Thermal-Fluid Research Workflow Plugin

English | 简体中文 | 繁體中文

A domain-rigor layer for thermal-fluid mechanical engineering research with AI agents.

Generic research agents can summarize papers and draft prose. This plugin helps them do the harder mechanical-engineering work: check heat-transfer and fluid-flow assumptions, catch invalid correlation use, question CFD validation, protect uncertainty analysis, explain mechanisms, and turn evidence into decision-ready research artifacts.

Use it when a thermal-fluid answer needs to be physically defensible, not just well written.

If this helps your research workflow, please star the repo so other mechanical-engineering researchers can find it.

Want the fastest path? Start with QUICKSTART.md.

Two-Minute Demo

Paste a prompt like this after installing the skill:

Use the mechanical-engineering-research skill to review this claim:

"The CFD model proves that the new microchannel heat sink is optimal because
the average Nusselt number is 40% higher than the baseline. The simulation used
k-epsilon turbulence, a coarse wall mesh, constant water properties, and three
flow rates between Re = 350 and 900. Pressure drop is not discussed."

Expected style of response:

Bottom line: The claim is overconfident. The result may indicate better heat
transfer in the tested cases, but it does not prove optimality.

Key issues:
- Re = 350-900 may be laminar or transitional for the stated geometry, so a
  k-epsilon turbulence model needs justification.
- A coarse wall mesh weakens confidence in wall heat flux and Nusselt number.
- Constant water properties may be acceptable only over a small temperature
  range; the temperature span must be stated.
- A 40% Nusselt increase is incomplete without pressure drop, pumping power,
  and thermal resistance.
- "Optimal" requires a design space, objective function, constraints, and
  uncertainty or grid-independence evidence.

Next checks: compare against laminar correlations or a conjugate heat-transfer
baseline, report y+ or wall treatment, run mesh independence, include pressure
drop and pumping power, and rewrite the claim as evidence from a limited CFD
study rather than proof of global optimality.

Workflow

%%{init: {"theme": "base", "themeVariables": {"fontFamily": "Inter, Segoe UI, Arial, sans-serif", "primaryColor": "#ecfeff", "primaryTextColor": "#0f172a", "primaryBorderColor": "#0f766e", "lineColor": "#475569", "secondaryColor": "#fff7ed", "tertiaryColor": "#f8fafc", "clusterBkg": "#ffffff", "clusterBorder": "#cbd5e1", "edgeLabelBackground": "#ffffff"}}}%%
flowchart TB
    A["Researcher or agent request<br/>paper, proposal, CFD, experiment, data, code, or slides"]:::input
    B["Thermal-Fluid Research Workflow Plugin<br/>routes the task and loads the right reference guidance"]:::core

    C["Academic research workflow<br/>outline, checkpoints, citation flow, review and revision loop"]:::scaffold
    D["Mechanical-engineering judgment layer<br/>physics, assumptions, validity ranges, mechanisms, and engineering tradeoffs"]:::core

    A --> B
    C -. "process scaffold" .-> B
    B --> D

    D --> E{"Choose the work mode"}:::gate

    E --> F1["Literature review<br/>mechanism map, source hierarchy, gaps, benchmark tables"]:::lane
    E --> F2["Analysis and DOE<br/>baseline case, parameter logic, plots, uncertainty"]:::lane
    E --> F3["CFD and experiments<br/>boundary conditions, mesh, sensors, calibration, validation"]:::lane
    E --> F4["Writing and proposals<br/>methods, results discussion, aims, reviewer criteria"]:::lane
    E --> F5["Research code and AI/ML<br/>reproducible pipeline, leakage checks, physics sanity tests"]:::lane
    E --> F6["Slides and innovation<br/>visual story, impact, disclosure, commercialization notes"]:::lane

    F1 --> G
    F2 --> G
    F3 --> G
    F4 --> G
    F5 --> G
    F6 --> G

    G["Thermal-fluid rigor gate<br/>regime | correlations | properties | scaling | validation | safety | standards"]:::gate
    H["Decision-ready output<br/>assumptions, evidence, equations, tradeoffs, gaps, and next verification steps"]:::output
    I["Reusable artifact<br/>brief, literature matrix, manuscript section, proposal narrative, code review, or slide outline"]:::artifact

    G --> H --> I

    classDef input fill:#eff6ff,stroke:#2563eb,stroke-width:2px,color:#0f172a;
    classDef core fill:#ccfbf1,stroke:#0f766e,stroke-width:3px,color:#0f172a;
    classDef scaffold fill:#f8fafc,stroke:#64748b,stroke-width:2px,color:#0f172a;
    classDef lane fill:#fff7ed,stroke:#f97316,stroke-width:2px,color:#0f172a;
    classDef gate fill:#fef3c7,stroke:#d97706,stroke-width:3px,color:#0f172a;
    classDef output fill:#ecfdf5,stroke:#16a34a,stroke-width:3px,color:#0f172a;
    classDef artifact fill:#f5f3ff,stroke:#7c3aed,stroke-width:2px,color:#0f172a;

Editable Mermaid source: assets/workflow.mmd.

What It Catches

• Correlations used outside their Reynolds, Prandtl, geometry, roughness, orientation, or phase-change validity range.
• CFD claims without mesh independence, wall treatment, convergence, boundary-condition, property-model, or validation evidence.
• Experiment plans missing sensor calibration, uncertainty propagation, repeatability, heat-loss correction, or flow-development checks.
• AI/ML workflows with leakage across videos, surfaces, experiments, geometries, pressures, or simulation families.
• Literature reviews that list papers chronologically instead of synthesizing mechanisms, methods, gaps, and benchmark evidence.
• Proposal sections that describe ambitious methods but do not connect barrier, capability, validation, metrics, risk, and impact.
• Results discussions that report trends without explaining the dominant physics.

Quick Install

OpenAI Codex

Ask Codex to install the plugin from GitHub:

Install the Codex plugin from https://github.com/hanhuark/mechanical-engineering-research-skill

If your Codex environment does not yet support community plugin installation from a GitHub repo, install the skill folder directly:

Install the Codex skill from GitHub repo hanhuark/mechanical-engineering-research-skill, path skills/mechanical-engineering-research.

Manual install on Windows:

git clone https://github.com/hanhuark/mechanical-engineering-research-skill.git
cd mechanical-engineering-research-skill
Copy-Item -Recurse .\skills\mechanical-engineering-research "$env:USERPROFILE\.codex\skills\mechanical-engineering-research" -Force

Claude Code

Clone the repository and launch Claude Code with the plugin directory:

git clone https://github.com/hanhuark/mechanical-engineering-research-skill.git
claude --plugin-dir ./mechanical-engineering-research-skill

Then invoke one of the workflow prompts, for example:

/thermal-fluid-research-workflow:me-cfd-review
/thermal-fluid-research-workflow:me-correlation-check
/thermal-fluid-research-workflow:me-figure-discussion

Use With Generic Academic Workflows

This plugin does not replace broad academic-research tools. Use generic academic workflows for process scaffolding: outline, citation management, drafting sequence, peer-review loop, and finalization. Use this plugin when the work depends on thermal-fluid validity: regimes, assumptions, correlations, property variation, scaling, CFD credibility, experiment design, uncertainty, and engineering tradeoffs.

academic research workflow = process scaffold
mechanical-engineering-research = thermal-fluid domain judgment layer

Workflow Prompts

Showcase

The examples are synthetic, public-safe artifacts designed to show the plugin's expected behavior:

Capabilities

Validation

Run repository validation:

python scripts\validate_repo.py

Optional local Codex/plugin validation:

python "$env:USERPROFILE\.codex\skills\.system\skill-creator\scripts\quick_validate.py" ".\skills\mechanical-engineering-research"
python "$env:USERPROFILE\.codex\skills\.system\plugin-creator\scripts\validate_plugin.py" "."

The CI workflow in .github/workflows/validate.yml runs the repository validation script and checks the thermal-fluid eval fixtures.

Release Notes

See CHANGELOG.md. The v0.2.0 release line adds the public-positioning refresh, workflow diagram, showcase examples, micro-workflows, validation fixtures, CI, and bilingual README files.

Related Tools

Contributing

Contributions are welcome when they improve reusable thermal-fluid research practice: stronger validity checks, better examples, clearer workflows, more robust eval fixtures, or better installation documentation. See CONTRIBUTING.md.

License

MIT License. See LICENSE.