← Plugin catalog
Scientific Research

Biosimulant

BOLAJI DEMILADE ODETARA v1.1.2

Run and revisit experiments

Create a free account to save this plugin.

From the developer

Declared capabilities

  • Start or continue an investigation
  • Build or adapt a model
  • Run or repeat an experiment

Declared limitations

  • General biology explanation without a request for sources, stored work or simulation; answer directly without calling Biosimulant.
  • A request for medical diagnosis or personalized treatment; Biosimulant is a research tool and must not be used to diagnose or prescribe.
  • An unrelated software request using the word simulation; a finance simulation is outside Biosimulant life sciences research workflows.

Not specified in the available declarations: pricing & account requirements.

Onboarding example

Pick up my protein-binding study. What have we tried, and what is still open?
Sources & dates

Developer declarations; not independently tested. Listing last checked Nov 17, 2026. Package observed Nov 16, 2026.

View package source →

Description

From the marketplace listing

Start a life sciences investigation in your AI assistant. Find evidence, work with data and models, and run computational experiments with your approval. Biosimulant keeps the setup, results, and research notes together in Studio so you can check what happened, rerun it, or pick up where you left off.

Language: English · Automatically detected from descriptions.

What changed

· 3 observations

Capabilities & instructions

Full description changed from “Research life sciences evidence, build private models and labs, run computational experiments, and inspect results.” to “Start a life sciences investigation in your AI assistant. Find evidence, work with data and models, and run computational experiments with your approval....”....

View comparison →

Technical updates · 1

Package or technical metadata updated

View technical comparison →

Files & skills

File archives

Plugin package62 files · 161 KBBrowse files →
Skill instructions
biosimulant10.3 KB

View saved version →

---
name: biosimulant
description: Use optional life sciences research workflow guidance with Biosimulant's authenticated MCP tools for Hub discovery, evidence, immutable workspaces, model authoring, compatibility, composition, managed runs, Passports, and publication.
metadata:
  version: "2026.10.16"
---

# Biosimulant

Labs are Biosimulant’s top-level resource. When users request a model, use the lab workflow. A lab contains executable model components described by `model.yaml`, coordinated by `lab.yaml`.

Biosimulant MCP is the product interface: it authenticates, authorizes, stores
immutable work, validates changes, executes approved compute, retrieves
artifacts, issues Passports, and publishes. This skill adds optional scientific
workflow guidance. It never adds permissions or capabilities to MCP.

Inspect the connected server's live tool schemas before acting. Do not infer
that MCP is unavailable because it has no resources/templates or because the
local `biosim` command is absent. If a required tool or scope is genuinely
missing, complete the supported portion and report the exact blocker.

For uploads, public dataset imports, spreadsheet inspection, or missing input
files, read [Files and datasets](references/files-and-datasets.md). Use original
bytes or source URLs and verified retained file references; never retype patient
data. Check the live schemas before assuming these tools are available.

## User-facing language

Describe Biosimulant as a life sciences research platform. Use “life sciences research,” “scientific evidence,” and “computational experiments” for general product copy. Retain precise scientific terms, including biological validation, physiology, and enzyme kinetics, when they describe the actual model, evidence, or limitations. This positioning does not expand supported workflows or establish scientific or clinical validity.

Speak to the user in plain English, including progress updates. Lead with what was found, changed, or completed and what it means for their goal. Describe actions such as searching published models or checking a private lab; do not narrate MCP method names such as hub_search or workspace_get. Omit internal IDs, raw JSON, status enums, request IDs, and checksums from ordinary replies unless the user requests technical detail, troubleshooting needs them, or an exact approval requires them. Preserve these values internally for tool calls, provenance, verification, and approval binding. Use readable names and source links where available. Explain material warnings, failed checks, missing evidence, uncertainty, and next steps in everyday language. Successful execution does not prove scientific validity; a draft is not ready to simulate just because it was created. Explain necessary scientific terms, preserve quantities and units, and never simplify away qualifications or approval requirements.

For example, say “Your private lab was created successfully. It is empty, so no simulation has run yet.” Say “I found three published labs” instead of “hub_search returned three results.” These examples describe outcomes only when the tool results confirm them.

## Workflow guidance

Read only the reference needed for the request:

- Hub discovery, durable runs, artifacts, and recovery: [references/managed-runs.md](references/managed-runs.md)
- Curated life sciences evidence: [references/biology-research.md](references/biology-research.md)
- Author model components inside lab workspaces: [references/model-build.md](references/model-build.md)
- Model composition and wiring: [references/composition.md](references/composition.md)
- Model compatibility profiles and local validation: [references/model-compatibility.md](references/model-compatibility.md)
- Passport review and publication: [references/qualification-publication.md](references/qualification-publication.md)
- SBML, CellML, ONNX, or custom Python: read the matching file under [references/runtimes](references/runtimes)
- MCP setup, MCP-v

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 13 — file references are metadata, not package contents.

build-or-adapt-a-model1.61 KB

View saved version →

---
name: build-or-adapt-a-model
description: Find a published model to reuse, adapt a model in a private lab, or design a model from evidence. Use when the user wants to choose, build, or revise an executable model or plan its tests.
---

# Build or adapt a model

Inspect the connected server's available tools and schemas. Explain model choices and approval requests in plain English, with the relevant scientific detail.

1. Clarify the scientific question, available data, and what the model needs to predict or explain. Check the user's existing lab before making a new one. When reusing a published model, inspect the exact release, inputs, outputs, units, assumptions, runtime, license, and attribution. Explain what can be reused and what needs to change.
2. For implementation, preserve source references and executable interfaces. Work in the correct private lab or copy, and preview the exact edits through the connected server. Apply them only under the current permission and approval rules. Test the behavior the user needs with real or clearly labeled example inputs. Report what was saved and which tests actually ran.
3. For a formal design request, use [Define what the model must do](references/requirements/workflow.md) to capture requirements and tests that could demonstrate them. Use [Plan how to build and test the model](references/technical-plan/workflow.md) when the requirements are approved. Keep templates and validation guidance with these steps. They are optional for ordinary modeling work.

Example: “Find a published model I can adapt for my question. Explain what it assumes and what I'd need to change.”

Referenced files: 28 — file references are metadata, not package contents.

create-mrs7.38 KB

View saved version →

---
name: create-mrs
description: Create or revise a Model Requirements Specification (MRS) for a biological or computational model from scientific briefs, assay/data evidence, and intended-use decisions. Use when defining what the model must do and what evidence will establish acceptance; do not use for implementation design or an MTS.
metadata:
  version: "2026.10.16"
---

# Create MRS

Create a controlled requirements document whose source of truth is the scientific purpose, intended use, supported domain, required behavior, validation evidence, and acceptance criteria. Do not let a preferred algorithm, runtime, or existing implementation redefine those requirements.

## Ground the draft

1. Read [references/suite-lifecycle.md](references/suite-lifecycle.md) for lifecycle, freeze, acceptance, and change-control rules.
2. Inspect the project for a biological brief, assay/data specification, existing MRS, validation protocol, relevant code, datasets/manifests, and decision records before asking questions.
3. Classify the model job. Read only the matching example reference(s):
   - predictive or ML: [references/examples/predictive-ml.md](references/examples/predictive-ml.md)
   - mechanistic: [references/examples/mechanistic.md](references/examples/mechanistic.md)
   - generative: [references/examples/generative.md](references/examples/generative.md)
   - optimization: [references/examples/optimization.md](references/examples/optimization.md)
   - simulation or digital twin: [references/examples/digital-twin.md](references/examples/digital-twin.md)
   - statistical estimation: [references/examples/statistical-estimation.md](references/examples/statistical-estimation.md)
   Read every applicable example for a hybrid model, but treat its numbers and scientific claims as illustrative rather than reusable facts.
4. Read [references/biosimulant-runtime.md](references/biosimulant-runtime.md) only when Biosimulant capability, delivery, or fit affects a requirement. An MRS may require a portable artifact or execution property, but it must not prescribe Biosimulant without an intended-use reason.

Prefer evidence over questions. Ask only about consequential scientific or product decisions that the available material cannot establish. Never invent owners, thresholds, sample sizes, assay behavior, citations, or approval state. Record unresolved facts as explicit open items with an owner and impact.

If the available study design cannot support the requested identification, validation, forecast, ranking, or intervention decision, stop that requested lifecycle at a read-only requirements/gap analysis. Do not create a project, workspace, revision, or prepared change merely to persist the refusal unless the user explicitly requests a durable gap-analysis record. Do not silently substitute a runnable exploratory model or weaker acceptance claim. You may propose a reduced intended use or minimum experimental design, but persistence or implementation begins only after the user explicitly accepts that changed objective.

## Create or revise

For a new MRS, run:

```bash
python3 <skill-dir>/scripts/start_mrs.py "<Model or Project Name>" --root <project-root>
```

Resolve `<skill-dir>` to the folder containing this `SKILL.md`. The command copies the protected template to `specifications/<model-slug>/mrs.md` and refuses to overwrite an existing file. The master asset is immutable; edit only the working copy.

For a revision, edit the existing MRS instead of starting from the template. Preserve its identifier lineage, increment the version according to project policy, update `Last revised` and revision history, assess approval impact, and retain decisions or superseded content needed for auditability. Changes to intended use, endpoint, domain, ground truth, required inputs, output interpretation, decision thresholds, or acceptance criteria require reapproval.

When working through the Biosimulant Agent Gateway, draft and validate the MRS with this s

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 13 — file references are metadata, not package contents.

create-mts9.67 KB

View saved version →

---
name: create-mts
description: Create or revise a Modeling Technical Specification (MTS) that implements an approved Model Requirements Specification for a biological or computational model. Use when defining architecture, methods, interfaces, verification, reproducibility, delivery, Biosimulant fit, and operations; do not use to invent or weaken MRS acceptance requirements.
metadata:
  version: "2026.10.16"
---

# Create MTS

Translate an approved MRS into a traceable implementation contract. The MTS explains how the requirements will be satisfied; it does not replace, reinterpret, or weaken them.

## Gate and ground the work

1. Locate the MRS and verify its identifier, version, `Approved` status, approvals, and mandatory requirements. A full MTS requires an approved, versioned MRS. If the MRS is Draft, In review, missing, or materially inconsistent, produce only a gap analysis or clearly non-authoritative skeleton and stop before calling it a completed MTS.
2. Read [references/suite-lifecycle.md](references/suite-lifecycle.md) and [references/mts-suite-guidance.md](references/mts-suite-guidance.md).
3. Inspect relevant code, manifests, environments, model artifacts, data/partition manifests, tests, operational constraints, and native scientific runtimes before choosing the architecture.
4. Classify every component by model job. Read only the matching example reference(s):
   - predictive or ML: [references/examples/predictive-ml.md](references/examples/predictive-ml.md)
   - mechanistic: [references/examples/mechanistic.md](references/examples/mechanistic.md)
   - generative: [references/examples/generative.md](references/examples/generative.md)
   - optimization: [references/examples/optimization.md](references/examples/optimization.md)
   - simulation or digital twin: [references/examples/digital-twin.md](references/examples/digital-twin.md)
   - statistical estimation: [references/examples/statistical-estimation.md](references/examples/statistical-estimation.md)
   Read every applicable example for a hybrid model, without carrying over illustrative thresholds or claims.
5. Read [references/biosimulant-runtime.md](references/biosimulant-runtime.md) before making a Biosimulant fit decision or specifying a Biosimulant implementation. When the referenced repository is available, inspect it and treat the current code as authoritative over the snapshot.

Prefer evidence over questions. Ask only about design decisions, operational constraints, or ownership that cannot be derived from the approved MRS and project artifacts. Never invent scientific evidence, approvals, parity tolerances, resource budgets, or validation results.

## Create or revise

For a new MTS, run:

```bash
python3 <skill-dir>/scripts/start_mts.py "<Model or Project Name>" --root <project-root>
```

Resolve `<skill-dir>` to the folder containing this `SKILL.md`. The command copies the protected template to `specifications/<model-slug>/mts.md` and refuses to overwrite an existing file. Edit only the working copy.

For a revision, preserve the MTS identifier lineage, update version/date/revision history, record the decision and alternatives, assess MRS impact and revalidation impact, and keep prior evidence traceable. If the intended use or any MRS-controlled requirement changes, return the issue to the MRS owner instead of changing it in the MTS.

When working through the Biosimulant Agent Gateway, draft and validate the MTS with this skill, then submit its contents through `workspace_technical_spec_set_prepare`. The Gateway commit is an immutable storage revision, not approval of the MTS or satisfaction of the MRS. Follow the preview's `requires_confirmation` decision and retain its exact diff and digest before `workspace_technical_spec_set_apply`, and preserve the document's own review state and traceability.

## Build the traceable design

- Include every mandatory MRS identifier in the traceability matrix. Map it to a component or design decision, test 

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 14 — file references are metadata, not package contents.

inspect-and-compare-results1.45 KB

View saved version →

---
name: inspect-and-compare-results
description: Read and compare saved Biosimulant results, including values, plots, and files. Use when the user asks what a completed experiment produced or how two runs differ.
---

# Inspect and compare results

Check the connected server's available read tools and schemas. Lead with what the saved results show in plain English, then give the relevant quantities, units, and limits.

1. Find the exact completed run or runs and retrieve their settings and outcomes. Read saved artifacts, not just filenames or job status. Use verified full content or a server-verified bounded preview when supported. Preserve units and labels, and say when a preview is sampled or a requested value is unavailable.
2. Compare inputs, revisions, settings, and output values side by side. Compare like quantities only. For Boltz-2, distinguish the predicted structure, model confidence, and affinity or binding scores, using the names and units in the saved files. Treat scores as predictions and state any limitation that affects the question.
3. Link to the saved results and files in Studio when the server provides those links. Use the available execution record when relevant. Report missing or failed outputs directly and never invent values, fabricate links, or rerun to fill a gap without being asked.

Example: “Compare my two completed Boltz-2 runs. What changed in the inputs, what do the saved scores show, and where can I open the structures?”

Referenced files: 1 — file references are metadata, not package contents.

run-or-repeat-an-experiment1.5 KB

View saved version →

---
name: run-or-repeat-an-experiment
description: Prepare or repeat a Biosimulant computational experiment using a known lab, inputs, and settings. Use for new runs, reruns, or comparisons that require fresh compute and explicit approval.
---

# Run or repeat an experiment

Check the connected server's tool schemas and current session policy. Explain the setup and approval in plain English, using exact quantities and units.

1. Resolve the exact lab and revision. For a repeat, retrieve the original run and use its saved inputs, parameters, and bounds. Show any requested changes or missing files. If the same setup cannot be recreated, explain the difference before preparing a substitute.
2. Prepare the plan through the connected service. Show the inputs, settings, compute limits, cost or pending estimate, expiry, and blockers. Follow the server's current approval rules and show its Studio review link when provided. If asked to prepare or wait for approval, stop at the plan. A chat response, plan ID, or hash by itself does not resolve a required Studio approval. A changed or expired plan needs a fresh review.
3. When authorized to execute, use the exact approved plan and check the resulting run through its terminal outcome. Report the actual completion or failure and link to saved results and files when the server provides them. An inspection request never needs a fresh run.

Example: “Prepare a rerun of my saved Boltz-2 experiment. Show me the inputs, settings, and estimated cost before I approve it.”

Referenced files: 1 — file references are metadata, not package contents.

start-or-continue-investigation1.62 KB

View saved version →

---
name: start-or-continue-investigation
description: Find relevant life sciences evidence or pick up a Biosimulant investigation using saved notes, labs, and runs. Use when the user wants to start, resume, or hand off research in Studio.
---

# Start or continue an investigation

1. For existing work, search the signed-in account with `project_search` or `session_list` when available. Use the linked lab or session to narrow ambiguous names. Read the matching session with `session_resume` and saved notes with the available note tools; use the linked lab and runs to verify what happened.
2. Say what has been tried, what evidence or results are saved, and what remains open. Link to the saved work when the server supplies a stable link. Opening or summarizing an investigation does not require creating another session, changing a lab, or starting a run.
3. For new research, find relevant evidence through the connected service and identify the source, what it supports, and any gap that affects the question. Create a Studio session or save a note only when requested. Respect the session's lab, ownership, and current approval settings. Keep research notes separate from execution approvals.

Use the [Biosimulant workflow guide](workflow-guide.md) when deeper guidance is needed, including session approvals, lab edits, file transfer, hosting, and publication. If a capability is missing, report what you could verify and offer a path through Studio when one is available.

Use readable names and plain English when telling the user what you found.

Example: “Pick up my protein-binding study. What have we tried, and what's still open?”

Referenced files: 23 — file references are metadata, not package contents.

Release notes

Use the Biosimulant brand mark as a standalone PNG for the listing and composer. Includes the four workflow skills and their model planning templates.

Declared in the saved package. Remote tools may change independently.

Package details

Publisher declarations from the archived package. These are separate from our research and the live service's terms.

Package author
BOLAJI DEMILADE ODETARA
Review scenarios
5 positive · 3 negativeScenario counts, not test results.

Declared capabilities

  • Start or continue an investigation
  • Build or adapt a model
  • Run or repeat an experiment
  • Inspect and compare results

Package observed Nov 16, 2026.

Technical details
First seen
Nov 5, 2026 · 18:00 UTC
Last seen
Nov 17, 2026 · 00:00 UTC
Latest observed change
Nov 6, 2026 · 12:12 UTC
Collection status
Collected

plugin_asdk_app_6aaf5b60db80819199cdaf5299792763

Download plugin data (JSON)

Plugin details: served from cache. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.