Build a production-ready regression model on tabular data using XGBoost with conformalized quantile regression for prediction intervals. Use when the user needs to predict a continuous target from tabular features (price, sales, demand, time-to-event, score) and report uncertainty alongside the point estimate. Default to this for any tabular regression task.

brojonat0

Machine Learning

Binary Classification

Build a production-ready binary classifier on tabular data using XGBoost. Use when the user needs to predict a binary outcome from tabular features (churn, fraud, conversion, default, click). Covers class imbalance, threshold tuning, calibration verification, and SHAP feature importance. Default to this for any binary classification task on tabular data.

brojonat0

Machine Learning

Multiclass Classification

Build a production-ready multiclass classifier on tabular data using XGBoost. Use when the user needs to predict one of several discrete classes from tabular features (product category, sentiment level, customer segment, intent, fault type). Covers per-class metrics, confusion matrix analysis, sample weighting for imbalance, top-K accuracy, and SHAP. Default to this for any tabular multiclass problem.

brojonat0

Machine Learning

Sklearn Pipeline Template

Build a tabular ML project with scikit-learn Pipelines, MLflow tracking, model artifacts, and a marimo demo notebook. Use when starting any new tabular classification or regression bundle so all bundles share the same plumbing.

brojonat0

Machine Learning

Setup Engine

Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.

onemanking0

Machine Learning

Reforge Qa

Drive the build-time repair loop with root-cause analysis and regression-first fixes.

OnePunchForAll0

Machine Learning

Nesting Orientation Review Gate

How to gate orientation-preference changes in the nesting heuristic without losing fit behavior or determinism

BSchafer010

Machine Learning

Be Llm Integration

LLM provider adapter layer with streaming, multi-model parallel execution, cost tracking, and graceful fallback

bssm-oss0

Machine Learning

Prioritize Assumptions

Prioritize assumptions using an Impact × Risk matrix and suggest experiments for each. Use when triaging a list of assumptions, deciding what to test first, or applying the assumption prioritization canvas.

bssm-oss0

Machine Learning

Feature Spec Updater

既存SPECを修正するスキル。新規SPEC生成(feature-spec-generator)と異なり、既存SPECをロードして変更された部分のみ更新する。変更履歴管理、diff表示、影響範囲分析を提供する。 "SPEC修正", "SPEC更新", "機能変更", "FR追加", "FR修正" 等のリクエストでトリガーされる。 <example> user: "006-srs-review-systemの復習間隔をSM-2からLeitnerに変更して" assistant: "feature-spec-updaterを使用して既存SPECを修正します" </example> <example> user: "005 SPECにオフラインモードFRを追加して" assistant: "feature-spec-updaterを使用してFRを追加します" </example>

buddypia0

Machine Learning

System Designer

C4モデル（Level 1 System Context + Level 2 Container）を使用してシステム設計図を生成するスキル。Mermaid C4図による視覚化を提供する。

buddypia0

Machine Learning

Cissp Tutor

Schema-based CISSP tutoring with analogies mapped to student background

BudgieBird0

Machine Learning

Nerc Tutor

Schema-based NERC RC exam tutoring with analogies mapped to student background

BudgieBird0

Machine Learning

Teach Me Testing

Multi-session learning companion that teaches testing progressively through 7 structured sessions with state persistence

thewoolleyman0

Machine Learning

Senior Qa

Use for THB-BBL risk-tiered validation planning, regression prevention, and release verification for changed behavior across request analysis, team assignment, exports, and scheduler flows. Do not use for implementation-only tasks.

therealityreport0

Machine Learning

Learn

Pipeline retrospective and pattern extraction for continuous learning. Use after every pipeline completion to capture lessons.

the-own-lab0

Machine Learning

Evolution Session

Independent evolution session executor — the "night shift" of the double-helix mechanism. Reads overnight-plan.md work orders, forges tools from pain ledger signals, and binds results into retrieval-methodology routing. Pure L3 toolmaking in a clean context. KEYWORDS: evolve, evolution, overnight, nightly, forge, L3, pain ledger, work order, toolmaking

themarshs0

Machine Learning

Skill Judge — 评价 + 锻造

Evaluate and forge Agent Skills into production-ready components. Two modes: (1) Whole-Skill evaluation — score a Skill against 8 dimensions (120 points), grade A-F. (2) Element Dissection — decompose Skills into atomic elements, score individually, detect combinations, compare against existing system, and forge精华 into precise locations. Use when reviewing, auditing, improving, or absorbing community Skills/Agents/Rules. Triggers: skill evaluation, skill review, skill audit, code review of skills, absorb community asset, forge skill elements.

themarshs0

Machine Learning

Knowledge Evolution

Hooks-driven instinct learning framework. Turns spiral iteration experience into atomic instincts with confidence decay, clustering into Rules/Skills/Agents.

themarshs0

Machine Learning

My Delivery Master

通用交付编排技能。用于复杂任务的能力发现、技能准入、原子化计划、分阶段执行与证据化验收；按约束启用模型运行时、可移植性、API/UI质量等控制模块。

theBulishMan0

Machine Learning

Threat Modeling And Security Triage

Model trust boundaries, abuse cases, sensitive data flows, and security mitigations, then classify residual risk. Use when creating THREAT_MODEL.md, SECURITY_REVIEW.md, SUPPLY_CHAIN.md, or deciding whether security findings are blocking, accepted, or mitigated.

thebobhuff0

Machine Learning

Option Scoring

MUST run before recommending when 2+ implementation options are compared. Triggers: '選択肢を並べて', '案を比較', '設計適合度', 'tradeoff', 'which approach'. Scores each option on weighted axes (climpt fixed spine + 2–3 doc-cited derived), outputs a matrix with fit % and DQ rule for w=2 violations, picks the highest non-DQ option with a single reason.

tettuan0

Machine Learning

Speckit Clarify

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

campeis0

Machine Learning

Gsd Set Profile

Switch model profile for GSD agents (quality/balanced/budget/inherit)

onelee850

Machine Learning

Refactoring Expert

Expert in code refactoring patterns, SOLID principles, design patterns, and incremental improvement.

CarGDev0

Machine Learning Skills | Skills Pool