default balances recency against the trend window this analysis requires.
4. Tool Allowlist
Per frontmatter allowed_tools:
search_companies— ticker resolution + company context (entity-alias fuzzy match)search_xbrl_facts— primary structured financial facts (is_primary default)search_documents— Layer 1 document discovery (page-level silver records)search_sec_filings— Layer 1 SEC filing metadata indexget_company_financials— consolidated IS/BS/CF highlightslist_coverage— universe-level coverage discoverysearch_unified— used by this skill per the retrieval strategyread_source_outline— Layer 2 lightweight page map (description + keywords)read_source_deep_outline— Layer 2.5a deep page map (table_titles/drivers/metrics)list_xbrl_concepts— XBRL concept discovery for non-standard line items (namespaceparam; defaultus-gaap— useifrs-fullfor foreign filers)read_source_pages— Layer 3 deep read of selected pages with table markerssearch_keyword_in_source— Layer 2.5b keyword page filter for large documents
5. Protocol
- Pre-flight (mandatory):
get_company_fiscal_calendar/{ticker}thenget_ticker_coverage/{ticker}; route on coverage. - Layer 1 — discovery:
search_documents/search_sec_filingsto find candidate filings by ticker/form_type/date. - Layer 2 — page map:
read_source_outline/{ticker}/{citation_id}; skip NULL-description pages; escalate toread_source_deep_outlineonly when labels can't disambiguate. - Layer 2.5 (optional):
search_keyword_in_sourceto narrow documents >50 pages. - Layer 3 — deep read:
read_source_pages/{ticker}/{citation_id}?pages=page<N>,...for the 3–5 selected pages only. - Multi-period (if applicable):
search_cross_periodafter fiscal-calendar resolution. - Output: write the deliverable per
## Output File, then append toagentii.md.
Output File
Write the final deliverable to _cross/{descriptive-slug}_{YYYY-MM-DD_HHMM}_sector-overview_{affix}.md or _sector/{sector_name}/{YYYY-MM-DD_HHMM}_sector-overview_{affix}.md .
Output Structure
- Executive Summary (≤200 words) — headline conclusions for the analysis.
- Data Sources — filings + structured endpoints used, with
{ticker} {citation_id} page<N>citations. - Analysis — the core findings, tables, and commentary for this dimension.
- Key Metrics — the quantitative results with QoQ/YoY context where relevant.
- Coverage Gaps & Citations — data not retrievable + citation index.
Citations & memory: follow contracts/citation-and-memory.md — ≥1 citation per 200 words; every material fact, table row, and metric is immediately followed by its inline clickable https://agentii.ai/v/{ticker}/{citation_id}/{N} link; a bottom Citations section provides a non-duplicative roll-up index; the closing TUI reply includes a compact Key Citations list (headline 5–10 facts) of clickable /v/ URLs; and append the run to agentii.md per contracts/agentii-md-schema.md.
Preflight
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.
Memory & Snapshot
- Memory load (pre-flight): load prior workspace context for the ticker before retrieval — see
contracts/memory-load.md. - Structured output frontmatter: emit the FR-090 block (
key_metrics,conclusions,facts_count,deducted_count,views_count,citation_count) percontracts/output-frontmatter-schema.md. - Snapshot synthesis: after writing the deliverable, update the two-tier snapshot and classify findings as
[FACT]/[DEDUCTED]/[VIEW]— seecontracts/snapshot-synthesis.md. - Session archival: record the run under
sessions/{YYYY-MM-DD}/and updatesessions/INDEX.mdpercontracts/session-format.md.
Final Summary (TUI)
End the closing chat reply with a compact Key Citations list (headline 5–10 facts), each a clickable https://agentii.ai/v/{ticker}/{citation_id}/{N} link, so the user can cmd+click straight to the exact SEC page. See contracts/citation-and-memory.md.
Error Handling
| Error | Action |
|---|---|
| Ticker not found | Suggest checking spelling or trying list_coverage |
| No data available | Flag in Coverage Gaps, proceed with available data |
| API key invalid | Direct user to agentii.ai/api-keys |
| MCP server unreachable | Retry once; if persistent, halt with AGENTII_MCP_UNREACHABLE |
References
- Methodology:
references/methodology.md— tool fallbacks, retrieval strategy, analysis framework - Output Structure:
references/output-structure.md— detailed deliverable sections and ordering
Files (agentii-investment-intelligence)
-
references
-
knowledge-frameworks.md 775 B
# Knowledge Frameworks — Industry Analysis Skills Sector-specific competitive and industry frameworks from the agentii knowledge base (spec 037). ## L2 Sector Frameworks - **Healthcare**: Pipeline valuation (rNPV), FDA catalyst analysis, patent cliff, drug pricing. - **Technology**: Adoption S-curves, network effects quantification, R&D efficiency, platform moats. - **Financials**: Spread analysis, credit cycle positioning, loan loss reserves, capital return. - **Porter's Five Forces**: Applied per-sector — barriers to entry, supplier/customer power. ## Historical Cases Query `search_by_analogue(market_regime, event_type, company_situation)` for sector precedents. Source: `gold.knowledge_entries` — query via `search_knowledge_entries(category_tags: K4)`. -
methodology.md 1.1 KB
# sector-overview — Methodology ## Retrieval Strategy Sector-level analysis combining XBRL aggregate data, SEC filing industry narratives, and peer-group financials. Primary: `search_xbrl_facts` for sector aggregate metrics. Secondary: `search_documents` for industry-level MD&A commentary and risk factors. ## Tool Fallbacks | Tool | Failure Mode | Fallback Action | Coverage Annotation | |------|-------------|----------------|---------------------| | `search_xbrl_facts` | No sector-level aggregates | Build from individual peer data | `aggregate_from_peers: true` | | `search_documents` | No industry narrative found | Proceed with quantitative-only | `narrative_unavailable: true` | | `read_source_pages` | Page not found | Try adjacent pages | `page_fallback: true` | ## Sector Analysis Framework - **TAM estimation**: top-down (industry reports via filings) + bottom-up (peer revenue aggregation) - **Competitive concentration**: HHI from peer revenue shares - **Regulatory landscape**: extracted from 10-K Item 1 / Risk Factors - **Growth drivers**: secular trends from MD&A and earnings calls -
modes.md 715 B
# sector-overview — Analyst Mode Definitions Derived from the skill's own methodology structure (scripts/mode_backfill.py, spec 046 M1). ### Mode: triggers **Objective**: Triggers analysis per the skill's methodology (see SKILL.md sections). ### Mode: defaults **Objective**: Defaults analysis per the skill's methodology (see SKILL.md sections). ### Mode: methodology **Objective**: Methodology analysis per the skill's methodology (see SKILL.md sections). ### Mode: retrieval-scope **Objective**: Retrieval Scope analysis per the skill's methodology (see SKILL.md sections). ### Mode: retrieval-strategy **Objective**: Retrieval Strategy analysis per the skill's methodology (see SKILL.md sections). -
output-structure.md 836 B
# sector-overview — Output Structure 1. **Executive Summary** (≤200 words) — sector definition, size, growth, key players 2. **TAM & Market Sizing** — top-down and bottom-up estimates with sources 3. **Competitive Landscape** — market share table, HHI concentration, leader/follower dynamics 4. **Growth Drivers & Trends** — secular trends, adoption curves, regulatory tailwinds/headwinds 5. **Regulatory Environment** — key regulations, pending changes, compliance burden 6. **Key Metrics** — sector aggregate growth, margins, valuation ranges 7. **Coverage Gaps & Citations** — data not retrievable + citation index **Sector output**: write to `_sector/{sector_name}/{YYYY-MM-DD_HHMM}_sector-overview_{affix}.md`. Cross-ticker analyses use `_cross/{descriptive-slug}_{YYYY-MM-DD_HHMM}_sector-overview_{affix}.md`. -
wsp-methodology.md 8.1 KB
# WSP Healthcare Sector Methodology ## Industry Segmentation (Banking & PE Lens) The healthcare industry is segmented by investment banks and private equity firms into three primary verticals, each with distinct valuation drivers and risk profiles: **Life Sciences**: Biotech, Large Pharma, Specialty Pharma, Generics. Differentiated by R&D intensity, pipeline maturity, and patent exposure. Generics compete on volume contracts and manufacturing cost; branded pharma competes on formulary positioning and clinical differentiation. **Med Tech**: Devices and Equipment. Capital equipment cycles, regulatory clearance pathways (510k vs PMA), and hospital capital budgeting cycles drive revenue visibility. **Healthcare Services**: The most structurally complex vertical, subdivided into Other Services (CROs, PBMs, pharmacies, distributors, HCIT), Payers (Managed Care Organizations, CMS), and Providers (hospitals, ASCs, SNFs, home health). Providers are further classified by acuity (acute vs. post-acute) and setting (inpatient vs. outpatient). ## PBM Ecosystem and Drug Pricing Mechanics Pharmacy Benefit Managers (PBMs) sit at the center of pharmaceutical economics, functioning as the intermediary that dictates which drug is dispensed (brand vs. generic) and at what net price. The PBM value chain operates through three levers: 1. **Formulary Rebates**: Branded manufacturers pay rebates to PBMs for inclusion on the formulary (covered drugs list). This is not a discount to the consumer -- it is a payment for market access that flows manufacturer-to-PBM, creating a spread between list price and net realized price that drives manufacturer gross-to-net calculations. 2. **Generic Utilization and Mail Order Penetration**: PBMs reduce system costs by converting prescriptions to generics and routing volume through captive mail-order facilities, capturing margin on both the spread and the distribution channel. 3. **Vertical Integration**: The industry has consolidated along the PBM axis. Cigna owns Express Scripts; CVS owns both Caremark (PBM) and Aetna (payer). These mergers and alliances create closed-loop ecosystems where the same entity controls the formulary, the pharmacy network, and the insurance risk pool. The summary statement from the WSP modeling framework: "PBMs reduce costs by negotiating drug prices with drug manufacturers and retail pharmacies and by driving generic utilization and mail order penetration." ## Generics Revenue Build Methodology The generics revenue build follows a structured, multi-stage projection framework: ### Stage 1: Market Sizing - Source branded revenue from the innovator's 10-K product disclosures or third-party prescription data. - Derive market volume: Branded Revenue / Estimated Brand Price (sourced from GoodRx or wholesale acquisition cost databases). - Assume 2% annual market volume growth as a baseline. ### Stage 2: Generic Penetration Curve - Model branded-to-generic conversion as a gradual process: 95% generic share in Year 1, stepping to 99% by Year 5. - Branded drugs retain a small residual share initially, fading as PBMs systematically drive conversions to therapeutically equivalent generics. ### Stage 3: Competitor Entry Dynamics - Model sequential new entrant arrivals (4 competitors in Year 1, adding one per year until the market becomes unprofitable for an additional entrant -- typically plateauing at 6-7 competitors). - Each new entrant erodes incumbent share: starting at 25% market share for the first mover, declining to approximately 14% at steady state. ### Stage 4: Price Erosion - Generic prices launch at roughly 50-55% of the branded price and decline approximately 10% per year with each new competitor entry. - Price erosion stabilizes once the competitor count plateaus (no further 10% annual decline when no new entrants). - At steady state, generic prices typically settle at 15-20% of the original branded price. ### Stage 5: Risk-Weighting for Pipeline Products - For products still in development, apply a probability weight to projected revenue based on the estimated likelihood of successful FDA bioequivalence approval. - Paragraph IV patent challenges (Hatch-Waxman framework): when a generic company challenges a branded patent before expiry and wins, it gains 180 days of marketing exclusivity -- a critical asymmetric upside scenario in generics modeling. ## Hospital Revenue Build Methodology ### Volume Derivation The hospital revenue model is built from physical capacity, not market share: - Beds per hospital (from 10-K operating data) x occupancy rate = average daily census. - Average daily census x 365 = total annual patient-days (inpatient volume proxy). - Outpatient volume split from total (typically ~13% of total volume for large hospital systems). - Equivalent Admissions = (Inpatient Admissions x total revenue per case ratio) + Outpatient Volume. This metric serves as the combined volume KPI, analogous to a retail company's transaction count. ### Revenue per Equivalent Admission - Revenue per equivalent admission functions as the "price" variable, driven by two factors: payer mix shifts and reimbursement rate changes. - Medicare reimbursement is based on Diagnosis Related Groups (DRGs) at contracted rates; Managed Medicare (Medicare Advantage) carries 300-400 bps higher reimbursement. - Medicaid rates are structurally the lowest among all payer types. ### Same-Facility Growth The hospital industry equivalent of same-store sales: revenue, admissions, and revenue per equivalent admission measured on a same-facility basis, excluding acquisitions. HCA 2018 baseline: 6.5% same-facility revenue growth, 2.5% admission growth, 3.9% revenue per equivalent admission growth. ### Acquisition Modeling - Newly acquired hospitals are modeled as smaller facilities (lower bed count) with lower Year-1 occupancy (~52% vs. ~57% for mature facilities). - Revenue contribution is multiplied by 0.5 in the acquisition year, reflecting a mid-year closing assumption. - Post-acquisition, new facilities inherit the same operational metrics (outpatient mix, length of stay, revenue per admission) as the existing portfolio. ## Payer and Provider Financial Metrics ### Medical Loss Ratio (MLR) The central KPI for managed care organizations: MLR = Medical Costs / Premium Revenue. This ratio governs both profitability and regulatory compliance (ACA minimum MLR requirements). ### Payer Mix Analysis For providers, revenue is decomposed by payer source, each with distinct reimbursement characteristics: - Medicare (Traditional FFS): ~21% of revenue, DRG-based reimbursement. - Managed Medicare (Medicare Advantage): ~11% of revenue, contracted rates on DRG basis, growing faster (+13.4% CAGR) as enrollment shifts to private plans. - Managed Care / Commercial: ~52% of revenue, 1-3 year contracts with volume steering through Preferred Provider Organizations. - Medicaid: structurally lowest reimbursement, increasingly incorporating outcomes-based payments or penalties. ### Uncompensated Care Modeled as: Gross Uncompensated Care Charges x Cost-to-Charges Ratio. This captures charity care, uninsured discounts, and price concessions. The cost-to-charges ratio (patient care costs / gross patient charges) serves as the conversion factor from list prices to economic cost. ### Payment Integrity Revenue Model A distinct sub-industry within HCIT: payment integrity companies audit claims for errors and over-billing, earning a percentage of what they "catch" (typically 20-30% contingency). The revenue model is directly tied to claims volume and payer adjudication inefficiency. ## Industry Structural Trends **Vertical Consolidation**: Payers acquiring PBMs, pharmacies acquiring payers, pharmacies merging with distributors -- creating integrated delivery and financing ecosystems that compress margins for independent players. **Value-Based Care Migration**: The fundamental reimbursement model shift from fee-for-service (volume-driven) to value-based care (outcome-driven), with pay-for-performance components increasingly embedded in provider contracts. **Integrated Delivery Networks (IDNs)**: Provider-payer systems operating within a defined geographic area, negotiating as a single entity against suppliers and leveraging combined data across the care continuum.
-
-
SKILL.md 6.9 KB
--- name: sector-overview multi_ticker_semantics: target_with_optional_peers description: Sector overview, TAM estimation, competitive concentration HHI, regulatory landscape, industry analysis, market size analysis, sector trends, industry structure, market growth rate, sector profitability temporal_scope: default_quarters: 4 max_quarters: 12 description: "Typical lookback: 4 quarters, max: 12" allowed_tools: - search_companies - search_xbrl_facts - search_documents - search_sec_filings - get_company_financials - list_coverage - search_unified - read_source_outline - read_source_deep_outline - list_xbrl_concepts - read_source_pages - search_keyword_in_source - search_knowledge_entries - get_knowledge_entry - search_by_analogue retrieval_scope: unstructured_document_search min_tool_diversity: 8 --- # sector-overview ## Triggers - Sector overview - TAM estimation - competitive concentration HHI - regulatory landscape - industry analysis - market size analysis - sector trends - industry structure - market growth rate - sector profitability ## Defaults | Parameter | Default Value | Rationale | |-----------|---------------|-----------| | ticker | (required) | Stock symbol to analyze | | lookback_quarters | 4 | Standard lookback for this skill type | ## Methodology ### 1. Retrieval Scope This skill operates with `retrieval_scope: unstructured_document_search`. It performs unstructured document search at scale via the three-layer retrieval protocol (Layer 1→2→2.5→3), escalating to `read_source_deep_outline` only when lightweight labels cannot disambiguate pages, plus structured XBRL where needed. ### 2. Retrieval Strategy Follows the retrieval strategy decision tree in `contracts/retrieval.md`. Primary branch: **(b)/(c) Unstructured Query via the three-layer protocol**. Resolve the canonical ticker first (exact → fuzzy alias → share-class) before any data call. ### 3. Temporal Scope Default lookback: 4 fiscal quarter(s); maximum: 12. The default balances recency against the trend window this analysis requires. ### 4. Tool Allowlist Per frontmatter `allowed_tools`: - `search_companies` — ticker resolution + company context (entity-alias fuzzy match) - `search_xbrl_facts` — primary structured financial facts (is_primary default) - `search_documents` — Layer 1 document discovery (page-level silver records) - `search_sec_filings` — Layer 1 SEC filing metadata index - `get_company_financials` — consolidated IS/BS/CF highlights - `list_coverage` — universe-level coverage discovery - `search_unified` — used by this skill per the retrieval strategy - `read_source_outline` — Layer 2 lightweight page map (description + keywords) - `read_source_deep_outline` — Layer 2.5a deep page map (table_titles/drivers/metrics) - `list_xbrl_concepts` — XBRL concept discovery for non-standard line items (`namespace` param; default `us-gaap` — use `ifrs-full` for foreign filers) - `read_source_pages` — Layer 3 deep read of selected pages with table markers - `search_keyword_in_source` — Layer 2.5b keyword page filter for large documents ### 5. Protocol 1. **Pre-flight (mandatory)**: `get_company_fiscal_calendar/{ticker}` then `get_ticker_coverage/{ticker}`; route on coverage. 2. **Layer 1 — discovery**: `search_documents` / `search_sec_filings` to find candidate filings by ticker/form_type/date. 3. **Layer 2 — page map**: `read_source_outline/{ticker}/{citation_id}`; skip NULL-description pages; escalate to `read_source_deep_outline` only when labels can't disambiguate. 4. **Layer 2.5 (optional)**: `search_keyword_in_source` to narrow documents >50 pages. 5. **Layer 3 — deep read**: `read_source_pages/{ticker}/{citation_id}?pages=page<N>,...` for the 3–5 selected pages only. 6. **Multi-period** (if applicable): `search_cross_period` after fiscal-calendar resolution. 7. **Output**: write the deliverable per `## Output File`, then append to `agentii.md`. ## Output File Write the final deliverable to `_cross/{descriptive-slug}_{YYYY-MM-DD_HHMM}_sector-overview_{affix}.md` or `_sector/{sector_name}/{YYYY-MM-DD_HHMM}_sector-overview_{affix}.md` . ## Output Structure 1. **Executive Summary** (≤200 words) — headline conclusions for the analysis. 2. **Data Sources** — filings + structured endpoints used, with `{ticker} {citation_id} page<N>` citations. 3. **Analysis** — the core findings, tables, and commentary for this dimension. 4. **Key Metrics** — the quantitative results with QoQ/YoY context where relevant. 5. **Coverage Gaps & Citations** — data not retrievable + citation index. **Citations & memory**: follow `contracts/citation-and-memory.md` — ≥1 citation per 200 words; every material fact, table row, and metric is immediately followed by its inline clickable `https://agentii.ai/v/{ticker}/{citation_id}/{N}` link; a bottom **Citations** section provides a non-duplicative roll-up index; the closing TUI reply includes a compact **Key Citations** list (headline 5–10 facts) of clickable `/v/` URLs; and append the run to `agentii.md` per `contracts/agentii-md-schema.md`. ## Preflight 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`. ## Memory & Snapshot - **Memory load** (pre-flight): load prior workspace context for the ticker before retrieval — see `contracts/memory-load.md`. - **Structured output frontmatter**: emit the FR-090 block (`key_metrics`, `conclusions`, `facts_count`, `deducted_count`, `views_count`, `citation_count`) per `contracts/output-frontmatter-schema.md`. - **Snapshot synthesis**: after writing the deliverable, update the two-tier snapshot and classify findings as `[FACT]`/`[DEDUCTED]`/`[VIEW]` — see `contracts/snapshot-synthesis.md`. - **Session archival**: record the run under `sessions/{YYYY-MM-DD}/` and update `sessions/INDEX.md` per `contracts/session-format.md`. ## Final Summary (TUI) End the closing chat reply with a compact **Key Citations** list (headline 5–10 facts), each a clickable `https://agentii.ai/v/{ticker}/{citation_id}/{N}` link, so the user can cmd+click straight to the exact SEC page. See `contracts/citation-and-memory.md`. ## Error Handling | Error | Action | |-------|--------| | Ticker not found | Suggest checking spelling or trying list_coverage | | No data available | Flag in Coverage Gaps, proceed with available data | | API key invalid | Direct user to agentii.ai/api-keys | | MCP server unreachable | Retry once; if persistent, halt with AGENTII_MCP_UNREACHABLE | ## References - **Methodology**: [`references/methodology.md`](references/methodology.md) — tool fallbacks, retrieval strategy, analysis framework - **Output Structure**: [`references/output-structure.md`](references/output-structure.md) — detailed deliverable sections and ordering
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.