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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/synthetic-sciences/opensciencenpx agentmods add skills/synthetic-sciences/openscience/multi-objective-optimizationWrote 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/multi-objective-optimization)<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/multi-objective-optimization"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/multi-objective-optimization/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/multi-objective-optimization"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/multi-objective-optimization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.00729 |
| Opus 5.5 | $0.00015 | $0.00292 |
| Sonnet 5.5 | $0.00007 | $0.00146 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
multi-objective-optimization 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 1mo 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Objective Molecular Optimization
Overview
Real drug design is never single-objective. A useful molecule must simultaneously satisfy potency, selectivity, solubility, metabolic stability, and safety constraints. This skill implements Pareto-aware optimization that balances multiple properties without collapsing to a single weighted score.
Based on:
- MultiMol (Yu et al., 2025): 82.3% multi-objective success rate with generate-then-rank
- MOLLM (Ran et al., 2025): LLMs as genetic operators for multi-objective molecular design
- DrugR (Liu et al., 2026): Multi-granular reward balancing across property groups
When to Use This Skill
- "Improve potency while keeping hERG safe" — classic multi-objective lead optimization
- Balancing ADMET tradeoffs — LogP vs solubility, BBB penetration vs peripheral safety
- Pareto analysis — identify which candidates best balance competing objectives
- Property-constrained generation — generate molecules within a defined property box
Do NOT use this skill for:
- Single-property optimization (use
molecular-optimization) - Property prediction without optimization (use
admet-prediction)
Related Skills
- molecular-optimization: Single-objective iterative optimization
- admet-prediction: Compute properties used as objectives
- admet-reasoning: Understand why properties need improvement
Installation
pip install rdkit-pypi numpy pandas
Optional
pip install matplotlib # For Pareto front visualization
Core Workflows
1. Multi-Objective Optimization
python scripts/pareto_optimize.py \
--smiles "c1ccc(NC(=O)c2ccccc2Cl)cc1" \
--objectives "LogP:minimize:3.0,QED:maximize:0.5,TPSA:range:20:130" \
--candidates 16 \
--output pareto_results.json
2. Pareto Analysis of Existing Candidates
python scripts/pareto_optimize.py \
--input candidates.csv \
--objectives "LogP:minimize:3.0,QED:maximize:0.5" \
--mode analyze \
--output pareto_front.json
What ships with it
1 file 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.
- 1mo ago First seen · 89 lines · 37 tokens per session scan A a06051c371b8
multi-objective-optimization is a skill published in the GitHub repository synthetic-sciences/openscience (4,243 stars, last pushed yesterday), licensed Apache-2.0. It adds 37 tokens to every session and 729 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
tinyjs
Build and modify tinyjs desktop apps — tiny macOS (and beta Windows/Linux) apps with a txiki.js JavaScript backend and a native webview window. Use when working in a project with a tinyjs.json, when the user mentions tinyjs, tiny.api, or tinyjs dev/build, or when porting an Electron app to tinyjs.
data-scientist
!cat Claude-Production-Grade-Suite/.protocols/ux-protocol.md 2>/dev/null || true !cat Claude-Production-Grade-Suite/.protocols/input-validation.md 2>/dev/null || true !cat Claude-Production-Grade-Suite/.protocols/tool-efficiency.md 2>/dev/null || true !cat Claude-Production-Grade-Suite/.protocols/visual-identity.md…
coding-plan
Enter "plan mode" for a coding task — read the relevant code, optionally ask clarifying questions, design one recommended approach, then write a plain, scannable plans/ - .md file. No source files are edited in this mode. Use this skill whenever the user says "plan mode", "/coding-plan", "make a plan", "draft a plan…
deep-research-plan
Enter "plan mode" for a deep-research or article-writing task — search the web, fetch sources, optionally run experiments in Python/Node, design one recommended outline and research strategy, then write a plain, scannable plans/ - .md file. No article content is drafted in this mode. Use this skill whenever the user…
songsee
Audio spectrograms/features (mel, chroma, MFCC) via CLI.
arxiv
Search arXiv papers by keyword, author, category, or ID.