synthetic-sciences/openscience is an AI workbench that carries out scientific research by reading papers, forming hypotheses, writing and running code, conducting experiments, analyzing results, and preparing reports. Researchers use it for work in machine learning, biology, physics, and chemistry with remote or local models. Catalogue add-ons extend its scientific workflows through skills and instructions.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/synthetic-sciences/openscience/denovo-designnpx skills add synthetic-sciences/openscience --skill denovo-designgit clone --depth 1 https://github.com/synthetic-sciences/openscienceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/synthetic-sciences/openscience/denovo-design)<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/denovo-design"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/denovo-design.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.01930 |
| Opus 5 | $0.00019 | $0.00965 |
| Sonnet 5 | $0.00008 | $0.00386 |
| Haiku 4.5 | $0.00004 | $0.00193 |
Grade A, and why
denovo-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
De Novo Molecule Design
Overview
De novo design is the computational generation of novel molecular structures with desired properties, without starting from known active compounds. This skill provides a complete toolkit for generating drug candidates through multiple complementary strategies: scaffold-based analog enumeration, fragment-based design, structure-based design (SBDD), multi-objective optimization, and drug-likeness filtering.
All generation strategies produce molecules with computed physicochemical properties and similarity metrics, enabling rapid prioritization. The scripts are designed for CPU-first execution using RDKit as the core cheminformatics engine, with optional GPU acceleration noted where applicable.
When to Use This Skill
Use this skill when you need to:
- Explore chemical space around a known lead compound by generating analogs with R-group enumeration, bioisosteric replacements, or random mutations
- Design molecules from fragments by growing, linking, or merging fragment hits from screening campaigns
- Generate molecules for a protein target using pocket shape complementarity or pharmacophore constraints
- Optimize a set of hits against multiple objectives (QED, LogP, synthetic accessibility, molecular weight) through iterative refinement
- Filter compound libraries for drug-likeness using Lipinski, Veber, PAINS, Brenk alerts, lead-like, fragment-like, or beyond Rule of Five criteria
- Enumerate focused libraries for virtual screening or synthesis planning
Installation
pip install rdkit-pypi datamol numpy pandas
Optional (for enhanced fragment design and structure-based approaches):
pip install scipy
For structure-based design with PDB parsing:
pip install biopython
Choosing the Right Strategy
| Scenario | Script | Strategy |
|---|---|---|
| Have a lead compound, want analogs | generate_analogs.py |
R-group, bioisostere, mutate |
| Have fragment screening hits | generate_fragments.py |
grow, link, merge |
| Have a protein structure / pocket | generate_sbdd.py |
shape, pharmacophore |
| Have hits, need property optimization | optimize.py |
multi-objective iterative |
| Have a library, need filtering | filter.py |
lipinski, veber, pains, etc. |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 164 lines · 38 tokens per session scan A 5ad3722c2086
denovo-design is a skill published in the GitHub repository synthetic-sciences/openscience (3,473 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 1,930 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
meta-paper-write
Use this meta-skill instead of answering directly when the current user asks to draft or produce a new academic/research paper or LaTeX manuscript. It uses multi-skill orchestration for manuscript workflows that need source search, citation planning, experiment or figure/table placeholders, drafting, length checks…
paper-revision-author
Revise independently drafted paper sections into one coherent LaTeX body before the abstract is written.
paper-section-author
Write one publication-style research-paper section as a bounded, citation-grounded LaTeX fragment from a writing plan, outline, citation plan, and optional figure/table context.
meta-arxiv-daily-digest-deck
Fetch the day's top arXiv submissions in a chosen category, write a structured per-paper digest, render the digest as a PPTX deck (one slide per paper), and persist the digest to long-term memory. Use for a daily 'arxiv morning briefing' — manual fire or cron-scheduled.
paper-quality-gate
Deterministic pre-compile gate for meta-paper-write. Enforces length/citation verdicts and rejects unsupported empirical-result claims when no user evidence was supplied.
paper-latex-sanitizer
Deterministically normalize safe LaTeX punctuation and replace unsupported forecast magnitudes with explicit placeholders before meta-paper-write publication gates run.