Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Cfd Convergence

ASecurity

Use when you must judge whether a computational fluid dynamics run has converged: check that residuals drop below tolerance and stay monotone, confirm the Courant number respects the scheme stability limit, and compare mesh refinement levels for answer stability. Produces the residual verdict, the CFL check, and the mesh convergence flag that decide whether results can be trusted. Trigger: cfd convergence, residual convergence, courant number, mesh refinement, solver stability.

2 stars
0 votes
0 copies
0 views
Added 9/27/2026
ai-agentspythonrustgo

Works with

claude code

Security Analysis

A100/100

Scanned 9/27/2026

Install to Claude Code

$npx -y skills add ashfordeOU/aero-agent-skills --skill cfd-convergence --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Cfd Convergence?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Cfd Convergence
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-cfd-convergence/badge)](https://www.skillsdirectory.com/skills/ashfordeou-cfd-convergence)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: cfd-convergence
description: "Use when you must judge whether a computational fluid dynamics run has converged: check that residuals drop below tolerance and stay monotone, confirm the Courant number respects the scheme stability limit, and compare mesh refinement levels for answer stability. Produces the residual verdict, the CFL check, and the mesh convergence flag that decide whether results can be trusted. Trigger: cfd convergence, residual convergence, courant number, mesh refinement, solver stability."
license: Apache-2.0
compliance: STANDARDS-REF
standards:
  - id: naca-tr-824
    reference-only: true
gated: false
domain: aerodynamics
pack: aerodynamics
compatibility: "agentskills.io SKILL.md; any SKILL.md host (Claude Code, Hermes, OpenClaw)"
metadata:
  domain: aerodynamics
  subdomain: cfd
  tags: [cfd-convergence, residual-convergence, courant-number, mesh-refinement, solver-stability]
  version: 0.1.0
  author: Aero Agent Skills
---

# CFD Convergence Checks (aerodynamics/cfd/cfd-convergence)

Use when the task is judging computational fluid dynamics
convergence: residual behavior, Courant number stability, and mesh
refinement stability of the answer.

## Domain quick reference

- A converged run has residuals below tolerance and still
  decreasing; oscillating or flat residuals mean the run is not
  converged.
- The Courant number must respect the scheme stability limit:
  about 1 for explicit schemes, higher for implicit schemes.
- Mesh refinement convergence compares the answer across mesh
  levels; small change means the discretization error is bounded.
- Validation against classic data (NACA Report 824) anchors the
  converged answer for airfoil cases.

## Workflow

1. Collect the residual history from the solver log.
2. Check convergence with residual_converged.
3. Confirm the Courant number with cfl_ok.
4. Compare mesh levels with mesh_refinement_ok.
5. Decide whether to trust the run.

## Pitfalls

- Calling a run converged on a flat residual plateau.
- Running explicit schemes at Courant numbers above the limit.
- Reporting an answer that changed on the next mesh level.

## Behavior contract (gate 3)

The residual, CFL, and mesh logic is exercised by the gate 3
contract test: scripts/test_cfd_convergence.py against
scripts/cfd_convergence_logic.py (stdlib unittest, offline). Run:
python3 scripts/test_cfd_convergence.py

## Compliance

- NACA Report 824 is US government work (public domain); summary
  and physics values only, per standards-map.yaml.
- compliance: STANDARDS-REF, gated: false.

Attribution

ashfordeOUashfordeOU
View sourceMore from ashfordeOU →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

694821 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →