risk · diff

git:20260614.5208b4c to git:20260615.1734111

22 added, 104 removed. Audit A to A.

---

name: risk

multi_ticker_semantics: single_target

description: Risk analysis, regulatory risk assessment, competitive risk, macro risk, technology risk, litigation risk, financial risk assessment, enterprise risk, operational risk, geopolitical risk exposure

temporal_scope:

default_quarters: 4

max_quarters: 10

description: "Typical lookback: 4 quarters, max: 10"

allowed_tools:

- search_companies

- search_xbrl_facts

- search_documents

- search_sec_filings

- get_company_financials

- list_coverage

- read_source_outline

- read_source_deep_outline

- list_xbrl_concepts

- read_source_pages

- search_keyword_in_source

retrieval_scope: unstructured_document_search

min_tool_diversity: 8

---

## Preflight

- !curl -s -o /dev/null -w "%{http_code}" --max-time 2 https://mcp.agentii.ai/mcp/health 2>/dev/null || echo "UNREACHABLE"

- **Ticker resolution **: Before any data retrieval, resolve the ticker via the three-layer fallback per retrieval.md Pre-Flight Step 0: (1) exact match via `search_companies(ticker=<input>)`, (2) pg_trgm fuzzy alias match via `gold.entity_aliases` (6,721 rows), (3) share class normalization for multi-class tickers (GOOG/GOOGL→GOOG, BRK.A/BRK.B→BRK.B). Return canonical ticker, match method, and confidence indicator.

- **Workspace style.md override check **: Check `./style.md` in the workspace root for per-workspace overrides (`default_lookback_quarters`, `reporting_currency`, `sector_focus`, `output_verbosity`, `peer_universe`). Apply overrides to output formatting and temporal scope. Precedence: workspace `style.md` > package `style.md` > skill defaults.

+ Run the canonical pre-flight sequence — MCP health probe, ticker resolution, workspace `style.md` override, memory load, and coverage check. See `contracts/preflight.md`.

- **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.

+ Include the `X-Agentii-Trace` header on every tool call per `contracts/x-agentii-trace-header.md`.

## Triggers

- analyze dim risk analysis

- run dim risk analysis analysis

- produce dim risk analysis report

- dim risk analysis breakdown

- dim risk analysis deep dive

- build a dim risk analysis

- assess dim risk analysis

- quantify dim risk analysis

- compare dim risk analysis across peers

- review dim risk analysis for

- generate dim risk analysis on

- dim risk analysis for investment decision

## Defaults

| Parameter | Default | Notes |

|---|---|---|

| lookback_years | 3 | Historical data window |

| include_peers | false | Whether to surface a peer comparison block |

## Methodology

### Retrieval Scope

This skill performs unstructured document search at scale (10-K, 10-Q, 8-K filings spanning multiple fiscal periods). The three-layer agent-use-ready retrieval protocol (Document Discovery → Page Map → Deep Read) applies to all unstructured document search at scale.

### Retrieval Strategy

- Follow the retrieval strategy decision tree in `retrieval.md`. This skill uses:

+ Follow the retrieval strategy decision tree in `contracts/retrieval.md`. This skill uses:

- Branch (a) for structured financial metrics via `search_xbrl_facts` with `list_xbrl_concepts` pre-condition for unfamiliar concepts.

- Branch (c) for single-period document queries via direct `read_source_outline` → `read_source_pages`.

- Branch (d) for simple lookups via `get_company_profile` / `search_earnings_calendar`.

**Layer 1 `secondary_label` allowlist **: prefer `?secondary_labels=other_events_8_01` to surface risk-event 8-Ks (litigation, regulatory action, cyber incidents) before Layer 2. Also score Layer 2 pages whose `labels.general.keywords` contain "risk factors" entity terms.

### Temporal Scope

Default: 4 fiscal quarters (max 8). Risk analysis: trailing 4 quarters for near-term risk exposure + forward indicators

### Tool Allowlist

- See frontmatter `allowed_tools` — 8 tools declared for this dimension.

+ See frontmatter `allowed_tools`.

### Protocol

This skill delivers analyst-grade output via 4 addressable mode(s); invoke with `--mode=<slug>` / `--modes=<slug1>,<slug2>` / `--mode=all` (see [Mode syntax](../../../../docs/commands/MODE_SYNTAX.md). The default invocation (no flag) runs the `essentials_modes` subset declared in this skill's frontmatter.

- ### Mode: general-risk-factors-identification-assessment

- **Display name**: General Risk Factors Identification & Assessment

-

- ### Objective

- Conduct comprehensive risk factor identification and assessment using official issuer

- disclosures to identify performance stagnation indicators and assess near-term and

- long-term impact across standardized risk categories.

- - executive_summary

- - long_term_risk_assessment

- - near_term_risk_assessment

- - novel_risk_factors

- - risk_identification

- - risk_trend_analysis

- ### Mode: technology-disruption-risk-analysis

- **Display name**: Technology Disruption Risk Analysis

-

- ### Objective

- Assess technology disruption risk exposure by evaluating secular technology trend

- impacts and emerging technology effects on the company's competitive positioning,

- business model resilience, and long-term strategic viability.

- - emerging_technology_analysis

- - executive_summary

- - risk_factors

- - secular_trend_analysis

- - strategic_response_assessment

- ### Mode: regulatory-compliance-risk-assessment

- **Display name**: Regulatory & Compliance Risk Assessment

-

- ### Objective

- Assess regulatory and compliance risk exposure by evaluating recent regulatory

- developments and forward-looking policy risks that could materially impact

- operations, earnings outlook, or strategic initiatives.

- - executive_summary

- - forward_policy_risk_analysis

- - recent_regulatory_developments

- - regulatory_preparedness

- - risk_mitigation

- ### Mode: external-shock-macro-risk-evaluation

- **Display name**: External Shock & Macro Risk Evaluation

-

- ### Objective

- Assess external shock and macroeconomic risk exposure by evaluating recent

- macro, geopolitical, and environmental events and analyzing financial

- sensitivity to external volatility factors.

- - executive_summary

- - external_shock_analysis

- - financial_sensitivity_analysis

- - risk_management_assessment

- - vulnerability_analysis

+ ### Analyst Modes

-

+ This skill exposes addressable analysis modes (`--mode=<slug>` / `--modes=<s1>,<s2>` / `--mode=all`; see [Mode syntax](../../../../docs/commands/MODE_SYNTAX.md)). The full mode definitions and their output templates live in `references/modes.md`. The default invocation runs the essentials subset.

## Tool Fallbacks

- |------|-------------|-----------------|---------------------|

- | `read_source_pages` | SQL error / PROXY_ERROR | Use `search_keyword_in_source(document_id, keyword)` if document_id known; otherwise `search_documents` with same query | "source file unavailable; used keyword search instead" |

- | `list_xbrl_concepts` | Timeout / 503 | Use direct `search_xbrl_facts` with standard US-GAAP concepts (Revenues, NetIncomeLoss, EarningsPerShareDiluted, OperatingIncomeLoss, Assets) | "concept discovery skipped due to timeout; using standard US-GAAP concepts" |

- Tool errors are retried ONCE with the fallback action before escalating to the retrieval gaps failure policy. If both Layer 2 and Layer 3 tools are unavailable, enter document access degradation mode (structured data + metadata only, flag output as degraded).

+ Per-tool failure modes and fallback actions are tabulated in `references/tool-fallbacks.md`.

## Output File

- Write the final deliverable to `{{ticker}}/{{YYYY-MM-DD_HHMM}}_risk_risk-assessment.md` .

+ Write the final deliverable to `{ticker}/{YYYY-MM-DD_HHMM}_risk_risk-assessment.md` .

## Output Structure

- The final deliverable MUST be written as a markdown file to the workspace using the convention :

+ The deliverable is a structured markdown report written to the path in `## Output File`. Full section-by-section template (headings, tables, and field definitions) lives in `references/output-structure.md`. Required elements:

- ```

- {ticker}/{YYYY-MM-DD_HHMM}_risk_{affix}.md

- ```

+ 1. **Executive Summary** — headline conclusions (≤200 words).

+ 2. **Core analysis sections** — per this skill's methodology and analyst modes.

+ 3. **Data classification** — tag findings `[FACT]` / `[DEDUCTED]` / `[VIEW]` per `contracts/snapshot-synthesis.md`.

+ 4. **Coverage Gaps & Citations** — inline `/v/` citations are PRIMARY (immediately after each fact); the bottom **Citations** section is a non-duplicative roll-up index.

+ 5. **Output frontmatter** — emit the FR-090 structured block per `contracts/output-frontmatter-schema.md`.

- Where `affix` is a short descriptive slug (e.g., `risk-matrix`, `regulatory-exposure`, `tech-disruption`, `macro-sensitivity`). Examples:

+ **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`.

- - `LLY/2026-05-25_1430_risk_risk-matrix.md`

- - `NVDA/2026-05-25_1545_risk_tech-disruption.md`

+ ## Memory & Snapshot

- The path is RELATIVE to the agent's invocation cwd. Skills MUST NOT write under absolute paths.

+ - **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`.

- **Citation density**: ≥1 citation per 200 words. Bare `page_no` integers are forbidden — always use `{ticker} {citation_id} page<N>`. **Citation link format **: use clickable links: `[📄 {ticker} {form_type} p.{N}](https://agentii.ai/v/{ticker}/{citation_id}/{N})`. Example: `[📄 LLY 10-K p.30](https://agentii.ai/v/LLY/sec175/30)`.

+ ## Final Summary (TUI)

- **agentii.md append **: After writing the output file, append a YAML block to `agentii.md` at the workspace root with `ticker`, `date`, `skill`, `output_file`, and `key_conclusions`. Create the file with a `# Project Memory Index` heading if it doesn't exist. See `contracts/agentii-md-schema.md`.

+ 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

|---|---|---|---|

| Missing data | Data API returns empty result set | Widen date range and retry once | "No data available for {ticker} in requested window." |

| Sector mismatch | Peer sector != target sector | Filter out mismatched peers | "Removed {n} peer(s) due to sector mismatch." |