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 skills add SFETNI/Deep-Matter-Chem-Skills --skill pinns-scientific-mlgit clone --depth 1 https://github.com/SFETNI/Deep-Matter-Chem-SkillsWrote 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/sfetni/deep-matter-chem-skills/pinns-scientific-ml)<a href="https://agentmods.dev/skills/sfetni/deep-matter-chem-skills/pinns-scientific-ml"><img src="https://agentmods.dev/badge/skills/sfetni/deep-matter-chem-skills/pinns-scientific-ml/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/sfetni/deep-matter-chem-skills/pinns-scientific-ml"><img src="https://agentmods.dev/badge/skills/sfetni/deep-matter-chem-skills/pinns-scientific-ml.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00008 | $0.03907 |
| Opus 5 | $0.00004 | $0.01954 |
| Sonnet 5 | $0.00002 | $0.00781 |
| Haiku 4.5 | $0.00001 | $0.00391 |
Grade A, and why
pinns-scientific-ml 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 12d 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PINNs for Scientific Machine Learning
Description
This skill covers physics-informed neural networks (PINNs) for scientific and engineering modeling: strong-form and weak-form physics losses, PDE residuals, boundary and initial condition enforcement, inverse problems, parameter identification, surrogate modeling for PDE systems, optimizer choices, validation, uncertainty analysis, and comparison against FEM, finite difference, spectral methods, and Gaussian-process surrogates. Invoke this skill when a neural model must satisfy known governing equations while fitting sparse data or approximating a parametric PDE solution.
Domain Context
PINNs approximate unknown fields with neural networks and train them by minimizing a combination of data mismatch and physics residual losses. The physics loss is usually computed by automatic differentiation of the network output with respect to space, time, and parameters. This makes PINNs attractive for inverse problems, sparse-data settings, moving between data and governing equations, and building differentiable surrogates for PDE systems.
PINNs are not a drop-in replacement for finite element, finite difference, finite volume, or spectral solvers. Classical solvers usually remain more reliable for well-posed forward PDEs with known geometry, boundary conditions, and material parameters. PINNs can be useful when data are sparse, parameters are unknown, the solution needs to be differentiable with respect to inputs, or the model must combine noisy measurements and governing equations. They can fail silently through loss imbalance, spectral bias, poor boundary enforcement, non-identifiability, bad nondimensionalization, or weak validation. [EXPERT REVIEW NEEDED]
The physical interpretation of a PINN depends on the exact loss. A network that minimizes a PDE residual at collocation points is not guaranteed to satisfy conservation, boundary conditions, shocks, discontinuities, or sharp interfaces unless the formulation and sampling strategy enforce them. Weak-form or variational PINNs can improve treatment of integral constraints and lower derivative order, but introduce quadrature, test-function, and domain-integration choices. [EXPERT REVIEW NEEDED]
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.
- 12d ago First seen · 291 lines · 8 tokens per session scan A ab5a89568ff3
pinns-scientific-ml is a skill published in the GitHub repository SFETNI/Deep-Matter-Chem-Skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 3,907 once invoked, about $0.0000 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 2026-08-31.
Other skills, from other repositories
primekg
Query the Precision Medicine Knowledge Graph (PrimeKG) for multiscale biological relationships across genes and proteins, drugs, diseases, phenotypes, pathways, biological processes, exposures and anatomy. Use this skill to search entities by name, pull direct neighbours and their evidence types, summarise the local…
fragment-based-count-matrix-generation
Use when you have a backed AnnData object containing processed fragment data (stored in .obsm['fragmentpaired'] or .
methylbase-object-handling
Use when after reading in per-sample methylation call files with methRead() and obtaining methylRawList objects, but before calculating differential methylation or performing annotation.
motif-annotation-correlation-analysis
Use when you have a chromVARDeviations object with multiple annotation sets (such as JASPAR motifs and kmers) and need to determine which annotation pairs are redundant (high correlation) versus synergistic (high synergy z-scores).
motif-database-query-and-matching
Use when you have a set of differentially accessible peaks (output from differential accessibility testing, e.g., tl.
motif-enrichment-statistical-testing
Use when after identifying a set of differentially accessible peaks (via tl.difftest or equivalent), when you need to infer which transcription factors may regulate the observed chromatin state changes.