Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

habit-recipes

Étoiles6

Forks2

Mis à jour6 juillet 2026 à 05:41

End-to-end HABIT workflow recipes for common research scenarios (multi-modal MRI habitat, DCE-MRI kinetic, CT-only radiomics, test-retest reproducibility, demo dataset walkthrough). Use when the user wants to run the entire pipeline (preprocess -> habitat -> features -> ML -> comparison) instead of one isolated step. Triggers on phrases like "全流程", "端到端", "整个流程跑一遍", "demo 走一遍", "full pipeline", "end-to-end", "complete workflow".

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

lichao312214129

lichao312214129/HABIT

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

Explorateur de fichiers

6 fichiers

SKILL.md

readonly

name

habit-recipes

description

HABIT End-to-End Recipes

Pre-baked workflows for the most common research scenarios. Each recipe lists:

The user phrase that should trigger it
Required inputs the agent must collect
The exact CLI sequence to run
Where each output lands
A validation checkpoint after every step

Available recipes

Recipe file	When to use	Modality
`references/recipe_mri_habitat_full.md`	Multi-modal MRI habitat study	T1+T2(+DWI/ADC)
`references/recipe_dce_kinetic.md`	DCE dynamic habitat study	DCE-MRI / dynamic CT
`references/recipe_ct_radiomics_only.md`	Classical radiomics on CT	CT
`references/recipe_test_retest.md`	Reproducibility / ICC study	any modality, two scans
`references/recipe_demo_walkthrough.md`	First-time user demo	bundled demo data

How the agent should use this skill

Identify which recipe matches the user's request (use the table above).
Open the corresponding recipe file in references/.
Walk the user through the Required Inputs checklist BEFORE writing any config — do not invent paths or modality names.
Generate each YAML config in turn, starting from the templates listed in skills/CONFIG_SOURCES.md under config/<module>/.
Run each command, then immediately call the scripts/validate_*.py from the corresponding skill to verify outputs before moving on.
If a step fails, hand off to habit-troubleshoot.

Recipe selection cheat sheet

User says...                                                Pick recipe...
---------------------------------------------------------- -------------------------------
"我有 T1+T2+DWI+ADC, 想做生境分析建模"                       recipe_mri_habitat_full
"DCE 动态对比增强分期生境 / kinetic"                         recipe_dce_kinetic
"我只有 CT, 想做传统影像组学"                                recipe_ct_radiomics_only
"两次扫描看重复性 / test-retest / ICC"                       recipe_test_retest
"我刚装好, 想跑一下 demo 看看"                               recipe_demo_walkthrough
"我想跑全流程"                                               ASK which scenario, then pick

Universal best practices for any recipe

Always run check_environment.py first — verify HABIT is installed.
Always run check_data_layout.py before preprocess — catches missing modalities early.
Always validate output after each major step — validate_preprocess_output.py then validate_habitat_output.py then inspect_feature_csv.py.
Save every config the agent generates in a ./configs/ subfolder of the user's working directory; reproducibility matters.
Use absolute paths in configs when the user has files scattered across drives; use relative when everything is under one project root.

Plus depuis ce dépôt

même dépôt

habit-quickstart

lichao312214129/HABIT

Entry-point router for the HABIT (Habitat Analysis Biomedical Imaging Toolkit) package. Use this FIRST whenever a user mentions HABIT, habitat analysis, tumor sub-region clustering, intra-tumor heterogeneity, "生境分析", "亚区聚类", "habitat segmentation", or wants a multi-step radiomics workflow. Verifies environment, validates data layout, then hands off to the right specialist skill.

2026-07-216

habit-troubleshoot

lichao312214129/HABIT

Diagnose and fix HABIT runtime errors — covers preprocess, habitat clustering, feature extraction, and ML/comparison failures. Use when the user pastes a Python traceback, when a `habit ...` CLI command fails, when an output file is missing or corrupt, or when results look biologically wrong (degenerate clusters, all-NaN features, AUC=0.5). Triggers on phrases like "报错", "出错", "不工作", "为什么", "error", "failed", "traceback", "crash", "AUC 太低", "没有生成结果".

2026-07-216

habit-feature-extraction

lichao312214129/HABIT

Extract quantitative features from HABIT habitat maps — traditional radiomics, whole-habitat radiomics, per-habitat radiomics, MSI (Most Significant Intensity), and ITH (Intra-Tumor Heterogeneity) scores. Use when the user has habitat .nrrd maps and wants per-subject feature CSVs ready for ML. Triggers on "提取生境特征", "MSI 特征", "ITH 异质性", "habitat features", "extract radiomics from habitats". Runs `habit extract`.

2026-07-066

habit-habitat-analysis

lichao312214129/HABIT

Generate tumor habitat (sub-region) maps from medical images using voxel-level clustering. Use when the user wants to identify intra-tumor heterogeneity zones, perform supervoxel clustering, generate habitat .nrrd maps, run kinetic DCE habitat, or use voxel-radiomics texture clustering. Triggers on "生境分析", "亚区聚类", "habitat", "supervoxel", "kinetic", "DCE 分期生境", "intra-tumor heterogeneity". Runs `habit get-habitat`.

2026-07-066

habit-machine-learning

lichao312214129/HABIT

Train, predict, or k-fold cross-validate ML classifiers on habitat / radiomics feature CSVs using HABIT. Supports LogisticRegression, RandomForest, XGBoost, SVM, MLP, AutoGluon, and 12+ feature selection methods (LASSO, mRMR, RFECV, ICC, correlation, ANOVA, ...). Use when the user wants to build a prediction model from feature CSVs. Triggers on "训练模型", "建模", "K折交叉验证", "k-fold", "LASSO", "feature selection", "predict mode". Runs `habit model` or `habit cv`.

2026-07-066

habit-model-comparison

lichao312214129/HABIT

Compare multiple trained classification models with publication-quality plots — ROC, DCA, calibration, precision-recall, DeLong's AUC test. Use when the user has prediction CSVs from 2+ models and wants side-by-side comparison. Triggers on "模型比较", "ROC 对比", "DeLong 检验", "决策曲线", "校准曲线", "model comparison", "compare AUC", "DCA". Runs `habit compare`.

2026-07-066

name

habit-recipes

description

HABIT End-to-End Recipes

Pre-baked workflows for the most common research scenarios. Each recipe lists:

The user phrase that should trigger it
Required inputs the agent must collect
The exact CLI sequence to run
Where each output lands
A validation checkpoint after every step

Available recipes

Recipe file	When to use	Modality
`references/recipe_mri_habitat_full.md`	Multi-modal MRI habitat study	T1+T2(+DWI/ADC)
`references/recipe_dce_kinetic.md`	DCE dynamic habitat study	DCE-MRI / dynamic CT
`references/recipe_ct_radiomics_only.md`	Classical radiomics on CT	CT
`references/recipe_test_retest.md`	Reproducibility / ICC study	any modality, two scans
`references/recipe_demo_walkthrough.md`	First-time user demo	bundled demo data

How the agent should use this skill

Identify which recipe matches the user's request (use the table above).
Open the corresponding recipe file in references/.
Walk the user through the Required Inputs checklist BEFORE writing any config — do not invent paths or modality names.
Generate each YAML config in turn, starting from the templates listed in skills/CONFIG_SOURCES.md under config/<module>/.
Run each command, then immediately call the scripts/validate_*.py from the corresponding skill to verify outputs before moving on.
If a step fails, hand off to habit-troubleshoot.

Recipe selection cheat sheet

User says...                                                Pick recipe...
---------------------------------------------------------- -------------------------------
"我有 T1+T2+DWI+ADC, 想做生境分析建模"                       recipe_mri_habitat_full
"DCE 动态对比增强分期生境 / kinetic"                         recipe_dce_kinetic
"我只有 CT, 想做传统影像组学"                                recipe_ct_radiomics_only
"两次扫描看重复性 / test-retest / ICC"                       recipe_test_retest
"我刚装好, 想跑一下 demo 看看"                               recipe_demo_walkthrough
"我想跑全流程"                                               ASK which scenario, then pick

Universal best practices for any recipe

Always run check_environment.py first — verify HABIT is installed.
Always run check_data_layout.py before preprocess — catches missing modalities early.
Always validate output after each major step — validate_preprocess_output.py then validate_habitat_output.py then inspect_feature_csv.py.
Save every config the agent generates in a ./configs/ subfolder of the user's working directory; reproducibility matters.
Use absolute paths in configs when the user has files scattered across drives; use relative when everything is under one project root.