跳到正文
cccskills
免费在 GitHub 公开

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 per event.

中文简介正在准备中。当前显示原文说明。

实测评分 未实测

查看安装方法

包含的文件(3)

  • SKILL.md7.4 KB
  • references/knowledge-frameworks.md4.5 KB
  • references/modes.md461 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

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

Defaults

ParameterDefault ValueRationale
forward_window_quarters4Standard catalyst window; extend to 8 on request
include_supersededfalseActive-only events by default; supersede chains on request
acip_gatetrueACIP status always shown next to FDA decisions — approval is not availability
procurement_lenstrueGovernment purchasing and campaign milestones tracked
holiday_labelingtrueHoliday-shifted weeks flagged on every calendar row

Preflight

Run canonical pre-flight per contracts/preflight.md. Include the X-Agentii-Trace header on every tool call per contracts/x-agentii-trace-header.md — carry the _run_id from your first tool result and name yourself (and your parent, if you were spawned). 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

FailureFallback
search_acip_events emptysearch_documents keyword ACIP + search_sec_filings; annotate coverage_gap
No ACIP row for a productFlag the unmodeled commercial step explicitly; never assume approval = launch
Procurement data missingState purchase-contract data unavailable; do not estimate values
Knowledge tools emptyProceed 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

ErrorFallback
No ACIP or PDUFA rowsFall back to earnings + pipeline events; annotate coverage_gap — never fabricate dates
Approval without ACIP rowPresent the gap as the central risk; do not imply commercial availability
Ticker not in med universeResolve 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

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

3-statement financial model, integrated IS BS CF, income statement projection, balance sheet forecast, cash flow statement, cross-statement balancing, financial model build, operating model, three statement model, integrated financial statements

中文简介正在准备中。当前显示原文说明。

agentii-ai/agentii-investment-intelligence2072026年10月20日 更新

Institutional-grade equity research skills for AI agents. 80 Claude-type skills across 14 verticals (equity-research-core, models-and-pitches, bio-pharm, scenarios, quantitative-analysis, idea-generation, options-derivatives, business-intelligence, industry-analysis, macro-strategy, portfolio-strategy, technical-analysis, risk-and-psychology, trading-as-business) powered by agentii.ai's agent-use-ready SEC filing data plane — SEC filings and 15K+ earnings call transcripts, 15.99M XBRL facts, and company profiles for 1,146+ US-public-equity tickers. Features the three-layer retrieval protocol (Document Discovery → Page Map → Deep Read, with deep-outline escalation) — measured, not asserted: 97.5% saved against a sequential read, and the page map itself is 10.0% of one (spec 062 T030, 2026-09-23) — server-side parallel multi-period search via search_cross_period, a full Excel/PPT generation pipeline with 3-tier office backend support, and the spec-046 governance layer (constitution, thesis and single-skill modes, mechanical gates, and a template-owned disclaimer on generated reports).

中文简介正在准备中。当前显示原文说明。

agentii-ai/agentii-investment-intelligence2072026年10月20日 更新

audit-xls

免费

Audit spreadsheet, formula error detection, hardcoded cell finder, cross-sheet reference audit, workbook auditor, Excel model audit, financial model QA, spreadsheet review, cell dependency trace, formula integrity check

中文简介正在准备中。当前显示原文说明。

agentii-ai/agentii-investment-intelligence2072026年10月20日 更新

Business model classification, business model analysis, structural analysis of how a company makes money, product offering decomposition, distribution channel analysis, customer segment analysis, revenue model identification, market sizing TAM SAM SOM, competitive positioning, business unit performance, management team & leadership analysis, what does the company sell, how does the company go to market, business model type platform service product, channel mix direct vs indirect, revenue concentration risk, CEO CFO executive backgrounds and changes

中文简介正在准备中。当前显示原文说明。

agentii-ai/agentii-investment-intelligence2072026年10月20日 更新

challenge

免费

Adversarial verification of research theses — cross-run/cross-thesis contradiction via the entity index, pre-mortem (Klarman/Kahneman: assume the loss already happened, reverse the path), inversion (Munger: invert, always invert), and wrong_if falsifiability review. ≈50-finding cap sorted by severity; content-derived finding IDs; incremental scoping with three backstops; lifecycle hooks at pillar-complete / thesis-complete / pre-reduction.

中文简介正在准备中。当前显示原文说明。

agentii-ai/agentii-investment-intelligence2072026年10月20日 更新

Chart pattern recognition, price action patterns, candlestick signal bars, pullback bar counting H1/H2/H3/H4, trend channels, micro channels, trading ranges, breakouts, major trend reversals 5-step sequence, wedges, double tops and bottoms, triangles, head and shoulders, climaxes, measured moves, support and resistance

中文简介正在准备中。当前显示原文说明。

agentii-ai/agentii-investment-intelligence2072026年10月20日 更新

查看 agentii-ai 的全部技能

报告此技能的问题