Claude Skill

fda-catalyst-vaccines

Vaccine catalyst analysis across the two-gate path: CBER BLA review and the ACIP recommendation gate that turns FDA approval into commercial availability. Lot release, procurement milestones, pediatric bridging, and healthy-population efficacy context — dated, verified, and sized

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_bio-pharm_skills_agentii_fda-catalyst-vaccines-3b0a195.zip · 5 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/bio-pharm/skills/agentii/fda-catalyst-vaccines
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

Methodology inspired by publicly taught vaccine commercial frameworks; all text is an original paraphrase.

Defaults

Parameter Default Value Rationale
forward_window_quarters 4 Standard catalyst window; extend to 8 on request
include_superseded false Active-only events by default; supersede chains on request
acip_gate true ACIP status always shown next to FDA decisions — approval is not availability
procurement_lens true Government purchasing and campaign milestones tracked
holiday_labeling true Holiday-shifted weeks flagged on every calendar row

Preflight

Run canonical pre-flight per contracts/preflight.md. Propagate X-Agentii-Trace per contracts/x-agentii-trace-header.md. Confirm ticker resolution via search_companies before catalyst queries.

Triggers

  • "When is [vaccine]'s ACIP meeting, and what is the vote outlook?"
  • "Is [vaccine] FDA-approved but still awaiting an ACIP recommendation?"
  • "What does the ACIP vote mean for [ticker]'s commercial launch?"
  • "What procurement milestones are pending for [vaccine/ticker]?"
  • "When is lot release expected for [vaccine]?"
  • "What pediatric or age-cohort bridging studies are pending?"
  • "Build a vaccine catalyst calendar for my watchlist."
  • "Which vaccine decisions land this quarter?"
  • "How do ACIP recommendation categories change uptake?"
  • "What happens between FDA approval and commercial availability?"
  • "Which vaccine catalysts overlap with [ticker]'s earnings date?"
  • "How did similar vaccines trade around their ACIP votes?"

Production Grounding

  • Two-gate path: FDA approval (CBER BLA) is necessary but not sufficient — the ACIP row (scheduled → voted → adopted) is the gate data, with CDC Director sign-off and MMWR publication distinct steps from the vote.
  • ACIP recommendation categories (routine / catch-up / risk-based / shared-clinical-decision-making) set the uptake ceiling; votes move stocks like PDUFA dates move drug names.
  • CBER context: healthy-population efficacy bar (large N, safety-first), lot-release testing, and manufacturing capacity as a catalyst in its own right.
  • Procurement milestones: government stockpiles and purchase contracts (doses/serials, procurement value), seasonal campaign timing.
  • Pediatric bridging, booster cycles, and age-cohort expansions re-open the catalyst window after launch.
  • Holiday-week labeling discipline: campaign-week comps are noisy; label holiday weeks explicitly. Never fabricate votes, dates, or procurement values (per references/knowledge-frameworks.md).

Data Source Priority

  1. ACIP gate data: search_acip_events / get_acip_event (vote counts, status ladder).
  2. FDA/CBER track: get_upcoming_pdufa / search_fda_approvals (BLA events).
  3. Panel and filing context: search_adcom_meetings (VRBPAC) + search_documents / search_sec_filings for procurement and lot-release disclosures.
  4. Historical grounding: search_investment_cases (acip_vote/approval events), search_by_analogue.

Methodology

Retrieval Scope

unstructured_document_search

Retrieval Strategy

  1. Resolve ticker(s) via search_companies; note vaccine product names.
  2. Pull ACIP events (search_acip_events) and FDA-track dates (get_upcoming_pdufa); pair them per product.
  3. For each ACIP event, retrieve vote detail (get_acip_event by vaccine + meeting date) and panel context.
  4. Layer procurement and lot-release milestones from filings (search_sec_filings 8-Ks, search_documents).
  5. Ground the play: search_investment_cases / search_by_analogue with vaccine filters; cite /v/ records.

Temporal Scope

See frontmatter temporal_scope block. Seasonal campaigns may require looking back up to 8 quarters.

Tool Allowlist

See frontmatter allowed_tools.

Protocol

  1. Ticker resolution
  2. Two-gate enumeration (FDA date + ACIP row per product)
  3. Per-event vote framing (recommendation category + history)
  4. Procurement and lot-release overlay
  5. Calendar synthesis + commercial-availability flags

Modes

  • Watchlist (default, multi-ticker): one dated calendar with per-ticker sections, sorted by date.
  • Single ticker deep-dive: full two-gate timeline per vaccine + procurement state.
  • ACIP gate: approval-to-recommendation transition tracking across names.

Tool Fallbacks

Failure Fallback
search_acip_events empty search_documents keyword ACIP + search_sec_filings; annotate coverage_gap
No ACIP row for a product Flag the unmodeled commercial step explicitly; never assume approval = launch
Procurement data missing State purchase-contract data unavailable; do not estimate values
Knowledge tools empty Proceed with structured data only; annotate knowledge coverage_gap

Output File

{ticker}/{YYYY-MM-DD_HHMM}_fda-catalyst-vaccines_{affix}.md (watchlist: watchlist/{YYYY-MM-DD_HHMM}_fda-catalyst-vaccines-calendar_{affix}.md)

Output Structure

  1. Executive Summary — highest-impact vaccine catalysts in the window, 2-3 sentences
  2. Two-Gate Calendar — dated table: date, ticker, product, FDA event, ACIP row, holiday-week flag, availability framing
  3. Per-Event Analysis — vote context (recommendation category, committee read) + decision history
  4. Procurement & Lot Release — contracts, stockpile status, campaign timing
  5. Historical Analogues — matched vaccine cases with /v/ citations and quantified outcomes
  6. Risk Assessment & Coverage Gaps — binary-risk sizing, two-gate failure modes, missing data

Error Handling

Error Fallback
No ACIP or PDUFA rows Fall back to earnings + pipeline events; annotate coverage_gap — never fabricate dates
Approval without ACIP row Present the gap as the central risk; do not imply commercial availability
Ticker not in med universe Resolve via CIK/vaccine-universe match; surface the classification gap

Memory Load

See contracts/memory-load.md.

Snapshot

See contracts/snapshot-synthesis.md.

Final Summary (TUI)

Include ### Key Citations block with 0-10 clickable /v/ URLs.

References

  • contracts/citation-and-memory.md
  • contracts/output-frontmatter-schema.md
  • contracts/memory-load.md
  • contracts/snapshot-synthesis.md
  • contracts/preflight.md
  • references/knowledge-frameworks.md
Files (agentii-investment-intelligence)
  • references
    • knowledge-frameworks.md 4.5 KB
      # FDA Catalyst Vaccines — Knowledge Frameworks
      
      Static grounding for `fda-catalyst-vaccines` (spec 055). Runtime records are retrieved via the knowledge tools and cited with /v/ URLs; this file carries the two-gate pathway ladder, failure modes, and the pattern disciplines. Shared regulatory scaffolding (scrutiny axes, binary-event sizing) lives in `../../fda-catalyst-analysis/references/knowledge-frameworks.md`.
      
      ## The Two-Gate Pathway Ladder
      
      1. **CBER BLA filing**: vaccines are biologics — review sits at CBER, with VRBPAC as the advisory committee.
      2. **FDA approval**: necessary but not sufficient. The approval catalyzes the stock, not the market.
      3. **ACIP review**: the Advisory Committee on Immunization Practices convenes on product, population, and schedule questions; the status ladder runs scheduled → voted → adopted.
      4. **CDC Director sign-off + MMWR publication**: distinct steps from the vote — a voted recommendation becomes policy only after adoption and publication.
      5. **Lot release**: each manufactured lot is released by CBER before shipment — a recurring operational gate that can delay a launch.
      6. **Procurement + campaign**: government stockpiles and purchase contracts (doses/serials, procurement value), seasonal campaign timing.
      7. **Cohort uptake**: ACIP-cohort uptake against the recommendation category sets the commercial trajectory.
      
      ## ACIP Recommendation Categories (the uptake ceiling)
      
      - **Routine**: full age-based recommendation — the widest commercial gate.
      - **Catch-up**: populations that missed the routine window.
      - **Risk-based**: restricted to at-risk groups — a materially smaller market.
      - **Shared-clinical-decision-making**: provider-patient discretion — the narrowest ceiling.
      
      The category, not the vote count, is the commercial data point.
      
      ## Failure Modes
      
      - **Treating FDA approval as commercial availability**: the ACIP row is the gate data; skipping it inflates the near-term revenue path.
      - **Conflating the vote with adoption**: CDC Director sign-off and MMWR publication are separate, delayable steps.
      - **Ignoring procurement timing**: government purchasing is lumpy; a stockpile order is a one-time catalyst, not a run-rate signal.
      - **Underweighting the healthy-population bar**: safety signals in large healthy cohorts get outsized regulatory scrutiny; the efficacy bar is prevention, not treatment.
      - **Missing pediatric bridging**: pediatric and age-cohort recommendations re-open the catalyst window after launch.
      - **Unlabeled holiday weeks**: campaign-week comps across holidays are noise without labels.
      
      ## Methodology Patterns (original paraphrase of publicly taught practice)
      
      ### Vaccine vocabulary (P1, cross-cutting)
      
      Doses/serials, procurement value, ACIP-cohort uptake. Launch tracking: consensus sales ÷ dose price ÷ campaign window → required doses → linear path vs actuals, overlaid with at least two named same-category uptake curves.
      
      ### Event-takeaway anatomy (P4)
      
      Headline verdict → per-stock takeaways → KOL distillation → vote data and category reads → modeled deltas vs consensus → what's-changed vectors → risk bullets. Conflicting committee reads surfaced verbatim and rated by materiality.
      
      ### POS / scenario discipline (cross-cutting)
      
      Unadjusted peak x POS = modeled number; the ACIP gate is a POS input, not an afterthought. Bull/base/bear with named-driver grids (category outcome, procurement size, campaign timing); explicit abstention where unquantifiable.
      
      ## Structured Data Surfaces
      
      - `search_acip_events` / `get_acip_event` — the CDC ACIP calendar with the status ladder and vote counts per vaccine + meeting date.
      - `get_upcoming_pdufa` / `search_fda_approvals` — CBER BLA dates and history.
      - `search_adcom_meetings` — VRBPAC meeting records and briefing inventories.
      
      ## Cross-Cutting Habits
      
      - **Buy-side lens**: track where investor attention sits; the client-question pattern — answer the most common question directly (e.g. "which recommendation category will the ACIP vote land?"); per-name bull/bear pivot conditions tied to the category outcome.
      - **Living-thesis loop**: estimates move first, ratings last; append exhibits to the prior note, never rewrite; campaign-week labels persist.
      - **Badge mapping (FR-092)**: verifiable facts `[FACT]`, derived arithmetic `[DEDUCTED]`, judgments `[VIEW]` — with a Category/Count/% summary table.
      
      ## Authoring-time citations
      
      Spec 055 med strategies and cases are linked here as they reach `approved` status; at runtime retrieve via `search_investment_cases` / `search_by_analogue` and cite with /v/ URLs.
      
    • modes.md 461 B
      # fda-catalyst-vaccines — Analyst Mode Definitions
      
      Derived from the skill's ## Modes section (spec 046 M1).
      
      ### Mode: watchlist
      
      **Objective**: One dated vaccine catalyst calendar with per-ticker sections, sorted by date.
      
      ### Mode: single-target
      
      **Objective**: Full two-gate timeline for one vaccine with procurement and lot-release state.
      
      ### Mode: acip-gate
      
      **Objective**: Track the approval-to-recommendation transition across names in the universe.
      
  • SKILL.md 7.2 KB
    ---
    name: fda-catalyst-vaccines
    description: "Vaccine catalyst analysis across the two-gate path: CBER BLA review and the ACIP recommendation gate that turns FDA approval into commercial availability. Lot release, procurement milestones, pediatric bridging, and healthy-population efficacy context — dated, verified, and sized per event."
    sectors: [med.medicines_biotech, med.medical_devices]
    multi_ticker_semantics: basket_v1_1
    temporal_scope:
      default_quarters: 4
      max_quarters: 8
      description: "Forward catalyst window default 4 quarters; up to 8 for multi-season campaign and bridging cycles."
    allowed_tools:
      - search_acip_events
      - get_acip_event
      - get_upcoming_pdufa
      - search_adcom_meetings
      - search_fda_approvals
      - search_companies
      - search_documents
      - search_sec_filings
      - search_investment_cases
      - search_by_analogue
      - search_knowledge_entries
    retrieval_scope: unstructured_document_search
    min_tool_diversity: 3
    parameter_free: false
    ---
    
    > Methodology inspired by publicly taught vaccine commercial frameworks; all text is an original paraphrase.
    
    ## Defaults
    
    | Parameter | Default Value | Rationale |
    |-----------|---------------|-----------|
    | forward_window_quarters | 4 | Standard catalyst window; extend to 8 on request |
    | include_superseded | false | Active-only events by default; supersede chains on request |
    | acip_gate | true | ACIP status always shown next to FDA decisions — approval is not availability |
    | procurement_lens | true | Government purchasing and campaign milestones tracked |
    | holiday_labeling | true | Holiday-shifted weeks flagged on every calendar row |
    
    ## Preflight
    
    Run canonical pre-flight per `contracts/preflight.md`. Propagate X-Agentii-Trace per `contracts/x-agentii-trace-header.md`. Confirm ticker resolution via `search_companies` before catalyst queries.
    
    ## Triggers
    
    - "When is [vaccine]'s ACIP meeting, and what is the vote outlook?"
    - "Is [vaccine] FDA-approved but still awaiting an ACIP recommendation?"
    - "What does the ACIP vote mean for [ticker]'s commercial launch?"
    - "What procurement milestones are pending for [vaccine/ticker]?"
    - "When is lot release expected for [vaccine]?"
    - "What pediatric or age-cohort bridging studies are pending?"
    - "Build a vaccine catalyst calendar for my watchlist."
    - "Which vaccine decisions land this quarter?"
    - "How do ACIP recommendation categories change uptake?"
    - "What happens between FDA approval and commercial availability?"
    - "Which vaccine catalysts overlap with [ticker]'s earnings date?"
    - "How did similar vaccines trade around their ACIP votes?"
    
    ## Production Grounding
    
    - Two-gate path: FDA approval (CBER BLA) is necessary but not sufficient — the ACIP row (scheduled → voted → adopted) is the gate data, with CDC Director sign-off and MMWR publication distinct steps from the vote.
    - ACIP recommendation categories (routine / catch-up / risk-based / shared-clinical-decision-making) set the uptake ceiling; votes move stocks like PDUFA dates move drug names.
    - CBER context: healthy-population efficacy bar (large N, safety-first), lot-release testing, and manufacturing capacity as a catalyst in its own right.
    - Procurement milestones: government stockpiles and purchase contracts (doses/serials, procurement value), seasonal campaign timing.
    - Pediatric bridging, booster cycles, and age-cohort expansions re-open the catalyst window after launch.
    - Holiday-week labeling discipline: campaign-week comps are noisy; label holiday weeks explicitly. Never fabricate votes, dates, or procurement values (per `references/knowledge-frameworks.md`).
    
    ## Data Source Priority
    
    1. ACIP gate data: `search_acip_events` / `get_acip_event` (vote counts, status ladder).
    2. FDA/CBER track: `get_upcoming_pdufa` / `search_fda_approvals` (BLA events).
    3. Panel and filing context: `search_adcom_meetings` (VRBPAC) + `search_documents` / `search_sec_filings` for procurement and lot-release disclosures.
    4. Historical grounding: `search_investment_cases` (acip_vote/approval events), `search_by_analogue`.
    
    ## Methodology
    
    ### Retrieval Scope
    unstructured_document_search
    
    ### Retrieval Strategy
    1. Resolve ticker(s) via `search_companies`; note vaccine product names.
    2. Pull ACIP events (`search_acip_events`) and FDA-track dates (`get_upcoming_pdufa`); pair them per product.
    3. For each ACIP event, retrieve vote detail (`get_acip_event` by vaccine + meeting date) and panel context.
    4. Layer procurement and lot-release milestones from filings (`search_sec_filings` 8-Ks, `search_documents`).
    5. Ground the play: `search_investment_cases` / `search_by_analogue` with vaccine filters; cite /v/ records.
    
    ### Temporal Scope
    See frontmatter temporal_scope block. Seasonal campaigns may require looking back up to 8 quarters.
    
    ### Tool Allowlist
    See frontmatter allowed_tools.
    
    ### Protocol
    1. Ticker resolution
    2. Two-gate enumeration (FDA date + ACIP row per product)
    3. Per-event vote framing (recommendation category + history)
    4. Procurement and lot-release overlay
    5. Calendar synthesis + commercial-availability flags
    
    ## Modes
    
    - **Watchlist** (default, multi-ticker): one dated calendar with per-ticker sections, sorted by date.
    - **Single ticker deep-dive**: full two-gate timeline per vaccine + procurement state.
    - **ACIP gate**: approval-to-recommendation transition tracking across names.
    
    ## Tool Fallbacks
    
    | Failure | Fallback |
    |---------|----------|
    | search_acip_events empty | `search_documents` keyword ACIP + `search_sec_filings`; annotate coverage_gap |
    | No ACIP row for a product | Flag the unmodeled commercial step explicitly; never assume approval = launch |
    | Procurement data missing | State purchase-contract data unavailable; do not estimate values |
    | Knowledge tools empty | Proceed with structured data only; annotate knowledge coverage_gap |
    
    ## Output File
    
    `{ticker}/{YYYY-MM-DD_HHMM}_fda-catalyst-vaccines_{affix}.md` (watchlist: `watchlist/{YYYY-MM-DD_HHMM}_fda-catalyst-vaccines-calendar_{affix}.md`)
    
    ## Output Structure
    
    1. **Executive Summary** — highest-impact vaccine catalysts in the window, 2-3 sentences
    2. **Two-Gate Calendar** — dated table: date, ticker, product, FDA event, ACIP row, holiday-week flag, availability framing
    3. **Per-Event Analysis** — vote context (recommendation category, committee read) + decision history
    4. **Procurement & Lot Release** — contracts, stockpile status, campaign timing
    5. **Historical Analogues** — matched vaccine cases with /v/ citations and quantified outcomes
    6. **Risk Assessment & Coverage Gaps** — binary-risk sizing, two-gate failure modes, missing data
    
    ## Error Handling
    
    | Error | Fallback |
    |-------|----------|
    | No ACIP or PDUFA rows | Fall back to earnings + pipeline events; annotate `coverage_gap` — never fabricate dates |
    | Approval without ACIP row | Present the gap as the central risk; do not imply commercial availability |
    | Ticker not in med universe | Resolve via CIK/vaccine-universe match; surface the classification gap |
    
    ## Memory Load
    
    See `contracts/memory-load.md`.
    
    ## Snapshot
    
    See `contracts/snapshot-synthesis.md`.
    
    ## Final Summary (TUI)
    
    Include ### Key Citations block with 0-10 clickable /v/ URLs.
    
    ## References
    
    - `contracts/citation-and-memory.md`
    - `contracts/output-frontmatter-schema.md`
    - `contracts/memory-load.md`
    - `contracts/snapshot-synthesis.md`
    - `contracts/preflight.md`
    - `references/knowledge-frameworks.md`
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.

Related