Numerical Linear Algebra Toolkit
Developmentnumerical-linear-algebra-toolkitNumerical Linear Algebra Toolkit is an Agent Skill for development published in the a5c-ai/babysitter repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
High-performance numerical linear algebra operations
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/a5c-ai/babysitter/blob/HEAD/library/specializations/domains/science/mathematics/skills/numerical-linear-algebra-toolkit/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/numerical-linear-algebra-toolkit, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Numerical Linear Algebra Toolkit
Purpose
Provides high-performance numerical linear algebra operations for scientific computing and mathematical analysis.
Capabilities
- Matrix decompositions (LU, QR, SVD, Cholesky, Schur)
- Eigenvalue/eigenvector computation
- Sparse matrix operations
- Iterative solvers (CG, GMRES, BiCGSTAB)
- Condition number estimation
- Error analysis and bounds
Usage Guidelines
- Decomposition Selection: Choose appropriate factorization for the problem
- Sparsity Exploitation: Use sparse formats for large sparse matrices
- Iterative Methods: Apply iterative solvers for very large systems
- Conditioning: Assess and monitor condition numbers
Tools/Libraries
- LAPACK
- BLAS
- SuiteSparse
- Eigen