Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

cfd-research

Étoiles39

Forks4

Mis à jour6 mai 2026 à 23:05

Top-level CFD research entry — alias for cfd-skills/cfd-pipeline (general path). Use when the user gives a CFD research topic and wants the full literature → hypothesis → mesh-gate → experiments → analysis → paper flow. The full self-contained recipe lives in cfd-skills/cfd-pipeline/SKILL.md.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

csml-rpi

csml-rpi/AI-CFD-Scientist

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

PhysiciensSciences de la vie, physiques et sociales·SOC 19-2012

Explorateur de fichiers

2 fichiers

SKILL.md

readonly

name	cfd-research
description	Top-level CFD research entry — alias for cfd-skills/cfd-pipeline (general path). Use when the user gives a CFD research topic and wants the full literature → hypothesis → mesh-gate → experiments → analysis → paper flow. The full self-contained recipe lives in cfd-skills/cfd-pipeline/SKILL.md.
allowed-tools	Bash, Read, Write

cfd-research (alias)

This skill is a thin alias for cfd-skills/cfd-pipeline/SKILL.md. The full self-contained, ARIS/DS-style end-to-end recipe (literature, hypothesis, requirements, mesh-gate, experiments, interpret, analyze, paper) — including all expert prompts embedded verbatim — is documented there.

Why an alias?

Historically, skills/ housed the router + research/code-mod/mesh-independence skills. cfd-skills/ was added later as the per-stage recipe layer.
After the Nov 2026 ARIS/DS-style refactor, the full recipes live under cfd-skills/. This file remains so existing routing in CLAUDE.md and external agent configurations keep working.

Use this skill if you came here via:

The CLAUDE.md "study/sensitivity/turbulence/backward step/channel/experiment/run" routing line.
An external agent config that was set up before the refactor.

Do this

Open cfd-skills/cfd-pipeline/SKILL.md and follow the general path chain (Steps 1–13).
For each sub-stage, follow the corresponding cfd-skills/cfd-<stage>/SKILL.md (each is fully self-contained with its expert prompts embedded).

Behavioral contracts preserved here

Mandatory mesh-independence gate before any experiment sweep — see cfd-skills/cfd-mesh-gate/SKILL.md.
Foam-Agent runtime for case execution — see skills/cfd-foamagent-runtime/SKILL.md (still the canonical Foam-Agent execution contract).
CFL-aware retry policy for slow/failing runs — see cfd-skills/cfd-experiment/SKILL.md.
Long-run policy (multi-hour OK; no premature timeout) — applies everywhere.
Expert prompts from prompts/prompts.yaml are embedded verbatim in every relevant cfd-skills/cfd-<stage>/SKILL.md. The YAML remains the authoritative source.

Migration note

If you have agent code that previously invoked /cfd-research, replace it with /cfd-pipeline for new work; both work identically today, but new development happens under cfd-skills/.

Plus depuis ce dépôt

même dépôt

cfd-analyze

csml-rpi/AI-CFD-Scientist

Per-case + cross-case TEXT/JSON analysis — collect all PROCEED-flagged cases, compute QoI tables, identify trends and correlations, produce analysis.json that downstream skills consume. Self-contained — embeds ResultsInterpreterAgent.system_prompt + user_prompt verbatim. Scope boundary — this skill produces text + tables only. Cross-case figure generation (Cf overlays, RMSE bars, Δ-fields, parametric trends) is owned by cfd-cross-analyze. Per-case PyVista renders are owned by cfd-viz mode=interpret. Paper figure planning + LaTeX writing is owned by cfd-paper.

2026-05-2039

cfd-code-modify

csml-rpi/AI-CFD-Scientist

Implement a custom OpenFOAM model (viscosity / turbulence / source term / fvOption) inside a case-local customModels directory. Self-contained — embeds the full openfoam_literature_change_agent_prompt_v2 protocol AND the compile_fix prompts verbatim. Builds payload, generates C++, compiles with wmake, smoke-tests. NEVER edits OpenFOAM installation directories.

2026-05-2039

cfd-cross-analyze

csml-rpi/AI-CFD-Scientist

Cross-experiment quantitative analysis. Author Python scripts (numpy + matplotlib + PyVista + pandas) that load every PROCEED case, compute aggregated metrics, and generate the comparison figures the paper needs (Cf overlays vs reference, RMSE bar charts, parametric trends, Δ-field contours). Then run a vision+text interpretation pass over the generated plots. This is the cross-case Python authoring layer cfd-paper consumes — without it, papers end up with only per-case contours.

2026-05-2039

cfd-experiment

csml-rpi/AI-CFD-Scientist

Run CFD cases. Two modes — sweep (ARIS-style, agent-driven, no FoamAgent handoff) for parameter variants on a known-good baseline; single-case (FoamAgent-driven via scripts/foam_run.py) for fresh case generation that needs RAG. Embeds RunValidityAgent prompts (Allrun preflight + runtime investigation) verbatim. Writes <case_dir>/run_result.json.

2026-05-2039

cfd-foamagent

csml-rpi/AI-CFD-Scientist

Generate one OpenFOAM case from a natural-language requirement using a markdown-driven FoamAgent loop. Self-contained — embeds parser/planner/writer/reviewer prompts verbatim from Foam-Agent/src/services/. The agent runtime drives the loop natively via Read/Write/Bash. FAISS RAG retrieval uses scripts/rag_query.py; pdflatex, xvfb-run, inline Python, jq, and all other tools are also available — the only forbidden script across the entire system is scripts/orchestrator_run.py.

2026-05-2039

cfd-hypothesis

csml-rpi/AI-CFD-Scientist

Convert literature + topic into a list of testable, FoamAgent-executable CFD hypotheses. Self-contained — embeds the HypothesisAgent system + user prompts verbatim from prompts/prompts.yaml. Outputs hypotheses.json. Use after cfd-literature in the general pipeline.

2026-05-2039

name	cfd-research
description	Top-level CFD research entry — alias for cfd-skills/cfd-pipeline (general path). Use when the user gives a CFD research topic and wants the full literature → hypothesis → mesh-gate → experiments → analysis → paper flow. The full self-contained recipe lives in cfd-skills/cfd-pipeline/SKILL.md.
allowed-tools	Bash, Read, Write

cfd-research (alias)

Why an alias?

Historically, skills/ housed the router + research/code-mod/mesh-independence skills. cfd-skills/ was added later as the per-stage recipe layer.
After the Nov 2026 ARIS/DS-style refactor, the full recipes live under cfd-skills/. This file remains so existing routing in CLAUDE.md and external agent configurations keep working.

Use this skill if you came here via:

The CLAUDE.md "study/sensitivity/turbulence/backward step/channel/experiment/run" routing line.
An external agent config that was set up before the refactor.

Do this

Open cfd-skills/cfd-pipeline/SKILL.md and follow the general path chain (Steps 1–13).
For each sub-stage, follow the corresponding cfd-skills/cfd-<stage>/SKILL.md (each is fully self-contained with its expert prompts embedded).

Behavioral contracts preserved here

Mandatory mesh-independence gate before any experiment sweep — see cfd-skills/cfd-mesh-gate/SKILL.md.
Foam-Agent runtime for case execution — see skills/cfd-foamagent-runtime/SKILL.md (still the canonical Foam-Agent execution contract).
CFL-aware retry policy for slow/failing runs — see cfd-skills/cfd-experiment/SKILL.md.
Long-run policy (multi-hour OK; no premature timeout) — applies everywhere.
Expert prompts from prompts/prompts.yaml are embedded verbatim in every relevant cfd-skills/cfd-<stage>/SKILL.md. The YAML remains the authoritative source.

Migration note

If you have agent code that previously invoked /cfd-research, replace it with /cfd-pipeline for new work; both work identically today, but new development happens under cfd-skills/.