linear-solvers agent skill by HeshamFS

At a glance

Before you install

Read from the skill's files at the directory's October 22, 2026 snapshot: what ships with it, what its code reads, and the terms it is published under.

• Bundled scripts: 6 script files (6 Python). Your agent may run them, so read them first.
• Tool permissions requested: Read, Write, Grep, Glob (the allowed-tools field of SKILL.md).
• License: Apache-2.0, an open-source or open-content license.

Install linear-solvers

The skills CLI works with Claude Code, Codex, Cursor and other agents; the other routes copy the folder by hand.

npx skills add https://github.com/HeshamFS/materials-simulation-skills/tree/main/skills/core-numerical/linear-solvers

tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/HeshamFS/materials-simulation-skills.git "$tmp/repo"
mkdir -p .claude/skills
cp -R "$tmp/repo/"skills/core-numerical/linear-solvers .claude/skills/
rm -rf "$tmp"

tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/HeshamFS/materials-simulation-skills.git "$tmp/repo"
mkdir -p .agents/skills
cp -R "$tmp/repo/"skills/core-numerical/linear-solvers .agents/skills/
rm -rf "$tmp"

For a user-level install, copy the folder to ~/.claude/skills/ (Claude Code) or ~/.agents/skills/ (Codex). Inside Codex, $skill-installer can also fetch a skill from GitHub. New to skills? Read How to install agent skills in Claude Code, Codex and Cursor.

HeshamFS/materials-simulation-skills is third-party code. Read SKILL.md and any bundled scripts before you install it.

How the author describes it

Select and configure linear solvers for Ax=b systems arising in numerical simulations — choose between direct (LU, Cholesky) and iterative (CG, GMRES, BiCGSTAB, MINRES) methods, analyze sparsity patterns and matrix conditioning, recommend preconditioners (AMG, ILU, IC), apply row/column scaling, and diagnose convergence stagnation from residual histories. Use when setting up a linear solve for FEM/FVM assembly, debugging slow or stalled Krylov iterations, choosing a preconditioner for SPD or nonsymmetric systems, or investigating ill-conditioning, even if the user only says "my solver is slow" or "GMRES won't converge."

From the description field of SKILL.md. Agents read this line to decide when to load the skill.

Sections in SKILL.md

• Goal
• Requirements
• Inputs to Gather
• Decision Guidance
• Solver Selection Flowchart
• Quick Reference
• Script Outputs (JSON Fields)
• Workflow
• Conversational Workflow Example
• Pre-Solve Checklist
• CLI Examples
• Error Handling
• Interpretation Guidance
• Convergence Rate
• Stagnation Diagnosis
• Verification checklist

Files in the skill folder

• CHANGELOG.md
• SKILL.md
• evals/evals.json
• evals/files/A.npy
• references/convergence_patterns.md
• references/preconditioner_catalog.md
• references/scaling_guidelines.md
• references/solver_decision_tree.md
• scripts/convergence_diagnostics.py
• scripts/preconditioner_advisor.py
• scripts/residual_norms.py
• scripts/scaling_equilibration.py
• scripts/solver_selector.py
• scripts/sparsity_stats.py

Suede Skill Check: 82/100 · B

linear-solvers passes the required frontmatter check and all seven graded checks, which cover the SKILL.md format, a declared license and a commit in the last year. Those checks earn 56 of the score’s points; the rest come from description quality, instruction depth, bundled files, maintenance and curated-list citations. How the score works.

Where this skill is cited

HeshamFS/materials-simulation-skills appears in 2 curated lists: BehiSecc/awesome-claude-skills, VoltAgent/awesome-agent-skills.

More science and research skills

All science and research skills

More from HeshamFS/materials-simulation-skills

All 24 skills in HeshamFS/materials-simulation-skills