molclaw-chroma-toolkit

Files (1)

• SKILL.md

SKILL.md (first lines)

# Chroma Protein Generation Toolkit

## Invocation

Use the exact tool name and parameter schema exposed by the current harness. Tool names in SDK examples below are raw MCP names, not model-facing aliases. Local files must be uploaded with `molclaw-file-transfer` before a server tool can use them. Repair PDB inputs first when the workflow requires it.

## Usage

### 1. Monomer Protein Generation
The description of tool *chroma_monomer*.

```tex
Generates a de novo single-chain protein candidate for exploratory protein design workflows.
Args:
    length (int): Number of residues in the monomer chain. Default: 100.
    steps (int): Diffusion sampling step count. Default: 500.
    device (str): Chroma execution device string. Default: 'cuda:0'.
    fmt (str): Output structure format, one of {'cif', 'pdb'}. Default: 'cif'.
    api_key (str|None): Optional Chroma API key for model access.
    dry_run (bool): If True, validate parameters and prepare output paths without model sampling. Default: False.
Return:
    status (str): 'success' or 'error'.
    msg (str): Human-readable execution summary.
    tool_name (str): Tool identifier 'chroma_monomer'.
    output_dir (str): Run-specific output directory under tool_result/chroma_toolkit_result.
    output_file (str): Target output structure file path.
    length (int): Effective residue length used in generation.
    steps (int): Effective sampling steps used in generation.
    device (str): Effective execution device.
    format (str): Effective output format.
```

How to use tool *chroma_monomer* :

```python
response = await client.session.call_tool(
    "chroma_monomer",
    arguments={
        "length": 150,
        "steps": 500,
        "device": "cuda:0",
        "fmt": "cif",
        "dry_run": False
    }
)
result = client.parse_result(response)
output_file = result["output_file"]

```

#### Example parameter sets

```python
# 1) Main mode
{
    "length": 150,
    "steps": 500,
    "device": "cuda:0",
    "fmt": "cif",
    "dry_run": False
}

# 2) Variant mode
{
    "length": 100,
    "steps": 50,
    "fmt": "cif",
    "dry_run": True
}
```

### 2. Complex Protein Generation
The description of tool *chroma_complex*.

```tex
Generates a multi-chain protein complex candidate for interface and assembly design studies.
Args:
    chains (str): Comma-separated chain lengths, for example '100,120'. Default: '100,100'.
    steps (int): Diffusion sampling step count. Default: 500.
    device (str): Chroma execution device string. Default: 'cuda:0'.
    fmt (str): Output structure format, one of {'cif', 'pdb'}. Default: 'cif'.
    api_key (str|None): Optional Chroma API key for model access.
    dry_run (bool): If True, validate parameters and prepare output paths without model sampling. Default: False.
Return:
    status (str): 'success' or 'error'.
    msg (str): Human-readable execution summary.
    tool_name (str): Tool identifier 'chroma_complex'.
    output_dir (str): Run-specific output directory under tool_result/chroma_toolkit_result.
    output_file (str): Target output structure file path.
    chains (str): Effective chain-length specification used in generation.
    steps (int): Effective sampling steps used in generation.
    device (str): Effective execution device.
    format (str): Effective output format.
```

How to use tool *chroma_complex* :

```python
response = await client.session.call_tool(
    "chroma_complex",
    arguments={
        "chains": "100,120",
        "steps": 500,
        "device": "cuda:0",
        "fmt": "cif",
        "dry_run": False
    }
)
result = client.parse_result(response)
output_file = result["output_file"]

```

#### Example parameter sets

```python
# 1) Main mode
{
    "chains": "100,120",

From InternScience/MolClaw, MIT.

More from InternScience/MolClaw