Pipeline Devices logo

Pipeline Devices

Community
agentii-ai
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.

Overview

Publisheragentii-ai
Repositoryagentii-investment-intelligence
Skill namepipeline-devices
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 Pipeline Devices 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/pipeline-devices
  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/pipeline-devices .claude/skills/pipeline-devices
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pipeline Devices 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 Pipeline Devices 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 Pipeline Devices 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 medtech pipeline frameworks; all text is an original paraphrase.

Defaults

ParameterDefault ValueRationale
asset_scopeall disclosed devicesFull-pipeline enumeration first
stage_lensfeasibility + pivotalDesign-iteration stages, not drug-phase labels
reimbursement_awaretrueValue framed against coverage paths, not raw approval
post_market_scantrueObligations and surveillance state surfaced
value_framerisk-adjustedModeled value = unadjusted peak x POS, both shown

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 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

FailureFallback
get_company_devices emptysearch_universe_devices by company or indication; annotate coverage_gap
No trial rowsMark stage undisclosed; do not guess pivotal vs feasibility
No decision historyFlag the submission track unknown; state both possibilities
Knowledge tools emptyProceed 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

ErrorFallback
Stage unknownMark "undisclosed"; do not guess
Classification ambiguousState the evidence-bar difference across tracks
No catalysts foundSay 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

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 Pipeline Devices AI skill do?

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.

Why use Pipeline Devices on TypingMind?

Because you install it once and use it with any model. Pipeline Devices 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 Pipeline Devices 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/pipeline-devices. 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 Pipeline Devices?

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 Pipeline Devices?

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

Is the Pipeline Devices 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 👇