Plugins

Effort-aware prompt routing for Claude Code. Classifies prompt complexity and injects effort guidance.

모델 성능 모니터링 및 데이터 드리프트 감지를 수행합니다. PSI, KS Test 기반 알림 시스템을 제공합니다.

Opt a project into down-tier model delegation: installs a standalone .claude/rules/ file telling Claude to route well-specified data and coding tasks to a cheaper model in a subagent, keeping judgment-heavy work in the main loop. Optional pre-shaped .claude/agents/ definitions and an optional agent-state feedback layer.

머신러닝 모델 학습 및 선택을 수행합니다. XGBoost, LightGBM, Random Forest 등 주요 알고리즘을 지원합니다.

Build a polished, production Telegram bot around a model / HF Space / API — a 7-phase playbook (Discover→Design→Menus→Data→Backend→Build→Deploy), a 32-entry gotchas catalog, and real starter module templates. (Private repo — installs for the owner.)

Run model creation and training as a product: training pipeline architecture (Argo/Kubeflow, trigger taxonomy), MLflow experiment/registry standards, distributed-training topology selection (Ray/Dask/Spark), Ray on K8s operations, notebook-to-production golden path, and fine-tuning strategy (prompt vs RAG vs PEFT).

Security vetting gate for new AI models: before any open-weights or hosted model is integrated into the Claude Code harness or local dev system, verify weights provenance and integrity, file-format safety, license and data terms, the serving path, and stage its agentic access.

The Excel spine. Designs and structures spreadsheet models before formulas are written and builds the analytical engines behind them: model-standards (tab structure, conventions, reference and lookup layer, executive output tabs), scenario-engine (three scenarios, sensitivity and tornado, risk-adjusted value), model-audit (formula audit plus assumption registry, board-ready), dcf-structure, bridge-waterfall, tam-sam-som-model, competitive-benchmarking-grid and portfolio-prioritization-matrix. Calls the xlsx engine for the actual build; thinking-toolkit and execution-toolkit reference it for numbers.

from Dieshen/claude_marketplace

Modern Python best practices. Use when creating new Python projects, and writing Python scripts, or migrating existing projects from legacy tools.

Keep your coding agent up to date with the latest web best practices

AI-powered .NET modernization and upgrade assistant. Helps upgrade .NET Framework and .NET applications to the latest versions of .NET.

Skills for scaffolding pages, components, API hooks, and reviewing code in the ModernStores Next.js/Turborepo project

from kerinin/claude-modes

The modular monolith applied pragmatically: one deployable unit, strictly bounded modules with public APIs, isolated data, and TypeScript-ecosystem boundary enforcement. Composable with your own conventions.

Manages module-level architecture documentation in the simplified arc42 LITE format with MDRs and Agents.md files.

Build complete Proteos modules interactively: discovery → entities + permissions → pages/lists/menus → live preview (pro module serve) → hooks/actions/components → deploy.

Spec-driven TDD framework: brainstorm -> provable completeness gate -> RED-before-GREEN -> review, with a codebase knowledge graph, self-healing memory, token governance, and human-gated writes. Local-first, Apache-2.0.

Apply Rob Fitzpatrick's 'The Mom Test' framework to customer discovery work.

Orientation and entry point for working on a Momen project. Load first for any Momen app task — designing or changing the data model, UI, server-side action flows, permissions, payments, or data bindings, or reading runtime logs — then follow it to the right capability. For Momen projects only; not generic programming help.

Set up a local Monata simulation environment with pixi, a local circuit-tool conda channel, and ngspice plus OpenVAF verification.

Run your monday CRM in plain language. Build a pipeline from scratch, start the day with a ranked deal briefing, spin up a forecast dashboard, audit board health, clean up messy data in bulk, and turn meeting notes into deal updates. Every skill writes back into monday as a real update, doc, or dashboard. Built on the official monday MCP connector.

Main entry point — onboards you, builds your profile, and routes to the right skill.

Google Ads, Meta Ads — campaign setup, optimization, ROAS tracking.

Content pipeline with authenticity audit, headline impact matrix, and substance scoring.

Deep diagnosis when business is stuck — root cause, not symptoms. Includes execution coaching.

Find and validate profitable business ideas with competitive intelligence.

Revenue tracking, unit economics, financial reports — Stripe integration.

Manage atomic project learnings (~/.smtm/projects/{slug}/learnings.jsonl). Auto-loaded into every other money-* skill so the agent gets smarter across sessions instead of cold-starting.

24/7 autonomous operations with health scoring, canary monitoring, and safety guardrails.