Market Share Tracking logo

Market Share Tracking

Community
agentii-ai
market-share-tracking

Weekly product-level commercial tracking — TRx/NRx with current/4-wk/12-wk share and YoY, launch curves overlaid with same-class analogs plus a consensus-implied trajectory, LOE/biosimilar erosion series, GTN/net-price stress brackets, and per-row data-caveat discipline. Use to track any launched drug, biologic, device, or vaccine against its class and consensus.

Overview

Publisheragentii-ai
Repositoryagentii-investment-intelligence
Skill namemarket-share-tracking
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 Market Share Tracking 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/market-share-tracking
  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/market-share-tracking .claude/skills/market-share-tracking
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Market Share Tracking 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 Market Share Tracking 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 Market Share Tracking 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 commercial-tracking approaches; all text is an original paraphrase.

Defaults

ParameterDefault ValueRationale
windowscurrent / 4-wk / 12-wkThree-window share + growth lattice
growth_metricTRx YoYWeekly, 4-wk, and 12-wk YoY alongside share
analog_count2≥2 named same-class analogs on the launch board
consensus_sourcecompany-levelProduct consensus via segment-share math [DEDUCTED]
caveatsper-rowA number without a caveat annotation is a defect

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 commercial-track queries.

Triggers

  • "Is [product] tracking above or below consensus?"
  • "How is the [product] launch trending?"
  • "Build the launch board for [product] with class analogs."
  • "What is the consensus-implied trajectory for [product]?"
  • "Show [product]'s TRx share and YoY for the last 12 weeks."
  • "How fast is [biosimilar] eroding [branded product]?"
  • "Stress-test [product]'s net price and GTN."
  • "What are the caveats on [product]'s scripts?"
  • "Track installed base and utilization for [device]."
  • "How is ACIP-cohort uptake tracking for [vaccine]?"

Production Grounding

  • Three-window lattice: current / 4-wk / 12-wk share and YoY; previous values shown next to new values.
  • Launch boards: actuals vs ≥2 named same-class analogs + consensus-implied trajectory (consensus sales ÷ net price ÷ script duration → required TRx → linear path); assumptions stated.
  • LOE erosion: entrant share vs branded YoY decay with approval/launch dates.
  • GTN/net-price stress: GTN brackets (50→80% flex), $/Rx = quarterly sales ÷ scripts, channel mix; half-of-sales-minus-volume net price is a stated judgment [VIEW].
  • Modality vocabularies: scripts/share/erosion (drugs & biologics); installed base, placements/procedures, utilization, ASP (devices); doses/serials, procurement, ACIP-cohort uptake (vaccines); never a script number for a device or vaccine.
  • Per-row caveats: restricted scripts, rounding, indication-mixed, IV invisibility, holiday weeks — every row carries its caveat or coverage_gap.
  • Badges: [FACT]/[DEDUCTED]/[VIEW] with the summary table.

Data Source Priority

  1. search_commercial_track — weekly track rows with stored previous values.
  2. Company-reported product sales: 10-K/Q XBRL (get_statement) and MD&A (search_documents).
  3. Transcript commentary on scripts/share/persistence via search_documents.
  4. Payer coverage/PA announcements and openFDA label events via search_documents + list_sources.
  5. Consensus: search_earnings_calendar company-level only; licensed Rx panels never assumed.

Methodology

Retrieval Scope

unstructured_document_search

Retrieval Strategy

  1. Resolve basket tickers via search_companies; map products to companies.
  2. Pull weekly rows via search_commercial_track (previous values stored alongside).
  3. Compute the three-window lattice from stored history; attach per-row caveats.
  4. Build the launch board: ≥2 named analog curves + consensus-implied trajectory arithmetic.
  5. LOE events: pair entrant share with branded YoY decay; date approval/launch.
  6. Stress net price (GTN brackets, $/Rx, channel mix); label derived values [DEDUCTED].
  7. Ground in knowledge (sectors=med); cite /v/ records.

Temporal Scope

See frontmatter temporal_scope block. Rolling windows recompute from stored history; holiday weeks are labeled.

Tool Allowlist

See frontmatter allowed_tools.

Protocol

  1. Ticker + product resolution
  2. Commercial-track pull (stored history)
  3. Three-window lattice computation
  4. Launch-board overlay + implied trajectory
  5. LOE erosion series (when applicable)
  6. GTN/net-price stress + caveat audit

Modes

  • Drug / biologic (default): scripts/share/erosion; LOE/biosimilar series.
  • Device: installed base, placements/procedures, utilization, ASP; no script numbers.
  • Vaccine: doses/serials, procurement, ACIP-cohort uptake; approval ≠ commercial availability.
  • Basket: multi-ticker watchlist with per-name sections.

Tool Fallbacks

FailureFallback
search_commercial_track emptyCompany-reported sales (get_statement/search_documents); annotate coverage_gap
Scripts restricted (IQVIA)State the restriction verbatim; refuse a share number; use company-reported metrics
No product consensusSegment share × company consensus [DEDUCTED]; else coverage_gap with required inputs
No analog seriesNamed-analog list with disclosed sales/scripts; flag degraded
One-quarter issuer / pre-revenuePipeline/cash-runway logic; no share arithmetic

Output File

{ticker}/{YYYY-MM-DD_HHMM}_market-share-tracking_{affix}.md (basket: watchlist/{YYYY-MM-DD_HHMM}_market-share-tracker_{affix}.md)

Output Structure

  1. Executive Summary — actuals vs consensus-implied trajectory, 2-3 sentences
  2. Launch Board — actuals vs ≥2 named analogs + consensus-implied path with stated arithmetic
  3. Share & YoY Lattice — current/4-wk/12-wk share and YoY with previous values
  4. LOE / Erosion Series — entrant share vs branded YoY decay with approval/launch dates
  5. Net-Price & GTN Stress — $/Rx, GTN brackets, channel mix, [DEDUCTED] labels
  6. Caveat Register — per-row annotations + coverage_gap list
  7. Coverage Gaps — missing sources and degraded modes

Error Handling

ErrorFallback
No commercial-track rowsCompany-reported sales only; annotate coverage_gap — never fabricate scripts
Product not in med universeResolve via product/company match; surface the classification gap
Consensus absentcoverage_gap with required inputs (sales, net price, script duration)

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 Market Share Tracking AI skill do?

Weekly product-level commercial tracking — TRx/NRx with current/4-wk/12-wk share and YoY, launch curves overlaid with same-class analogs plus a consensus-implied trajectory, LOE/biosimilar erosion series, GTN/net-price stress brackets, and per-row data-caveat discipline. Use to track any launched drug, biologic, device, or vaccine against its class and consensus.

Why use Market Share Tracking on TypingMind?

Because you install it once and use it with any model. Market Share Tracking 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 Market Share Tracking 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/market-share-tracking. 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 Market Share Tracking?

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 Market Share Tracking?

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

Is the Market Share Tracking 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 👇