From godchi
Use when starting or planning any machine-learning task — exploring a dataset, engineering features, training, tuning hyperparameters, evaluating, integrating a model into a service or device, or deploying. Gives the senior AI-engineer lifecycle and routes to the right guard and detailed phase doc.
How this skill is triggered — by the user, by Claude, or both
Slash command
/godchi:ai-ml-workflowThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
The disciplined lifecycle toilact follows for ML work. This skill is the **map**: it names the phases,
The disciplined lifecycle toilact follows for ML work. This skill is the map: it names the phases,
the order, and which guard/doc to pull for each. Detailed playbooks live in the on-demand library — load
them with /gc-lib ml-lifecycle/<phase> only when you reach that phase (they are not auto-loaded).
Any ML/data task: EDA, feature engineering, preprocessing, training, hyperparameter tuning, evaluation, the iterate loop, on-device/service integration, deployment. Works for any ML project — tabular, time-series / forecasting, or NLP (e.g. a daily prediction pipeline, a fine-tuned transformer).
/gc-lib ml-lifecycle/eda — understand distributions, missingness, leakage risk, target balance./gc-lib ml-lifecycle/feature-engineering — MUST honor ml-data-leakage-guard./gc-lib ml-lifecycle/preprocess — fit transforms on the train fold only./gc-lib ml-lifecycle/training — reproducible runs, seeds, logged metrics./gc-lib ml-lifecycle/tuning — search with an inner split; MUST honor walk-forward-guard./gc-lib ml-lifecycle/loop — out-of-sample only; decide iterate vs ship./gc-lib ml-lifecycle/integrate — share ONE feature builder train↔serve;
MUST honor model-feature-versioning./gc-lib ml-lifecycle/deploy — version, monitor, roll back safely.ml-data-leakage-guard — feature(T) uses only data known at T.walk-forward-guard — train-on-past / test-on-future, no shuffle.model-feature-versioning — frozen feature contract, no train/serve skew.Follow the godchi gate: brainstorm the approach, write a short plan, confirm with the user before changing a chosen modelling decision, review results before declaring success. Reply in Vietnamese.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub toilact/godchi --plugin godchi