hh-health-ai/healthcare-equity/epi-funnel-input
Claude Code and agent skill by hh-health-ai/healthcare-equity
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
This skill should be used when the user asks to "build the patient funnel for [indication]", "size the addressable population", "epi inputs for the rNPV/TAM", "prevalence and incidence for [disease]", or needs the disease-burden top of a revenue model.
Install
npx vskill@latest install hh-health-ai/healthcare-equity/epi-funnel-inputSKILL.md
Epidemiology Funnel Input
Build the code-anchored disease-burden top of the patient funnel — the defensible input to TAM and rNPV work.
Workflow
- Define the indication in code terms via the ICD10 Codes connector: the ICD-10-CM family and the clinically relevant subsets (severity, line-of-therapy, biomarker restrictions the label imposes — pull exact label language from clinical-catalysts adcom-label when a label exists). The code definition disciplines the epidemiology search and later lets claims data validate the estimate.
- Assemble prevalence/incidence from graded sources via PubMed connector and web research: national surveillance (CDC/registries) > published epi studies > society estimates > company decks (label company TAM claims as claims-to-test, not inputs). Time-stamp and geography-stamp every figure; US vs global funnels are separate builds.
- Construct the funnel explicitly, one conversion per line with its source: population → prevalent/incident cases → diagnosed (diagnosis rate is the classic overestimate — seek claims-based validation) → treatment-eligible under the actual/expected label → presenting to the relevant specialty (link provider-adoption's footprint as the capacity check) → realistic peak-penetration band anchored on analog launches. Show ranges, not points, where sources disagree.
- Sanity-check against observed reality: does the implied treated population reconcile with current claims volumes (procedure-volume-tracker) and reported patient counts of incumbents? An epi funnel that implies more treated patients than the claims data shows is wrong at the diagnosis or presentation step — reconcile before shipping. This is the THM-02 bottoms-up discipline (the full TAM prompt lives in healthcare-equity screen-themes; this skill produces its healthcare-specific top).
- State what the funnel does not prove (funnel-discipline reference): disease burden is a ceiling, not demand; eligibility is not paid demand.
- End with the EVIDENCE BRIEF block (layer: commercial-volume/exposure). Hand the funnel to healthcare-equity model-valuation (MOD-03 rNPV patient funnel) with every conversion assumption exposed for scenario work.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingmodules/procedure-exposure/skills/epi-funnel-input/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/hh-health-ai/healthcare-equity/epi-funnel-input)