pipeline-devices
Device pipeline analysis: feasibility and pivotal study stages, design-iteration cycles, RWE studies, and post-market obligations, with reimbursement-aware value framing and decision-track awareness across the med universe.
Install
npx skills add https://github.com/agentii-ai/agentii-investment-intelligence/tree/main/plugins/vertical-plugins/bio-pharm/skills/agentii/pipeline-devices
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install agentii-ai-agentii-investment-intelligence@llmmart
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 medtech pipeline frameworks; all text is an original paraphrase.
Defaults
| Parameter | Default Value | Rationale |
|---|---|---|
| asset_scope | all disclosed devices | Full-pipeline enumeration first |
| stage_lens | feasibility + pivotal | Design-iteration stages, not drug-phase labels |
| reimbursement_aware | true | Value framed against coverage paths, not raw approval |
| post_market_scan | true | Obligations and surveillance state surfaced |
| value_frame | risk-adjusted | Modeled value = unadjusted peak x POS, both shown |
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 asset queries.
Triggers
- "Analyze [ticker]'s device pipeline."
- "What is in [ticker]'s feasibility and pivotal portfolio?"
- "Where is each of [ticker]'s devices in its design cycle?"
- "Which of [ticker]'s programs are approaching submission?"
- "What RWE studies support [ticker]'s devices?"
- "What post-market obligations does [ticker] carry?"
- "Risk-adjust [ticker]'s device pipeline."
- "What is the next catalyst for each of [ticker]'s devices?"
- "How does [ticker]'s device pipeline compare to peers?"
- "Which device classifications (PMA/De Novo/510(k)) map to [ticker]'s pipeline?"
- "Map [ticker]'s devices by clinical stage and indication."
- "What does [ticker]'s pipeline say about its reimbursement path?"
Production Grounding
- Device stage ladder: feasibility (first-in-human, small N) → pivotal (registrational) → submission (PMA / De Novo / 510(k)) → post-market. Devices iterate through design versions; design freezes and iteration cycles are the pipeline milestones, not drug-style phases.
- Pivotal design varies by classification: PMA demands the highest evidence bar, De Novo novel classification, 510(k) equivalence — the pipeline's value path depends on the expected track.
- RWE studies (registries, claims analyses) increasingly support coverage and label expansion; treat them as pipeline assets with their own timelines.
- Post-market obligations (surveillance studies, MDR reporting) shape long-term liability and the re-approval path.
- Reimbursement-aware framing: pipeline value assumes a coverage path; an asset without one is discounted.
- Grounding detail lives in
references/knowledge-frameworks.md.
Data Source Priority
get_company_devices/search_universe_devices— asset inventory from the med universe.search_clinical_trials/get_clinical_trial— study stage, design type, status, enrollment.get_device_decision— decision history and upcoming decisions per device.- Knowledge layer:
search_knowledge_entriesfor framework grounding.
Methodology
Retrieval Scope
structured_only
Retrieval Strategy
- Pull asset inventory (
get_company_devices), cross-check the universe (search_universe_devices). - Enrich per asset with study records (
search_clinical_trials) — stage, design type, status-diff. - Pull decision history and upcoming dates (
get_device_decision). - Flag post-market obligations and RWE study presence per asset.
- Size each asset (peak x POS); ground in knowledge entries.
Temporal Scope
See frontmatter temporal_scope block. Device development and post-market windows span years; history may reach back 8-12 quarters.
Tool Allowlist
See frontmatter allowed_tools.
Protocol
- Asset enumeration
- Stage and design-cycle mapping
- Decision-track alignment
- Post-market and RWE overlay
- Risk-adjusted synthesis
Modes
- Phase scan (default): all devices by stage with next catalyst and expected track.
- Design cycle: design-iteration state, freezes, and submission readiness.
- Post-market: obligations, surveillance state, and RWE support.
Tool Fallbacks
| Failure | Fallback |
|---|---|
| get_company_devices empty | search_universe_devices by company or indication; annotate coverage_gap |
| No trial rows | Mark stage undisclosed; do not guess pivotal vs feasibility |
| No decision history | Flag the submission track unknown; state both possibilities |
| Knowledge tools empty | Proceed with structured data only |
Output File
{ticker}/{YYYY-MM-DD_HHMM}_pipeline-devices_{affix}.md
Output Structure
- Executive Summary — pipeline stance in 2-3 sentences
- Asset Table — stage, design type, expected track, next catalyst
- Design-Cycle Read — iteration state, freezes, submission readiness
- Post-Market & RWE — obligations, surveillance, registries
- Risk-Adjusted Sizing — peak x POS with reimbursement framing
- Coverage Gaps — missing records, undisclosed stage, degraded modes
Error Handling
| Error | Fallback |
|---|---|
| Stage unknown | Mark "undisclosed"; do not guess |
| Classification ambiguous | State the evidence-bar difference across tracks |
| No catalysts found | Say so explicitly; note the pipeline may be early-stage |
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.mdcontracts/output-frontmatter-schema.mdcontracts/memory-load.mdcontracts/snapshot-synthesis.mdcontracts/preflight.mdreferences/knowledge-frameworks.md
Files (agentii-investment-intelligence)
-
references
-
knowledge-frameworks.md 4.6 KB
# Pipeline Devices — Knowledge Frameworks Static grounding for `pipeline-devices` (spec 055). Runtime records are retrieved via the knowledge tools and cited with /v/ URLs; this file carries the device stage ladder, design-iteration discipline, RWE ladder, post-market obligations, and failure modes. Shared regulatory scaffolding (scrutiny axes) lives in `../../fda-catalyst-analysis/references/knowledge-frameworks.md`. ## Device Stage Ladder (iteration, not phases) - **Feasibility**: first-in-human, small N, safety and signal — the design is not yet frozen. - **Pivotal**: registrational study sized to the evidence bar of the expected track: PMA (highest), De Novo (novel classification), 510(k) (equivalence — often no pivotal at all). - **Submission / decision**: PMA approval, De Novo grant, or 510(k) clearance; the track determines the size of the binary event. - **Post-market**: surveillance studies, MDR reporting, next-generation design work — the pipeline does not end at approval. Devices iterate: version freezes, design changes, and equivalence testing between generations are the milestones. A device "pipeline" is a sequence of design cycles, not a fixed phase ladder. ## Design-Iteration Discipline - Track the current design version per asset and whether it is frozen (a freeze is the submission-readiness signal). - Design changes mid-pivotal reset evidence: flag any asset that changed design after study start. - Next-generation programs: the v2 asset cannibalizes the v1 installed base — model them together, not separately. ## RWE Ladder - **Registries**: longitudinal product-outcome data, often conditionally required post-approval. - **Claims analyses**: utilization and outcome signals at scale, supporting label expansion and coverage. - **Post-approval studies**: FDA-required commitments (conditions of approval) with their own timelines. - RWE is a pipeline asset: it extends labels, supports coverage, and feeds the next design cycle. ## Post-Market Obligations - PMAs carry conditions of approval and surveillance requirements; missing them risks recall-class escalation. - MDR trends are early-warning data: a rising adverse-event series precedes formal action. - Installed-base economics: the obligation set scales with the base — utilization data settles whether the base is healthy. ## POS / Scenario Discipline (cross-cutting) Unadjusted peak x POS = the modeled number; both terms shown; POS changes logged with reasons. Reimbursement is a probability input: an asset without a plausible coverage path gets a discounted POS. Bull/base/bear with named-driver grids (track outcome, coverage timing, adoption rate); explicit abstention where unquantifiable. ## Commercial Context (P1 launch board, applied forward) Consensus sales ÷ ASP ÷ procedure ramp → required procedure volume → linear path vs at least two named same-category adoption curves. ASP carries label-expansion annotations: each expansion re-prices the opportunity. Installed base, placements, procedures, and utilization are the forward vocabulary for every pivotal asset. ## Failure Modes - **Applying drug-phase labels to devices**: feasibility/pivotal stages are iteration points, not fixed phases; a "Phase II device" mislabels the evidence bar. - **Ignoring the design-freeze signal**: submission readiness is the freeze, not the enrollment count. - **Sizing without the reimbursement gate**: approval-track value assumed, coverage path absent. - **Ignoring post-market obligations**: the liability tail is part of pipeline value. - **v1/v2 double-counting**: next-generation programs modeled independently of the base they cannibalize. ## Structured Data Surfaces - `get_company_devices` / `search_universe_devices` — device inventory and owner joins. - `search_clinical_trials` / `get_clinical_trial` — study stage, design type, status, enrollment. - `get_device_decision` — decision history and upcoming decisions per device. ## Cross-Cutting Habits - **Buy-side lens**: track where investor attention sits; the client-question pattern — answer the most common question directly (e.g. "has the design frozen, or is another iteration coming?"); per-asset bull/bear pivot conditions. - **Living-thesis loop**: estimates move first, ratings last; append exhibits to the prior note, never rewrite; design-version history persists across updates. - **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_knowledge_entries` and cite with /v/ URLs. -
modes.md 430 B
# pipeline-devices — Analyst Mode Definitions Derived from the skill's ## Modes section (spec 046 M1). ### Mode: phase-scan **Objective**: All devices by stage with next catalyst and expected regulatory track. ### Mode: design-cycle **Objective**: Design-iteration state, version freezes, and submission readiness. ### Mode: post-market **Objective**: Surveillance obligations, recall posture, and RWE support per asset.
-
-
SKILL.md 6.2 KB
--- name: pipeline-devices description: "Device pipeline analysis: feasibility and pivotal study stages, design-iteration cycles, RWE studies, and post-market obligations, with reimbursement-aware value framing and decision-track awareness across the med universe." sectors: [med.medicines_biotech, med.medical_devices] multi_ticker_semantics: single_target temporal_scope: default_quarters: 8 max_quarters: 20 description: "Long-horizon pipeline window default 8 quarters; up to 20 for multi-year device development and post-market programs." allowed_tools: - get_company_devices - search_universe_devices - search_clinical_trials - get_clinical_trial - get_device_decision - search_companies - get_company_profile - search_knowledge_entries retrieval_scope: structured_only min_tool_diversity: 3 parameter_free: false --- > Methodology inspired by publicly taught medtech pipeline frameworks; all text is an original paraphrase. ## Defaults | Parameter | Default Value | Rationale | |-----------|---------------|-----------| | asset_scope | all disclosed devices | Full-pipeline enumeration first | | stage_lens | feasibility + pivotal | Design-iteration stages, not drug-phase labels | | reimbursement_aware | true | Value framed against coverage paths, not raw approval | | post_market_scan | true | Obligations and surveillance state surfaced | | value_frame | risk-adjusted | Modeled value = unadjusted peak x POS, both shown | ## 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 asset queries. ## Triggers - "Analyze [ticker]'s device pipeline." - "What is in [ticker]'s feasibility and pivotal portfolio?" - "Where is each of [ticker]'s devices in its design cycle?" - "Which of [ticker]'s programs are approaching submission?" - "What RWE studies support [ticker]'s devices?" - "What post-market obligations does [ticker] carry?" - "Risk-adjust [ticker]'s device pipeline." - "What is the next catalyst for each of [ticker]'s devices?" - "How does [ticker]'s device pipeline compare to peers?" - "Which device classifications (PMA/De Novo/510(k)) map to [ticker]'s pipeline?" - "Map [ticker]'s devices by clinical stage and indication." - "What does [ticker]'s pipeline say about its reimbursement path?" ## Production Grounding - Device stage ladder: feasibility (first-in-human, small N) → pivotal (registrational) → submission (PMA / De Novo / 510(k)) → post-market. Devices iterate through design versions; design freezes and iteration cycles are the pipeline milestones, not drug-style phases. - Pivotal design varies by classification: PMA demands the highest evidence bar, De Novo novel classification, 510(k) equivalence — the pipeline's value path depends on the expected track. - RWE studies (registries, claims analyses) increasingly support coverage and label expansion; treat them as pipeline assets with their own timelines. - Post-market obligations (surveillance studies, MDR reporting) shape long-term liability and the re-approval path. - Reimbursement-aware framing: pipeline value assumes a coverage path; an asset without one is discounted. - Grounding detail lives in `references/knowledge-frameworks.md`. ## Data Source Priority 1. `get_company_devices` / `search_universe_devices` — asset inventory from the med universe. 2. `search_clinical_trials` / `get_clinical_trial` — study stage, design type, status, enrollment. 3. `get_device_decision` — decision history and upcoming decisions per device. 4. Knowledge layer: `search_knowledge_entries` for framework grounding. ## Methodology ### Retrieval Scope structured_only ### Retrieval Strategy 1. Pull asset inventory (`get_company_devices`), cross-check the universe (`search_universe_devices`). 2. Enrich per asset with study records (`search_clinical_trials`) — stage, design type, status-diff. 3. Pull decision history and upcoming dates (`get_device_decision`). 4. Flag post-market obligations and RWE study presence per asset. 5. Size each asset (peak x POS); ground in knowledge entries. ### Temporal Scope See frontmatter temporal_scope block. Device development and post-market windows span years; history may reach back 8-12 quarters. ### Tool Allowlist See frontmatter allowed_tools. ### Protocol 1. Asset enumeration 2. Stage and design-cycle mapping 3. Decision-track alignment 4. Post-market and RWE overlay 5. Risk-adjusted synthesis ## Modes - **Phase scan** (default): all devices by stage with next catalyst and expected track. - **Design cycle**: design-iteration state, freezes, and submission readiness. - **Post-market**: obligations, surveillance state, and RWE support. ## Tool Fallbacks | Failure | Fallback | |---------|----------| | get_company_devices empty | `search_universe_devices` by company or indication; annotate coverage_gap | | No trial rows | Mark stage undisclosed; do not guess pivotal vs feasibility | | No decision history | Flag the submission track unknown; state both possibilities | | Knowledge tools empty | Proceed with structured data only | ## Output File `{ticker}/{YYYY-MM-DD_HHMM}_pipeline-devices_{affix}.md` ## Output Structure 1. **Executive Summary** — pipeline stance in 2-3 sentences 2. **Asset Table** — stage, design type, expected track, next catalyst 3. **Design-Cycle Read** — iteration state, freezes, submission readiness 4. **Post-Market & RWE** — obligations, surveillance, registries 5. **Risk-Adjusted Sizing** — peak x POS with reimbursement framing 6. **Coverage Gaps** — missing records, undisclosed stage, degraded modes ## Error Handling | Error | Fallback | |-------|----------| | Stage unknown | Mark "undisclosed"; do not guess | | Classification ambiguous | State the evidence-bar difference across tracks | | No catalysts found | Say so explicitly; note the pipeline may be early-stage | ## 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.
Reviews (0)
No reviews yet.
No comments yet.