Fda Catalyst Medicines logo

Fda Catalyst Medicines

Community
agentii-ai
fda-catalyst-medicines

CDER-track catalyst analysis for medicines: PDUFA target dates, AdCom votes, sNDA/sBLA label expansions, biosimilar interchangeability and 180-day exclusivity, Orange Book state, and CRL remediation timelines — enumerated, verified, and sized per event for any biotech/pharma ticker or watchlist.

Overview

Publisheragentii-ai
Repositoryagentii-investment-intelligence
Skill namefda-catalyst-medicines
Stars
207
Forks
16
Bundled files
2
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by agentii-ai on GitHub. Read the source before you install it.

Installation

Install the Fda Catalyst Medicines AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/agentii-ai/agentii-investment-intelligence/tree/main/marketplace-beachhead/plugins/bio-pharm/skills/agentii/fda-catalyst-medicines
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/agentii-ai/agentii-investment-intelligence.git /tmp/agentii-investment-intelligence
mkdir -p .claude/skills
cp -r /tmp/agentii-investment-intelligence/marketplace-beachhead/plugins/bio-pharm/skills/agentii/fda-catalyst-medicines .claude/skills/fda-catalyst-medicines
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Fda Catalyst Medicines in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Fda Catalyst Medicines on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Fda Catalyst Medicines is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Methodology inspired by publicly taught biotech catalyst 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
exclusivity_trackingtrueOrange Book and 180-day exclusivity state attached to launch-relevant events
holiday_labelingtrueHoliday-shifted weeks flagged on every calendar row
horizon_days180Default for get_upcoming_pdufa horizon

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 the PDUFA date for [drug/ticker]?"
  • "What AdCom meetings are coming up for [ticker]?"
  • "Has [drug]'s sNDA/sBLA label expansion been approved?"
  • "Which biosimilars have interchangeability designation, and when does 180-day exclusivity run?"
  • "What is [drug]'s Orange Book patent and exclusivity state?"
  • "How is [ticker]'s CRL remediation timeline shaping up?"
  • "Build a PDUFA/AdCom calendar for my pharma watchlist."
  • "Evaluate the approval odds for [drug] ahead of its AdCom."
  • "What label expansions are pending for [ticker] this year?"
  • "Which medicine decisions land this quarter?"
  • "How do biosimilar launches erode the reference product's share?"
  • "Which catalysts overlap with [ticker]'s earnings date?"

Production Grounding

  • CDER mechanics: NDA/BLA review tracks, PDUFA target dates, priority review, breakthrough designation, accelerated approval, CRL deficiency classes and the remediation reset, AdCom vote patterns.
  • Label expansions (sNDA/sBLA) are the commercial catalysts beyond first approval; Orange Book patent and exclusivity state sets the generic or biosimilar entry window.
  • Biosimilar timeline note: interchangeability plus 180-day exclusivity for the first interchangeable delays competing entry — and approval is not launch; commercial timing follows exclusivity expiry and patent-settlement terms.
  • Holiday-week labeling discipline: comps across holiday-shifted weeks are noisy; every calendar row carries its caveat, and holiday weeks are labeled explicitly.
  • Apply AdCom-style scrutiny axes when framing outcome odds; never fabricate dates, votes, or outcomes — annotate coverage gaps instead (per references/knowledge-frameworks.md).

Data Source Priority

  1. Structured catalyst data: get_upcoming_pdufa / get_pdufa_decision (pipeline.fda_calendar_event).
  2. AdCom and approval history: search_adcom_meetings / get_adcom_meeting; search_fda_approvals / get_fda_approval.
  3. Company and filing context: get_company_profile, search_documents, search_sec_filings; briefing docs via list_sources(source_type=adcom_briefing) + read_source_outline/read_source_pages with meeting slugs.
  4. Historical grounding: search_investment_cases (event_type=adcom_vote/pdufa_decision/crl/approval), search_by_analogue, search_investment_strategies (sectors=med).
  5. Earnings overlap: search_earnings_calendar / list_upcoming_earnings.

Methodology

Retrieval Scope

unstructured_document_search

Retrieval Strategy

  1. Resolve ticker(s) via search_companies; note primary drug/application names.
  2. Pull active PDUFA events (get_upcoming_pdufa, horizon_days=default); layer AdCom meetings and earnings dates.
  3. Per event: decision history (get_pdufa_decision by drug/application), approval record (get_fda_approval), label and Orange Book state.
  4. For AdCom events, retrieve briefing documents via list_sources + read_source_outline/read_source_pages using meeting slugs; apply scrutiny axes.
  5. Ground the play in knowledge: search_investment_cases / search_by_analogue with med filters; cite /v/ records.

Temporal Scope

See frontmatter temporal_scope block. Exclusivity windows may require looking back up to 8 quarters when requested.

Tool Allowlist

See frontmatter allowed_tools.

Protocol

  1. Ticker resolution
  2. Catalyst enumeration (PDUFA / AdCom / label expansion / exclusivity events)
  3. Per-event outcome framing (scrutiny axes + decision history)
  4. Historical analogue retrieval
  5. Calendar synthesis + exclusivity and risk flags

Modes

  • Watchlist (default, multi-ticker): one dated calendar with per-ticker sections, sorted by date.
  • Single ticker deep-dive: full event timeline, per-event probability framing, label and exclusivity state.
  • Event type: restrict to PDUFA / AdCom / label expansion / biosimilar milestones on request.
  • Exclusivity scan: Orange Book and 180-day windows as the launch-timing lens.

Tool Fallbacks

FailureFallback
get_upcoming_pdufa emptySearch filings (search_documents keyword PDUFA) + search_sec_filings 8-Ks; annotate coverage_gap
AdCom briefing path 404search_documents with source_institution filter; degrade to calendar metadata
Knowledge tools emptyProceed with structured data only; annotate knowledge coverage_gap
Orange Book state unknownFlag exclusivity window unavailable; never infer expiry dates

Output File

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

Output Structure

  1. Executive Summary — highest-impact CDER-track catalysts in the window, 2-3 sentences
  2. Catalyst Calendar — dated table: date, ticker, event type, drug, application, holiday-week flag, expected-impact framing
  3. Per-Event Analysis — scrutiny-axes assessment (safety/statistics/subgroups/benefit-risk) + decision history
  4. Label & Exclusivity State — sNDA/sBLA status, Orange Book state, 180-day windows, biosimilar entry timing
  5. Historical Analogues — matched cases with /v/ citations and quantified outcomes
  6. Risk Assessment & Coverage Gaps — binary-risk sizing, overlap clusters, unverified or missing data

Error Handling

ErrorFallback
No PDUFA rowsFall back to earnings + AdCom + label events; annotate coverage_gap — never fabricate dates
Superseded datesActive-only by default; expose supersede chain via include_superseded=true
Ticker not in med universeResolve via CIK/drug-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

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Fda Catalyst Medicines AI skill do?

CDER-track catalyst analysis for medicines: PDUFA target dates, AdCom votes, sNDA/sBLA label expansions, biosimilar interchangeability and 180-day exclusivity, Orange Book state, and CRL remediation timelines — enumerated, verified, and sized per event for any biotech/pharma ticker or watchlist.

Why use Fda Catalyst Medicines on TypingMind?

Because you install it once and use it with any model. Fda Catalyst Medicines is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Fda Catalyst Medicines in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/agentii-ai/agentii-investment-intelligence/tree/main/marketplace-beachhead/plugins/bio-pharm/skills/agentii/fda-catalyst-medicines. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Fda Catalyst Medicines?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Fda Catalyst Medicines?

As many as you like. As long as a model supports skills, you can use Fda Catalyst Medicines with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Fda Catalyst Medicines AI skill free?

Yes. It is published on GitHub by agentii-ai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇