turnaround
Turnaround analysis, stagnation detection, performance inflection, operational improvement, restructuring analysis, management change impact, cost cutting effectiveness, business transformation, recovery trajectory, operational metrics improvement
Install
npx skills add https://github.com/agentii-ai/agentii-investment-intelligence/tree/main/plugins/agent-plugins/agentii-equity-agent/skills/agentii/turnaround
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
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.
Triggers
- analyze dim turnaround stagnation
- run dim turnaround stagnation analysis
- produce dim turnaround stagnation report
- dim turnaround stagnation breakdown
- dim turnaround stagnation deep dive
- build a dim turnaround stagnation
- assess dim turnaround stagnation
- quantify dim turnaround stagnation
- compare dim turnaround stagnation across peers
- review dim turnaround stagnation for
- generate dim turnaround stagnation on
- dim turnaround stagnation 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 and earnings call transcripts 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 contracts/retrieval.md. This skill uses:
- Branch (a) for structured financial metrics via
search_xbrl_factswithlist_xbrl_conceptspre-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=results_of_operations_8_01,other_events_8_01 to surface restructuring, cost-action, and operational-inflection 8-Ks before Layer 2.
Temporal Scope
Default: 8 fiscal quarters (max 16). Turnaround/stagnation: 8 quarters for operational trend detection and inflection-point analysis
Tool Allowlist
See frontmatter allowed_tools.
Protocol
This skill delivers analyst-grade output via 9 addressable mode(s); invoke with --mode=<slug> / --modes=<slug1>,<slug2> / --mode=all (see Mode syntax. The default invocation (no flag) runs the essentials_modes subset declared in this skill's frontmatter.
Analyst Modes
This skill exposes addressable analysis modes (--mode=<slug> / --modes=<s1>,<s2> / --mode=all; see Mode syntax). The full mode definitions and their output templates live in references/modes.md. The default invocation runs the essentials subset.
Tool Fallbacks
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}_turnaround_turnaround-assessment.md .
Output Structure
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:
- Executive Summary — headline conclusions (≤200 words).
- Core analysis sections — per this skill's methodology and analyst modes.
- Data classification — tag findings
[FACT]/[DEDUCTED]/[VIEW]percontracts/snapshot-synthesis.md. - Coverage Gaps & Citations — inline
/v/citations are PRIMARY (immediately after each fact); the bottom Citations section is a non-duplicative roll-up index. - Output frontmatter — emit the FR-090 structured block per
contracts/output-frontmatter-schema.md.
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.
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
| Failure Mode | Detection | Action | User-Facing Message |
|---|---|---|---|
| Missing data | Data API returns empty result set | Widen date range and retry once | "No data available for in requested window." |
| Partial data | Data API returns <80% expected records | Proceed with coverage gaps section | "Analysis based on partial data; see Coverage Gaps section." |
| Sector mismatch | Peer sector != target sector | Filter out mismatched peers | "Removed peer(s) due to sector mismatch." |
| Insufficient history | Ticker <3 years on public markets | Downgrade to limited-history profile | "Limited historical data; analysis adjusted accordingly." |
| MCP unreachable | Preflight probe fails | Halt with actionable error | "agentii data plane unreachable; check connection." |
Files (agentii-investment-intelligence)
-
references
-
knowledge-frameworks.md 2.2 KB
# Knowledge Frameworks — {SKILL_NAME} This file augments the skill methodology with practitioner frameworks, case precedents, and sector-specific analysis rubrics from the agentii knowledge base (spec 037). It is progressively disclosed — loaded on demand, not at skill activation (FR-014). ## How to Use Before executing the analysis, scan the relevant frameworks below for the target sector and analysis type. Where a framework applies, incorporate its methodology alongside the standard protocol. Cite knowledge entries by their `/v/knowledge/{citation_id}` link. ## Practitioner Frameworks ### Fundamental Analysis (L2) - **Fisher Scuttlebutt Method**: Channel checks, supplier interviews, customer surveys — validate management claims through primary research. - **Morningstar Moats**: Network effects, switching costs, intangible assets, cost advantage, efficient scale — score competitive durability. - **Greenblatt Magic Formula**: Rank on earnings yield + ROIC — quantitative screen for quality-at-a-reasonable-price. - **Mauboussin Expectations Investing**: Price-implied expectations vs. fundamentals — identify the gap. ### Management Assessment - **CEO/CFO track record**: Past capital allocation decisions, M&A history, share buyback timing. - **Incentive alignment**: Compensation structure, insider ownership, option grants. ### Sector-Specific Playbooks - **Healthcare (Pharma/Biotech)**: Pipeline depth analysis, FDA catalyst calendar, patent cliff exposure, drug pricing risk. - **Technology**: Adoption S-curves, network effects quantification, R&D efficiency, platform ecosystem lock-in. - **Financials**: Spread analysis (NIM), credit cycle positioning, loan loss reserve adequacy, capital return capacity. - **Consumer**: Brand strength metrics, unit economics, channel mix trends, customer acquisition cost payback. ## Historical Analogues When the current situation matches a known pattern, query `search_by_analogue` with the appropriate `market_regime`/`event_type`/`company_situation` tags. Cite relevant cases as precedent. ## References All frameworks sourced from `gold.knowledge_entries` (spec 037). See `contracts/citation-and-memory.md` for citation format conventions. -
life-cycle-methodology.md 4.5 KB
# Company Life Cycle Classification — Institutional Methodology Methodology synthesized from institutional investment research; all text is an original paraphrase. --- ## Cash Flow-Based Classification Traditional life cycle classification relies on proxies: age (older = mature), size (bigger = mature), or profitability. These proxies are weak. Age and size have low correlation with where a company actually is in its life cycle. A better approach uses the three components of the cash flow statement. ### The Five Stages (3-Year Rolling Sign Patterns) | Stage | Operating CF (CFO) | Investing CF (CFI) | Financing CF (CFF) | Description | |:---:|:---:|:---:|:---:|------| | **Birth** | − | − | + | Company is investing heavily and not yet generating positive operating cash flow. Raising external capital to fund growth. | | **Growth** | + | − | + | Operating CF has turned positive. Still investing heavily. Still raising capital (debt or equity) to fund expansion. | | **Mature** | + | − | − | Strong operating CF. Still investing (CFI negative). Now generating enough cash to pay down debt and return capital (CFF negative). | | **Decline** | + | + | − | Operating CF still positive but company is divesting assets (CFI positive — selling more than investing). Paying down obligations. | | **Turnaround** | Transitional | Transitional | Transitional | Signs changing. Company moving from one stage to another. The key is identifying the direction of transition. | ### Classification Methodology Use a 3-year rolling window to smooth annual volatility: 1. For each of the last 3 fiscal years, classify CFO, CFI, CFF as positive or negative 2. If all 3 years show the same pattern → stable stage 3. If only 2 of 3 years match → transitional (flag reduced confidence) 4. If the pattern has shifted in the most recent year → potential stage transition — cross-reference with qualitative indicators --- ## Transition Probability Matrix (1990-2022 IPO Cohort) Based on analysis of all US IPOs from 1990-2022, companies at each stage have the following 3-year transition probabilities: | From \ To | Birth | Growth | Mature | Decline | |-----------|:---:|:---:|:---:|:---:| | **Birth** | 35% | 50% | 10% | 5% | | **Growth** | 5% | 55% | 35% | 5% | | **Mature** | 2% | 5% | 75% | 18% | | **Decline** | 8% | 12% | 20% | 60% | Key observations: - Growth → Mature is the most common transition (35% probability over 3 years) - Companies can move backward in the cycle (Mature → Growth if new product cycles or acquisitions shift the CF pattern) - Birth companies have a 50% probability of reaching Growth within 3 years; those that don't typically fail or remain sub-scale - Decline companies have a 40% probability of transitioning out of Decline within 3 years (Turnaround = 20%, back to Growth = 12%, Birth = 8%) --- ## TSR by Stage Transition Historical total shareholder returns for companies transitioning between stages (1990-2022): | Transition | 3-Year Median TSR | Interpretation | |-----------|:---:|------| | Birth → Growth | +35% | Highest return — operating leverage kicks in | | Decline → Mature (Turnaround) | +28% | Successful restructuring reprices the stock | | Growth → Growth (stay) | +18% | Steady compounder | | Mature → Mature (stay) | +8% | Low growth, stable returns | | Growth → Mature | +5% | Transition priced in; modest returns | | Mature → Decline | −12% | Value destruction as business erodes | --- ## Integration with Turnaround Assessment This CF-based classification complements the existing financial scorecard approach. Two perspectives: 1. **CF-based**: What does the cash flow pattern tell us about where the company IS in the life cycle? 2. **Scorecard-based**: What do the financial metrics tell us about whether this is a genuine turnaround or a value trap? When both frameworks agree (CF-based says "Decline transitioning" + scorecard ≥ 7) → highest conviction. When they disagree → investigate the discrepancy. A company with strong turnaround scorecard metrics but CF pattern still firmly in Decline may be too early to enter. --- ## Limitations - **CFO borderline**: Companies with near-zero operating CF may flip classifications year-to-year. Use 3-year rolling window. - **Acquisition distortion**: Large acquisitions can temporarily shift CFI deeply negative, mimicking Growth stage in a Mature company. Adjust for M&A cash flows when significant. - **Financial companies**: Banks and insurers have different CF statement structures. This classification is less reliable for financial sector companies. -
modes.md 4.3 KB
# turnaround — Analyst Mode Definitions Extracted from SKILL.md for progressive disclosure (US5). The skill body keeps a pointer under `## Methodology → Analyst Modes`. ### Mode: performance-stagnation-detection-and-classification **Display name**: performance-stagnation-detection-and-classification <!-- ported_from: references/prompts/5/5_1.yaml --> **Focus**: Identify and extract indicators of performance stagnation across four key dimensions using comprehensive financial and operational analysis. (rewritten via tool-name-map.json:system_v2_7) - `get_company_profile` - `search_keyword_in_source` - `search_xbrl_facts` ### Mode: growth-catalyst-identification-and-assessment **Display name**: growth-catalyst-identification-and-assessment <!-- ported_from: references/prompts/5/5_2_1.yaml --> **Focus**: Identify and extract announcements related to new products, services, or business initiatives that could serve as major catalysts to reaccelerate grow. (rewritten via tool-name-map.json:system_v2_7) - `get_company_profile` - `search_keyword_in_source` ### Mode: growth-catalyst-execution-monitoring-and-progress-assessment **Display name**: growth-catalyst-execution-monitoring-and-progress-assessment <!-- ported_from: references/prompts/5/5_2_1_1.yaml --> **Focus**: Monitor and assess the execution progress of identified growth catalyst initiatives through trackable metrics, market sentiment analysis, and mileston. (rewritten via tool-name-map.json:system_v2_7) - `get_company_profile` - `search_keyword_in_source` ### Mode: leadership-change-impact-analysis **Display name**: leadership-change-impact-analysis <!-- ported_from: references/prompts/5/5_2_2.yaml --> **Focus**: Identify and analyze senior leadership or key personnel changes that could materially shift company strategy, investor sentiment, or growth trajectory. (rewritten via tool-name-map.json:system_v2_7) - `get_company_profile` - `search_keyword_in_source` ### Mode: strategic-leadership-impact-assessment-and-financial-projection **Display name**: strategic-leadership-impact-assessment-and-financial-projection <!-- ported_from: references/prompts/5/5_2_3.yaml --> **Focus**: Analyze the speculated strategy or strategic shift tied to new executive appointments and assess the expected financial statement impacts based on the. (rewritten via tool-name-map.json:system_v2_7) - `get_company_profile` - `search_keyword_in_source` ### Mode: strategic-initiative-execution-status-and-effectiveness-assessment **Display name**: strategic-initiative-execution-status-and-effectiveness-assessment <!-- ported_from: references/prompts/5/5_2_3_1.yaml --> **Focus**: Monitor and assess the execution status and effectiveness of strategic initiatives announced or underway, focusing on transformation levers that could. (rewritten via tool-name-map.json:system_v2_7) - `get_company_profile` - `search_keyword_in_source` ### Mode: operational-execution-progress-and-effectiveness-assessment **Display name**: operational-execution-progress-and-effectiveness-assessment <!-- ported_from: references/prompts/5/5_3.yaml --> **Focus**: Identify and extract trackable metrics and qualitative signals that reflect the execution progress and early results of the company's turnaround strat. (rewritten via tool-name-map.json:system_v2_7) - `get_company_profile` - `search_keyword_in_source` ### Mode: new-product-performance-evaluation-and-turnaround-contribution-assessment **Display name**: new-product-performance-evaluation-and-turnaround-contribution-assessment <!-- ported_from: references/prompts/5/5_4_1.yaml --> **Focus**: Identify and extract trackable metrics and indicators that evaluate the execution, market feedback, and impact of new products/services launched as gr. (rewritten via tool-name-map.json:system_v2_7) - `get_company_profile` - `search_keyword_in_source` ### Mode: financial-turnaround-metrics-and-performance-validation **Display name**: financial-turnaround-metrics-and-performance-validation <!-- ported_from: references/prompts/5/5_4_2.yaml --> **Focus**: Identify and extract quantitative financial metrics and supporting commentary that assess the financial outcomes of strategic turnaround initiatives. (rewritten via tool-name-map.json:system_v2_7) - `get_company_profile` - `search_keyword_in_source` - `search_xbrl_facts` <!-- END port-dimension-prompts methodology + modes --> -
output-structure.md 1.2 KB
# turnaround — Output Structure (full template) Extracted from SKILL.md for progressive disclosure (US5). The skill body keeps a compact summary under `## Output Structure`. The final deliverable MUST be written as a markdown file to the workspace using the convention : ``` {ticker}/{YYYY-MM-DD_HHMM}_turnaround_{affix}.md ``` Where `affix` is a short descriptive slug (e.g., `turnaround-thesis`, `restructuring-progress`, `cost-action`, `inflection-signals`). Examples: - `LLY/2026-05-25_1430_turnaround_turnaround-thesis.md` - `NVDA/2026-05-25_1545_turnaround_restructuring-progress.md` The path is RELATIVE to the agent's invocation cwd. Skills MUST NOT write under absolute paths. **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`. -
tool-fallbacks.md 1.8 KB
# turnaround — Tool Fallbacks Extracted from SKILL.md for progressive disclosure (US5). | Tool | Failure Mode | Fallback Action | Coverage Annotation | |------|-------------|-----------------|---------------------| | `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" | | `read_source_deep_outline` | PROXY_ERROR / 404 | Use lightweight `read_source_outline` and flag `deep_outline_degraded: true` | "deep outline unavailable; used lightweight page map instead" | | `read_source_outline` | PROXY_ERROR / 404 | Use `list_sources` for document-level metadata | "page map unavailable; used document listing 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" | | `get_company_fiscal_calendar` | Cross-validation failed | Use XBRL-derived period grid from `search_xbrl_facts` `period_end` dates | "fiscal calendar mismatch; using XBRL-derived period grid" | | `search_unified` | Intermittent error | Use parallel `search_documents` + `search_xbrl_facts` with the same query | "unified search unavailable; used parallel document + XBRL search" | | `batch_search` | PROXY_ERROR | Use sequential individual calls (one per sub-query) | "batch search unavailable; used sequential calls" | 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).
-
-
SKILL.md 7.1 KB
--- name: turnaround multi_ticker_semantics: single_target description: Turnaround analysis, stagnation detection, performance inflection, operational improvement, restructuring analysis, management change impact, cost cutting effectiveness, business transformation, recovery trajectory, operational metrics improvement essentials_modes: [performance-stagnation-detection-and-classification, growth-catalyst-identification-and-assessment, growth-catalyst-execution-monitoring-and-progress-assessment] 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 - get_company_profile - list_coverage - 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 - search_investment_cases - get_investment_case retrieval_scope: unstructured_document_search min_tool_diversity: 10 --- <!-- analog: thesis-tracker --> ## 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`. ## Triggers - analyze dim turnaround stagnation - run dim turnaround stagnation analysis - produce dim turnaround stagnation report - dim turnaround stagnation breakdown - dim turnaround stagnation deep dive - build a dim turnaround stagnation - assess dim turnaround stagnation - quantify dim turnaround stagnation - compare dim turnaround stagnation across peers - review dim turnaround stagnation for - generate dim turnaround stagnation on - dim turnaround stagnation for investment decision ## Defaults | Parameter | Default | Notes | |---|---|---| | lookback_years | 3 | Historical data window | | include_peers | false | Whether to surface a peer comparison block | <!-- BEGIN port-dimension-prompts methodology + modes --> ## Methodology ### Retrieval Scope This skill performs unstructured document search at scale (10-K, 10-Q, 8-K filings and earnings call transcripts 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 `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=results_of_operations_8_01,other_events_8_01` to surface restructuring, cost-action, and operational-inflection 8-Ks before Layer 2. ### Temporal Scope Default: 8 fiscal quarters (max 16). Turnaround/stagnation: 8 quarters for operational trend detection and inflection-point analysis ### Tool Allowlist See frontmatter `allowed_tools`. ### Protocol This skill delivers analyst-grade output via 9 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. ### 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 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}_turnaround_turnaround-assessment.md` . ## Output Structure 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: 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`. **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`. ## 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 | Failure Mode | Detection | Action | User-Facing Message | |---|---|---|---| | Missing data | Data API returns empty result set | Widen date range and retry once | "No data available for {ticker} in requested window." | | Partial data | Data API returns <80% expected records | Proceed with coverage gaps section | "Analysis based on partial data; see Coverage Gaps section." | | Sector mismatch | Peer sector != target sector | Filter out mismatched peers | "Removed {n} peer(s) due to sector mismatch." | | Insufficient history | Ticker <3 years on public markets | Downgrade to limited-history profile | "Limited historical data; analysis adjusted accordingly." | | MCP unreachable | Preflight probe fails | Halt with actionable error | "agentii data plane unreachable; check connection." |
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.