Claude Skill

pitch-deck

Investment pitch deck, investment committee presentation, buy-side pitch, sell-side pitch, investment thesis slides, executive summary presentation, financial presentation, board deck, investor presentation, strategy deck

LLM Mart · 0 points · 0 views 0 listing impressions 0 install-command copies
Virus-scanned Reviewed automatically before listing.

Full trust report

Download agentii-ai-agentii-investment-intelligence-plugins_vertical-plugins_models-and-pitches_skills_agentii_pitch-deck-1a2d679.zip · 8 KB
Part of agentii-ai/agentii-investment-intelligence — 46 skills

Install

skills CLI npx skills add https://github.com/agentii-ai/agentii-investment-intelligence/tree/main/plugins/vertical-plugins/models-and-pitches/skills/agentii/pitch-deck
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install agentii-ai-agentii-investment-intelligence@llmmart
Git 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

pitch-deck

Triggers

  • Investment pitch deck
  • investment committee presentation
  • buy-side pitch
  • sell-side pitch
  • investment thesis slides
  • executive summary presentation
  • financial presentation
  • board deck
  • investor presentation
  • strategy deck

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: structured_only. It performs structured data retrieval only (XBRL facts, financials, earnings calendar) — no unstructured document search. Document-retrieval tools are excluded from allowed_tools.

2. Retrieval Strategy

Follows the retrieval strategy decision tree in contracts/retrieval.md. Primary branch: (a) Structured Data Query. Resolve the canonical ticker first (exact → fuzzy alias → share-class) before any data call.

3. Temporal Scope

Default lookback: 4 fiscal quarter(s); maximum: 8. 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)
  • get_company_financials — consolidated IS/BS/CF highlights
  • get_company_profile — sector/industry classification + metadata
  • search_earnings_calendar — EPS actual/estimate/surprise + report dates
  • list_xbrl_concepts — XBRL concept discovery for non-standard line items (namespace param; default us-gaap — use ifrs-full for foreign filers)

5. Protocol

  1. Pre-flight (mandatory): call get_company_fiscal_calendar/{ticker} then get_ticker_coverage/{ticker}; route on coverage.
  2. Concept discovery (non-standard concepts only): list_xbrl_concepts(query=<term>, ticker=<T>).
  3. Structured retrieval: search_xbrl_facts(ticker, concept=[...], fiscal_year=[...]) (is_primary default) and/or get_company_financials/{ticker}.
  4. Batch rule: 3+ same-tool queries → consolidate via batch_search (≤8 sub-queries).
  5. Output: write the deliverable per ## Output File, then append to agentii.md.

Deliverable Chain

Inputs → Build → Validate → Output → Next

  1. Inputs: resolved ticker + structured facts (search_xbrl_facts, get_company_financials) and any filing pages from the three-layer protocol.
  2. Build: write a self-contained Python script using python-pptx that creates the .pptx deck per ## Output Structure. Execute via Bash: python3 script.py. Verify the .pptx file exists at the output path. If python-pptx is absent, fall back to .md slide spec per contracts/office-tooling.md.
  3. Validate: run the ## Validation Gates below.
  4. Output: write the artifact path per ## Output File.
  5. Next: append to agentii.md; hand off to a downstream pitch/review skill if requested.

Disclaimer (Q139/T137) — REQUIRED, template-owned

This output is presentation-shaped, so it MUST carry the canonical disclaimer from scenarios/templates/disclaimer.md — verbatim, not restated or paraphrased. The clause set is the contract; the wording is the workspace's rendering (Q126).

  • Rule 1: include the block as authored. Do not write your own.
  • Rule 2: [WORKSPACE] / [AS_OF] / [GENERATED] are FILLED, never shipped. An unfilled placeholder fails the output gate.
  • Rule 4: the disclaimer states what the document IS; the badges, epistemic_state and coverage-gaps sections state what each claim IS. Do not let the disclaimer carry a burden the body should.

Why this is written here rather than assumed. This skill has no template and no producer (measured 2026-09-18 — scenarios/templates/ holds neither). So there is nothing yet to mount the disclaimer ON, and check_disclaimer.py reports this output as nothing to gate yet rather than as compliant. Recording the requirement in the output contract means it is already binding when a template or producer is written, instead of being rediscovered afterwards — which is how the thesis report's own disclaimer came to be retrofitted rather than designed in.

Output File

Primary deliverable: {ticker}/{YYYY-MM-DD_HHMM}_pitch-deck_{affix}.pptx — real PowerPoint binary via Bash + python-pptx per contracts/office-tooling.md. Degraded fallback: {ticker}/{YYYY-MM-DD_HHMM}_pitch-deck_{affix}.md when python-pptx is absent (FR-044).

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
Files (agentii-investment-intelligence)
  • references
    • capital-allocation-methodology.md 7.4 KB
      # Capital Allocation Assessment — Institutional Methodology
      
      Methodology synthesized from institutional investment research; all text is an original paraphrase.
      
      ---
      
      ## The CEO's Most Important Job
      
      Capital allocation is the primary responsibility of senior management. It describes how a company raises and spends money, and it plays a central role in long-term value creation. Yet the skills that enable someone to become a CEO are often not the same as those needed to allocate capital effectively. New CEOs commonly have the same functional background as their predecessors, and most have experience in general management rather than capital allocation.
      
      The institutional evidence is stark: the vast majority of companies could improve financial performance through more active capital reallocation. Scholars measuring capital reallocation across business units found an optimal degree of reallocation, but fewer than 1% of the 5,760 observations were above that threshold. The other 99%+ under-reallocate.
      
      ---
      
      ## The Eight Uses of Capital
      
      A company's capital deployment is categorized into eight uses. Each has different characteristics, risk profiles, and historical returns.
      
      ### Deployment Benchmarks (1970-2024, US Public Companies)
      
      | Use of Capital | Typical Share | Key Question |
      |---------------|:---:|------|
      | **Mergers & Acquisitions** | ~15% | Is management buying growth at prices that create value? M&A is the largest and riskiest use of capital. |
      | **Capital Expenditures** | ~30% | Is capex directed at growth opportunities or maintenance? Maintenance capex is a cost of staying in business, not an investment. |
      | **Research & Development** | ~18% | Is R&D spending efficient? Revenue per dollar of R&D measures innovation productivity. |
      | **Sales & Marketing** | ~15% | Is S&M spending acquiring customers at acceptable cost? CAC payback period < 12 months for healthy unit economics. |
      | **Net Working Capital** | Variable | Is working capital managed efficiently? DSO + DIO trends signal operational discipline. |
      | **Divestitures** | Variable | Is management willing to exit businesses that don't create value? Inertia is the default. |
      | **Dividends** | Variable | Are dividends sustainable? A dividend cut signals management previously overestimated earnings power. |
      | **Share Buybacks** | Variable | Are buybacks at attractive prices or are they pro-cyclical (buying high)? Buyback timing reveals capital allocation skill. |
      
      ### The Capital Allocation Hierarchy
      
      Capital should be deployed in priority order. The institutional framework:
      
      1. **Fund value-creating organic investments first** (Capex, R&D, S&M with ROIC > WACC)
      2. **Strategic M&A with clear synergy path and disciplined pricing**
      3. **Return excess capital to shareholders** (dividends, buybacks) — this is the residual, not the priority
      4. **Avoid value-destroying uses**: M&A at excessive premiums, buybacks at peak valuations, maintaining "strategic" businesses that destroy value
      
      ---
      
      ## ROIIC as Capital Allocation Quality Metric
      
      Return on Incremental Invested Capital (ROIIC) measures the return on NEW capital deployed:
      
      ```
      ROIIC = ΔNOPAT / ΔInvested Capital (over rolling 3-5 year periods)
      ```
      
      A company with ROIIC consistently above WACC is deploying capital into value-creating opportunities. ROIIC consistently below WACC means growth is destroying value — the company would create more value by returning capital to shareholders than by reinvesting it.
      
      ---
      
      ## Five Principles of Capital Allocation
      
      ### 1. Zero-Based Capital Allocation
      Do not allocate capital based on last year's allocation. Each dollar should go to its highest and best use regardless of precedent. The fact that a division received $100M last year does not mean it should receive it again this year.
      
      ### 2. Fund the Best Opportunities First
      Rank all investment opportunities by expected risk-adjusted return. Fund from the top down until capital is exhausted. The marginal project should earn at least the cost of capital.
      
      ### 3. Dividends and Buybacks Are Residual
      Return capital to shareholders only after all value-creating investment opportunities are funded. A company borrowing to pay dividends or buy back stock is signaling that it cannot find value-creating investments — this is either a mature business or a management team with limited imagination.
      
      ### 4. Understand M&A Track Record
      The majority of acquisitions destroy value for the acquirer's shareholders. Assess management's M&A track record: deal rationale, price discipline, integration execution, and post-deal ROIC vs. pre-deal projections. A CEO who has done 5+ deals should have a measurable track record.
      
      ### 5. Align Incentives with Returns on Capital
      Compensation should be tied to returns-based metrics (ROIC, ROIIC, economic profit), not just growth metrics (revenue, EPS). If management is paid for growth, they will deliver growth — even if it destroys value. If paid for returns, they will deliver returns.
      
      ---
      
      ## Stock-Based Compensation Analysis
      
      ### The Trend
      SBC for Russell 3000 companies has grown from 0.2% of sales in 2006 to 1.3% in 2022. In absolute terms, SBC was approximately $25 billion in 2006 and approximately $270 billion in 2022.
      
      ### The Economic Reality
      SBC is a real economic cost. It transfers value from existing shareholders to employees through dilution. The fact that it is a non-cash expense does not make it a non-cost.
      
      ### Key Metrics
      - **SBC as % of Revenue**: > 1.3% of revenue exceeds the Russell 3000 average — requires explanation
      - **SBC as % of Market Cap**: annual dilution > 2% of market cap per year is a structural earnings quality concern
      - **SBC per Employee**: wide variance across industries — compare to sector peers
      
      ### Dilution Impact
      ```
      True Per-Share Value Growth = Growth in Enterprise Value − SBC Dilution
      ```
      
      A company growing enterprise value at 8% annually but diluting shareholders at 3% through SBC is delivering only 5% per-share value growth. The SBC is a transfer, not a cost saving.
      
      ---
      
      ## Capital Reallocation: The Under-Investment Evidence
      
      The empirical evidence on capital reallocation is striking. Researchers compared year-over-year capital allocation change to improvement in return metrics. They found:
      
      - An optimal degree of reallocation exists — companies should actively shift capital toward higher-return opportunities
      - Fewer than 1% of companies operate above the optimal reallocation threshold
      - 99%+ of companies under-reallocate, consistent with status quo bias and escalation of commitment
      
      The behavioral explanation: managers prefer to continue existing projects rather than admit past errors by reallocating away from them. The sunk cost fallacy is embedded in corporate capital allocation.
      
      ---
      
      ## Red Flags in Capital Allocation
      
      1. M&A as the dominant use of capital (> 40% of deployment) — suggests inability to grow organically
      2. Buybacks exceeding R&D + Capex combined — under-investment in future growth
      3. Buybacks at price-to-book > 3× — likely overpaying for the company's own stock
      4. Dividend payout ratio > 80% when ROIIC < WACC — distributing capital that should be reinvested or preserved
      5. Frequent "strategic reviews" without divestitures — inability to exit failing businesses
      6. SBC > 3% of revenue — severe dilution masking true economic performance
      7. Capex consistently below depreciation — under-investing in asset base maintenance
      8. Working capital build exceeding revenue growth — operational inefficiency absorbing capital
      
    • formula-sheet.md 129 B
      # Pitch Deck — Canonical Formulas
      
      See `## Deliverable Chain` and `## Validation Gates` in SKILL.md for the complete workflow.
      
    • institutional-defaults.md 107 B
      # Pitch Deck — Institutional Defaults
      
      See `## Defaults` table in SKILL.md for default parameter values.
      
    • modes.md 710 B
      # pitch-deck — 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).
      
    • validation-checklist.md 538 B
      # Pitch Deck — Validation Checklist
      
      Expanded version of `## Validation Gates` with per-gate remediation steps.
      
      1. **slide count**: between 12 and 16
       - *Remediation*: If outside: refuse delivery, report actual count.
      2. **executive summary**: present and is slide #2
       - *Remediation*: If missing: refuse delivery.
      3. **source footers**: every slide has standard agentii citation
       - *Remediation*: If any missing: refuse delivery.
      4. **body text density**: no slide > 50 words
       - *Remediation*: If exceeded: flag slides for splitting.
      
  • SKILL.md 7.7 KB
    ---
    name: pitch-deck
    multi_ticker_semantics: single_target
    description: Investment pitch deck, investment committee presentation, buy-side pitch, sell-side pitch, investment thesis slides, executive summary presentation, financial presentation, board deck, investor presentation, strategy deck
    temporal_scope:
     default_quarters: 4
     max_quarters: 8
     description: "Typical lookback: 4 quarters, max: 8"
    allowed_tools:
     - search_companies
     - search_xbrl_facts
     - get_company_financials
     - get_company_profile
     - search_earnings_calendar
     - list_xbrl_concepts
     - Bash
    retrieval_scope: structured_only
    min_tool_diversity: 5
    ---
    
    # pitch-deck
    
    ## Triggers
    
    - Investment pitch deck
    - investment committee presentation
    - buy-side pitch
    - sell-side pitch
    - investment thesis slides
    - executive summary presentation
    - financial presentation
    - board deck
    - investor presentation
    - strategy deck
    
    ## 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: structured_only`. It performs structured data retrieval only (XBRL facts, financials, earnings calendar) — no unstructured document search. Document-retrieval tools are excluded from `allowed_tools`.
    
    ### 2. Retrieval Strategy
    
    Follows the retrieval strategy decision tree in `contracts/retrieval.md`. Primary branch: **(a) Structured Data Query**. Resolve the canonical ticker first (exact → fuzzy alias → share-class) before any data call.
    
    ### 3. Temporal Scope
    
    Default lookback: 4 fiscal quarter(s); maximum: 8. 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)
    - `get_company_financials` — consolidated IS/BS/CF highlights
    - `get_company_profile` — sector/industry classification + metadata
    - `search_earnings_calendar` — EPS actual/estimate/surprise + report dates
    - `list_xbrl_concepts` — XBRL concept discovery for non-standard line items (`namespace` param; default `us-gaap` — use `ifrs-full` for foreign filers)
    
    ### 5. Protocol
    
    1. **Pre-flight (mandatory)**: call `get_company_fiscal_calendar/{ticker}` then `get_ticker_coverage/{ticker}`; route on coverage.
    2. **Concept discovery** (non-standard concepts only): `list_xbrl_concepts(query=<term>, ticker=<T>)`.
    3. **Structured retrieval**: `search_xbrl_facts(ticker, concept=[...], fiscal_year=[...])` (is_primary default) and/or `get_company_financials/{ticker}`.
    4. **Batch rule**: 3+ same-tool queries → consolidate via `batch_search` (≤8 sub-queries).
    5. **Output**: write the deliverable per `## Output File`, then append to `agentii.md`.
    
    ## Deliverable Chain
    
    **Inputs** → **Build** → **Validate** → **Output** → **Next**
    
    1. **Inputs**: resolved ticker + structured facts (`search_xbrl_facts`, `get_company_financials`) and any filing pages from the three-layer protocol.
    2. **Build**: write a self-contained Python script using `python-pptx` that creates the `.pptx` deck per `## Output Structure`. Execute via `Bash: python3 script.py`. Verify the `.pptx` file exists at the output path. If `python-pptx` is absent, fall back to `.md` slide spec per `contracts/office-tooling.md`.
    3. **Validate**: run the `## Validation Gates` below.
    4. **Output**: write the artifact path per `## Output File`.
    5. **Next**: append to `agentii.md`; hand off to a downstream pitch/review skill if requested.
    
    ## Disclaimer (Q139/T137) — REQUIRED, template-owned
    
    This output is **presentation-shaped**, so it MUST carry the canonical disclaimer from
    `scenarios/templates/disclaimer.md` — verbatim, not restated or paraphrased. The
    clause set is the contract; the wording is the workspace's rendering (Q126).
    
    - **Rule 1**: include the block as authored. Do not write your own.
    - **Rule 2**: `[WORKSPACE]` / `[AS_OF]` / `[GENERATED]` are FILLED, never shipped.
      An unfilled placeholder fails the output gate.
    - **Rule 4**: the disclaimer states what the document IS; the badges, `epistemic_state`
      and coverage-gaps sections state what each claim IS. Do not let the disclaimer carry
      a burden the body should.
    
    **Why this is written here rather than assumed.** This skill has **no template and no
    producer** (measured 2026-09-18 — `scenarios/templates/` holds neither). So there is
    nothing yet to mount the disclaimer ON, and `check_disclaimer.py` reports this output as
    `nothing to gate yet` rather than as compliant. Recording the requirement in the output
    contract means it is already binding when a template or producer is written, instead of
    being rediscovered afterwards — which is how the thesis report's own disclaimer came to
    be retrofitted rather than designed in.
    
    ## Output File
    
    Primary deliverable: `{ticker}/{YYYY-MM-DD_HHMM}_pitch-deck_{affix}.pptx` — real PowerPoint binary via `Bash` + `python-pptx` per `contracts/office-tooling.md`. Degraded fallback: `{ticker}/{YYYY-MM-DD_HHMM}_pitch-deck_{affix}.md` when `python-pptx` is absent (FR-044).
    
    ## 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 |
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.

Related