# Molclaw Denovo Sampling

> Generate new molecules de novo.

- Skill: `internscience/molclaw-denovo-sampling` (Agent Skill)
- Install (CLI): `npx skillmds@latest add internscience/molclaw-denovo-sampling`
- Raw SKILL.md: https://api.skillmd.com/api/skills/internscience/molclaw-denovo-sampling/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- License: MIT license
- Author: internscience (https://skillmd.com/u/internscience)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/internscience/molclaw-denovo-sampling

---


# Molecule Generation De Novo

Note: 
- Local files are not directly accessible by the server. Please upload them to the server using `molclaw-file-transfer` before execution. 
- For PDB file inputs, it is recommended to preprocess them using `molclaw-pdbfixer` before execution.
- Please refer to skill `molclaw-scp-server` to complete tool invocation.

The description of tool *reinvent_denovo_sampling*.

```tex
Generate new molecules de novo.
Args:
    n (int): Number of molecules for sampling
    lipinski (bool): Required flag controlling Lipinski filtering (commonly True)
    filter_preset (str): Required filter preset; options: ['none', 'minimal', 'default', 'strict', 'druglike', 'all'] (commonly 'druglike')
Return:
    status (str): success/error
    msg (str): message
    save_smiles_file (str): Path to the saved SMILES file
    output_smiles_list (List[str]): List of generated SMILES strings
```

How to use tool *reinvent_denovo_sampling* :

```python
response = await client.session.call_tool(
    "reinvent_denovo_sampling",
    arguments={
        "n": n,
        "lipinski": True,
        "filter_preset": filter_type
    }
)
result = client.parse_result(response)
output_smiles_list = result["output_smiles_list"]
```