===============
LIBRARY RULES
===============
From library maintainers:
- Use `import isabl_cli as ii` convention
- Filter queries with Django-style syntax: status='SUCCEEDED', application__name='MUTECT'
- Applications inherit from AbstractApplication
- Data model hierarchy: Individual -> Sample -> Experiment -> Analysis
- Analysis statuses: CREATED -> STAGED -> SUBMITTED -> STARTED -> SUCCEEDED / FAILED
- Use system_id for experiments/individuals/samples, pk for analyses/projects/applications

### Install Isabl Plugin

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/README.md

Use these commands to install the Isabl plugin from the marketplace.

```bash
/plugin marketplace add juanesarango/isabl-mcp
```

```bash
/plugin install isabl
```

--------------------------------

### Run Isabl MCP Server Directly or Install Globally

Source: https://github.com/juanesarango/isabl-mcp/blob/main/README.md

These commands allow you to run the Isabl MCP server directly without installation using 'uvx', or install it globally using pip for persistent access.

```bash
uvx isabl-mcp        # run directly, no install needed
```

```bash
pip install isabl-mcp # or install globally
```

--------------------------------

### Example Isabl CLI Command

Source: https://github.com/juanesarango/isabl-mcp/blob/main/README.md

An example of using the Isabl CLI to check the status of RNA apps within a specific project. This command is part of the broader Isabl ecosystem for managing bioinformatics workflows.

```bash
/isabl:isabl-monitor-analyses check the status of RNA apps in project 455
```

--------------------------------

### Development Commands for MCP Server

Source: https://github.com/juanesarango/isabl-mcp/blob/main/README.md

Commands for setting up the development environment, running tests, linting, and starting the MCP server locally. Ensure you are in the 'mcp-server' directory before executing.

```bash
cd mcp-server
uv sync --dev
```

```bash
uv run pytest
```

```bash
uv run ruff check isabl_mcp/  # lint
```

```bash
uv run mcp dev isabl_mcp/server.py  # test with MCP Inspector
```

```bash
uv run isabl-mcp           # start server locally
```

--------------------------------

### Build and Print Isabl Experiment Queries

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/isabl-query-data/SKILL.md

Constructs a query to find experiments filtered by project and sample category, then iterates through the results to print system IDs and sample identifiers. Ensure the `isabl_cli` library is installed and configured.

```python
import isabl_cli as ii

experiments = ii.get_experiments(
    projects=102,
    sample__category="TUMOR"
)
for exp in experiments:
    print(f"{exp.system_id}: {exp.sample.identifier}")
```

--------------------------------

### Get FASTQ Files

Source: https://github.com/juanesarango/isabl-mcp/blob/main/knowledge/output/site/api-client-resource-utilities/resource-crud-retrieval/README.md

Returns the paired FASTQ file lists (R1 and R2) for an experiment. Validates pairing and raises an error if counts do not match.

```APIDOC
## GET /api/experiments/{experiment_id}/fastq

### Description
Retrieves the paired FASTQ R1 and R2 file lists for a given experiment.

### Method
GET

### Endpoint
/api/experiments/{experiment_id}/fastq

### Parameters
#### Path Parameters
- **experiment_id** (string) - Required - The ID of the experiment.

### Response
#### Success Response (200)
- **r1_files** (array) - A list of R1 FASTQ file paths.
- **r2_files** (array) - A list of R2 FASTQ file paths.

#### Response Example
```json
{
  "r1_files": ["path/to/file1_R1.fastq.gz"],
  "r2_files": ["path/to/file1_R2.fastq.gz"]
}
```
```

--------------------------------

### Get Experiment or Analysis Instance by ID

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/isabl-query-data/SKILL.md

Instantiate an Experiment object using its system ID or an Analysis object using its primary key. Requires 'isabl_cli'.

```python
import isabl_cli as ii

# By system_id
exp = ii.Experiment("SAMPLE_001")

# By primary key
analysis = ii.Analysis(12345)
```

--------------------------------

### GET /projects/{pk}/drive-directory

Source: https://github.com/juanesarango/isabl-mcp/blob/main/knowledge/output/site/api-models-serializers-endpoints/views-endpoints/README.md

Retrieves or creates a Google Drive directory for a project.

```APIDOC
## GET /projects/{pk}/drive-directory

### Description
Maps a project to a Google Drive folder, creating the folder structure if it does not exist.

### Method
GET

### Endpoint
/projects/{pk}/drive-directory

### Parameters
#### Path Parameters
- **pk** (integer) - Required - The primary key of the project.
```

--------------------------------

### GET /igv/experiment/{system_id}

Source: https://github.com/juanesarango/isabl-mcp/blob/main/knowledge/output/site/api-models-serializers-endpoints/views-endpoints/README.md

Renders an experiment in the IGV genome viewer.

```APIDOC
## GET /igv/experiment/{system_id}

### Description
Loads experiment data into the IGV HTML interface.

### Method
GET

### Parameters
#### Path Parameters
- **system_id** (string) - Required - The system identifier for the experiment.
```

--------------------------------

### Configure Isabl MCP Server in Codex

Source: https://github.com/juanesarango/isabl-mcp/blob/main/README.md

Add this TOML configuration to your ~/.codex/config.toml file to integrate the Isabl MCP server with Codex. Remember to substitute the example API URL and token with your specific credentials.

```toml
[mcp_servers.isabl]
command = "uvx"
args = ["isabl-mcp"]
env = { "ISABL_API_URL" = "https://your-isabl-instance.com/api/v1/", "ISABL_API_TOKEN" = "your-token" }
```

--------------------------------

### Get Isabl Entity Types with Python SDK

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/isabl-query-data/SKILL.md

Demonstrates the main entity types available in the Isabl SDK and their corresponding query functions. Use these to initiate data retrieval.

```python
import isabl_cli as ii

# Main entity types and their query functions
experiments = ii.get_experiments(...)      # Sequencing data
analyses = ii.get_analyses(...)            # Pipeline results
samples = ii.get_instances("samples", ...) # Tissue specimens
individuals = ii.get_instances("individuals", ...)  # Patients/subjects
applications = ii.get_instances("applications", ...)  # Pipelines
projects = ii.get_instances("projects", ...)  # Project groupings
```

--------------------------------

### GET /projects/{pk}/jira-epic

Source: https://github.com/juanesarango/isabl-mcp/blob/main/knowledge/output/site/api-models-serializers-endpoints/views-endpoints/README.md

Retrieves or creates a JIRA epic associated with a given project.

```APIDOC
## GET /projects/{pk}/jira-epic

### Description
Retrieves or creates a JIRA epic associated with a given project using the project primary key.

### Method
GET

### Endpoint
/projects/{pk}/jira-epic

### Parameters
#### Path Parameters
- **pk** (integer) - Required - The primary key of the project.
```

--------------------------------

### Get Specific or All Results from an Analysis

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/isabl-query-data/SKILL.md

Extract specific results (like a VCF file path) or all results for an application from an experiment. Uses 'isabl_cli.utils'.

```python
import isabl_cli as ii
from isabl_cli import utils

# Get specific result from an experiment
vcf_path, analysis = utils.get_result(
    experiment=experiment,
    application_key=123,
    result_key="vcf"
)
print(f"VCF: {vcf_path}")

# Get all results for an application
results = utils.get_results(
    experiment=experiment,
    application_name="variant_caller"
)
```

--------------------------------

### Initialize ISABL CLI Application

Source: https://github.com/juanesarango/isabl-mcp/blob/main/knowledge/output/site/applications-analysis-workflows/validation-preconditions/README.md

Sets up the main entry point for the ISABL command-line interface application. This function is typically called when the script is executed.

```python
def main():
    app = ISABLCLI()
    app.run()

if __name__ == "__main__":
    main()
```

--------------------------------

### Track Running Isabl Analyses

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/isabl-monitor-analyses/SKILL.md

Retrieves and displays details for analyses currently in the 'STARTED' status, ordered by start time. Shows the analysis primary key, application name, target system ID, and duration in hours.

```python
running = ii.get_analyses(
    projects=PROJECT_PK,
    status="STARTED",
    ordering="-started"
)

if running:
    print(f"\n=== RUNNING ({len(running)}) ===")
    for a in running[:20]:
        hours = (datetime.now() - a.started).total_seconds() / 3600
        target = a.targets[0].system_id if a.targets else "N/A"
        print(f"  [{a.pk}] {a.application.name}: {target} ({hours:.1f}h)")
```

--------------------------------

### GET /igv/analysis/{pk}

Source: https://github.com/juanesarango/isabl-mcp/blob/main/knowledge/output/site/api-models-serializers-endpoints/views-endpoints/README.md

Renders an analysis in the IGV genome viewer.

```APIDOC
## GET /igv/analysis/{pk}

### Description
Loads analysis data into the IGV HTML interface.

### Method
GET

### Parameters
#### Path Parameters
- **pk** (integer) - Required - The primary key of the analysis.
```

--------------------------------

### Create Individual, Samples, and Experiments via API

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/isabl-submit-data/SKILL.md

Demonstrates the step-by-step creation of biological entities (individual, samples, experiments) using the ISABL API. Each entity is created individually, providing granular control.

```python
# 1. Create individual
individual = ii.create_instance("individuals", {
    "identifier": submission_data["individual"]["identifier"],
    "species": submission_data["individual"]["species"],
    "gender": submission_data["individual"]["gender"],
    "center": submission_data["individual"]["center"],
})
print(f"Created individual: {individual.system_id}")

# 2. Create samples
samples = {}
for sample_data in submission_data["samples"]:
    sample = ii.create_instance("samples", {
        "identifier": sample_data["identifier"],
        "category": sample_data["category"],
        "disease": sample_data["disease"],
        "individual": {"pk": individual.pk},
    })
    samples[sample_data["identifier"]] = sample
    print(f"Created sample: {sample.system_id}")

# 3. Create experiments
for exp_data in submission_data["experiments"]:
    sample = samples[exp_data["sample_identifier"]]
    experiment = ii.create_instance("experiments", {
        "identifier": exp_data["identifier"],
        "sample": {"pk": sample.pk},
        "technique": exp_data["technique"],
        "platform": exp_data["platform"],
        "center": exp_data["center"],
        "raw_data": exp_data["raw_data"],
        "projects": [{"pk": PROJECT_PK}],
    })
    print(f"Created experiment: {experiment.system_id}")
```

--------------------------------

### Find Stale Analyses

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/isabl-project-report/SKILL.md

Identifies analyses that have been in 'STARTED' status for more than 7 days.

```python
from datetime import datetime, timedelta

stale_cutoff = datetime.now() - timedelta(days=7)

stale = ii.get_analyses(
    projects=PROJECT_PK,
    status="STARTED",
    modified__lt=stale_cutoff.isoformat()
)

if stale:
    print(f"Stale analyses (started > 7 days ago): {len(stale)}")
```

--------------------------------

### GET /reference/data

Source: https://github.com/juanesarango/isabl-mcp/blob/main/knowledge/output/site/cli-commands-user-tools/user-facing-commands-authentication-retrieval-management/README.md

Retrieves reference data based on assemblies or sequencing techniques.

```APIDOC
## GET /reference/data

### Description
Retrieves reference data from assemblies or sequencing techniques depending on provided arguments.

### Method
GET

### Endpoint
/reference/data

### Parameters
#### Query Parameters
- **identifier** (string) - Optional - Identifier for the reference.
- **data_id** (string) - Optional - Specific data ID.
- **resources** (list) - Optional - Resources to include.
- **model** (string) - Optional - Internal model for reference lookup.
```

--------------------------------

### Define a Complete Isabl Application

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/isabl-write-app/SKILL.md

Use the AbstractApplication base class to define metadata, CLI options, validation logic, and execution commands.

```python
from isabl_cli import AbstractApplication, options

class MyApplication(AbstractApplication):
    """
    Brief description of what this application does.
    """

    # Required metadata
    NAME = "my_application"
    VERSION = "1.0.0"

    # Optional: restrict to specific assembly/species
    ASSEMBLY = "GRCh37"  # or "GRCh38", None for any
    SPECIES = "HUMAN"    # or None for any

    # CLI configuration
    cli_help = "Run my application on experiments"
    cli_options = [options.TARGETS]  # or REFERENCES, PAIRS

    # Configurable settings (can be overridden in database)
    application_settings = {
        "tool_path": "/usr/bin/mytool",
        "threads": 4,
    }

    # Define expected results
    application_results = {
        "output_file": {
            "frontend_type": "text-file",
            "description": "Main output file",
            "verbose_name": "Output",
        }
    }

    def validate_experiments(self, targets, references):
        """
        Raise AssertionError if experiments are invalid for this app.
        Called before creating analyses.
        """
        assert len(targets) == 1, "Requires exactly one target experiment"
        assert targets[0].technique.method == "WGS", "Only WGS supported"

    def get_dependencies(self, targets, references, settings):
        """
        Return (dependency_analyses, inputs_dict) if this app needs
        results from other applications.
        """
        return [], {}

    def get_command(self, analysis, inputs, settings):
        """
        Return the shell command to execute.
        This is the core of the application.
        """
        target = analysis.targets[0]
        output_dir = analysis.storage_url

        return f"""
        {settings.tool_path} \
            --input {target.bam_files["GRCh37"]["url"]} \
            --output {output_dir}/result.txt \
            --threads {settings.threads}
        """

    def get_analysis_results(self, analysis):
        """
        Return dict of result paths after successful completion.
        Keys should match application_results.
        """
        return {
            "output_file": f"{analysis.storage_url}/result.txt"
        }
```

--------------------------------

### GET /instances/count

Source: https://github.com/juanesarango/isabl-mcp/blob/main/knowledge/output/site/cli-commands-user-tools/user-facing-commands-authentication-retrieval-management/README.md

Retrieves the number of database instances that match the provided criteria.

```APIDOC
## GET /instances/count

### Description
Returns the count of database instances matching the specified endpoint and filters.

### Method
GET

### Endpoint
/instances/count

### Parameters
#### Query Parameters
- **endpoint** (string) - Required - The target database endpoint.
- **filters** (object) - Optional - Criteria to filter the instances.
```

--------------------------------

### Define Application Settings and Results

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/isabl-write-app/SKILL.md

Configure settings that can be overridden in the database and define expected output results.

```python
from isabl_cli import AbstractApplication, options

class MyApplication(AbstractApplication):
    NAME = "my_application"
    VERSION = "1.0.0"
    cli_options = [options.TARGETS]

    # Configurable settings (can be overridden in database)
    application_settings = {
        "tool_path": "/usr/bin/mytool",
        "threads": 4,
        "memory_gb": 16,
    }

    # Define expected results
    application_results = {
        "output_file": {
            "frontend_type": "text-file",
            "description": "Main output file",
            "verbose_name": "Output",
        }
    }
```

--------------------------------

### GET /instances

Source: https://github.com/juanesarango/isabl-mcp/blob/main/knowledge/output/site/cli-usage-tooling/api-client-helpers-cli/README.md

Retrieve instances from a list API endpoint with optional identifiers and filters.

```APIDOC
## GET /instances

### Description
Fetches objects from list endpoints. Supports optional identifiers and filters. Returns a list of types.SimpleNamespace objects.

### Method
GET

### Endpoint
/instances

### Parameters
#### Query Parameters
- **identifiers** (list/str) - Optional - List of identifiers to filter by.
- **filters** (dict) - Optional - Keyword arguments for filtering results.
- **verbose** (bool) - Optional - If true, prints a count of retrieved objects.
```

--------------------------------

### Retrieve Project Information

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/isabl-project-report/SKILL.md

Fetches basic project metadata using the project primary key.

```python
import isabl_cli as ii

project = ii.get_instance("projects", PROJECT_PK)

print(f"Project: {project.title}")
print(f"Short title: {project.short_title}")
print(f"PI: {project.principal_investigator}")
print(f"Analyst: {project.analyst}")
print(f"Description: {project.description}")
```

--------------------------------

### Configure Isabl MCP Server in Cursor

Source: https://github.com/juanesarango/isabl-mcp/blob/main/README.md

Add this JSON configuration to your .cursor/mcp.json file to set up the Isabl MCP server connection in Cursor. Ensure you replace the placeholder URL and token with your actual Isabl instance details.

```json
{
  "mcpServers": {
    "isabl": {
      "command": "uvx",
      "args": ["isabl-mcp"],
      "env": {
        "ISABL_API_URL": "https://your-isabl-instance.com/api/v1/",
        "ISABL_API_TOKEN": "your-token"
      }
    }
  }
}
```

--------------------------------

### Get Individual Data Tree

Source: https://github.com/juanesarango/isabl-mcp/blob/main/knowledge/output/site/api-client-resource-utilities/resource-crud-retrieval/README.md

Fetches all related data for a single individual identified by an identifier.

```APIDOC
## GET /api/individuals/{identifier}/tree

### Description
Retrieves the complete aggregated data tree for a single individual.

### Method
GET

### Endpoint
/api/individuals/{identifier}/tree

### Parameters
#### Path Parameters
- **identifier** (string) - Required - The identifier for the individual.

### Response
#### Success Response (200)
- **tree** (object) - The aggregated data tree for the individual.

#### Response Example
```json
{
  "individual_id": "ind_123",
  "experiments": [...],
  "analyses": [...]
}
```
```

--------------------------------

### Get Analyses

Source: https://github.com/juanesarango/isabl-mcp/blob/main/knowledge/output/site/api-client-resource-utilities/resource-crud-retrieval/README.md

Fetches analysis objects from the API by either identifiers or filter keyword arguments.

```APIDOC
## GET /api/analyses

### Description
Fetches analysis objects from the API.

### Method
GET

### Endpoint
/api/analyses

### Parameters
#### Query Parameters
- **identifiers** (list) - Optional - A list of analysis identifiers.
- **filter_kwargs** (object) - Optional - Key-value pairs for filtering analyses.

### Response
#### Success Response (200)
- **analyses** (array) - A list of analysis objects.

#### Response Example
```json
[
  {
    "id": "analysis_a",
    "name": "Analysis A"
  },
  {
    "id": "analysis_b",
    "name": "Analysis B"
  }
]
```
```

--------------------------------

### Verify Application Settings

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/isabl-debug-analysis/SKILL.md

Inspects application-level settings and specific tool paths to ensure correct configuration.

```python
# Get application settings
app = ii.get_instance("applications", analysis.application.pk)
print(f"Settings: {app.settings}")

# Check specific setting
from my_apps import MyApplication
instance = MyApplication()
print(f"Tool path: {instance.settings.tool_path}")
```

--------------------------------

### Get Experiments

Source: https://github.com/juanesarango/isabl-mcp/blob/main/knowledge/output/site/api-client-resource-utilities/resource-crud-retrieval/README.md

Retrieves experiment resources by accepting optional identifiers or filter keyword arguments.

```APIDOC
## GET /api/experiments

### Description
Fetches experiment resources from the API.

### Method
GET

### Endpoint
/api/experiments

### Parameters
#### Query Parameters
- **identifiers** (list) - Optional - A list of experiment identifiers.
- **filter_kwargs** (object) - Optional - Key-value pairs for filtering experiments.

### Response
#### Success Response (200)
- **experiments** (array) - A list of experiment objects.

#### Response Example
```json
[
  {
    "id": "exp_001",
    "name": "Experiment Alpha"
  },
  {
    "id": "exp_002",
    "name": "Experiment Beta"
  }
]
```
```

--------------------------------

### Implement get_command for Isabl Application

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/isabl-write-app/SKILL.md

Defines the shell command execution logic for an application by inheriting from AbstractApplication.

```python
from isabl_cli import AbstractApplication, options

class MyApplication(AbstractApplication):
    NAME = "my_application"
    VERSION = "1.0.0"
    cli_options = [options.TARGETS]

    application_settings = {
        "tool_path": "/usr/bin/mytool",
        "threads": 4,
    }

    def get_command(self, analysis, inputs, settings):
        """
        Return the shell command to execute.
        This is the core of the application.
        """
        target = analysis.targets[0]
        output_dir = analysis.storage_url

        return f"""
        {settings.tool_path} \
            --input {target.bam_files["GRCh37"]["url"]} \
            --output {output_dir}/result.txt \
            --threads {settings.threads}
        """
```

--------------------------------

### GET /data/files

Source: https://github.com/juanesarango/isabl-mcp/blob/main/knowledge/output/site/cli-commands-user-tools/user-facing-commands-authentication-retrieval-management/README.md

Fetches file paths for raw experimental data based on filters and identifiers.

```APIDOC
## GET /data/files

### Description
Returns file paths for experiments' raw data according to provided filters, identifiers, and desired data types.

### Method
GET

### Endpoint
/data/files

### Parameters
#### Query Parameters
- **filters** (object) - Optional - Criteria to filter experiments.
- **identifiers** (list) - Optional - Specific identifiers for data retrieval.
- **verbose** (boolean) - Optional - Enables detailed output.
- **dtypes** (list) - Optional - Specific data types to fetch.
```

--------------------------------

### GET /analyses/{pk}/result-file

Source: https://github.com/juanesarango/isabl-mcp/blob/main/knowledge/output/site/api-models-serializers-endpoints/views-endpoints/README.md

Endpoints for reading, downloading, or streaming analysis result files.

```APIDOC
## GET /analyses/{pk}/result-file

### Description
Provides access to files within an analysis output directory. Supports rendering content (cat-like), downloading, or HTTP streaming.

### Method
GET

### Parameters
#### Path Parameters
- **pk** (integer) - Required - The primary key of the analysis.
```

--------------------------------

### Use Cursor Pagination for Large Datasets

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/isabl-query-data/SKILL.md

Employ cursor-based pagination for efficiently retrieving very large datasets of instances. Uses 'isabl_cli'.

```python
import isabl_cli as ii

# Use cursor pagination for very large datasets
experiments = ii.get_instances(
    "experiments",
    projects=102,
    paginator="cursor"
)
```

--------------------------------

### Get Projects

Source: https://github.com/juanesarango/isabl-mcp/blob/main/knowledge/output/site/api-client-resource-utilities/resource-crud-retrieval/README.md

Retrieves project resources from the API using optional identifiers or filter keyword arguments.

```APIDOC
## GET /api/projects

### Description
Fetches project resources from the API.

### Method
GET

### Endpoint
/api/projects

### Parameters
#### Query Parameters
- **identifiers** (list) - Optional - A list of project identifiers.
- **filter_kwargs** (object) - Optional - Key-value pairs for filtering projects.

### Response
#### Success Response (200)
- **projects** (array) - A list of project objects.

#### Response Example
```json
[
  {
    "id": "proj_xyz",
    "name": "Project XYZ"
  },
  {
    "id": "proj_abc",
    "name": "Project ABC"
  }
]
```
```

--------------------------------

### Define Scope for Analysis Monitoring

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/isabl-monitor-analyses/SKILL.md

Set up parameters like project ID, application name, and time range for monitoring analyses. Imports necessary libraries for date and time manipulation.

```python
import isabl_cli as ii
from datetime import datetime, timedelta

# Define what to monitor
PROJECT_PK = 102
APPLICATION_NAME = "MUTECT"  # or None for all
HOURS_BACK = 24  # Look at last N hours

cutoff = datetime.now() - timedelta(hours=HOURS_BACK)
```

--------------------------------

### Get Multiple Individual Data Trees

Source: https://github.com/juanesarango/isabl-mcp/blob/main/knowledge/output/site/api-client-resource-utilities/resource-crud-retrieval/README.md

Retrieves the complete aggregated data trees for multiple individuals by accepting identifiers or filters.

```APIDOC
## GET /api/individuals/trees

### Description
Retrieves the complete aggregated data trees for multiple individuals.

### Method
GET

### Endpoint
/api/individuals/trees

### Parameters
#### Query Parameters
- **identifiers** (list) - Optional - A list of individual identifiers.
- **filter_kwargs** (object) - Optional - Key-value pairs for filtering individuals.

### Response
#### Success Response (200)
- **trees** (array) - A list of aggregated data trees for the individuals.

#### Response Example
```json
[
  {
    "individual_id": "ind_123",
    "experiments": [...]
  },
  {
    "individual_id": "ind_456",
    "analyses": [...]
  }
]
```
```

--------------------------------

### Import OS Module

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/isabl-submit-data/SKILL.md

Initial import statement for validation scripts.

```python
import os
```

--------------------------------

### Define Application Metadata

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/isabl-write-app/SKILL.md

Create the application class by inheriting from AbstractApplication and specifying required metadata like NAME and VERSION.

```python
from isabl_cli import AbstractApplication, options

class MyApplication(AbstractApplication):
    """
    Brief description of what this application does.
    """

    # Required metadata
    NAME = "my_application"
    VERSION = "1.0.0"

    # Optional: restrict to specific assembly/species
    ASSEMBLY = "GRCh37"  # or "GRCh38", None for any
    SPECIES = "HUMAN"    # or None for any
```

--------------------------------

### Optimize Data Fetching with Field Selection

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/isabl-query-data/SKILL.md

Improve performance by fetching only necessary fields when retrieving experiments. Uses 'isabl_cli'.

```python
import isabl_cli as ii

# Only fetch needed fields
experiments = ii.get_experiments(
    projects=102,
    fields=["pk", "system_id", "sample"]
)
```

--------------------------------

### Retrieve Specific Fields for Isabl Experiments

Source: https://github.com/juanesarango/isabl-mcp/blob/main/skills/isabl-query-data/SKILL.md

Fetches only the 'system_id' and 'sample' fields for Isabl experiments to optimize data retrieval. This is useful when only specific attributes are needed, adhering to ID display conventions.

```python
import isabl_cli as ii

experiments = ii.get_experiments(projects=102, fields=["system_id", "sample"])
for exp in experiments:
    print(f"experiment_id={exp.system_id}")
```