🎯

drift-detection

🎯Skill

from rsmdt/the-startup

VibeIndex|
What it does

Monitors and identifies deviations in machine learning model performance, alerting developers to potential data drift or concept drift that could impact model accuracy.

πŸ“¦

Part of

rsmdt/the-startup(36 items)

drift-detection

Installation

Install ScriptRun install script
curl -fsSL https://raw.githubusercontent.com/rsmdt/the-startup/main/install.sh | sh
Add MarketplaceAdd marketplace to Claude Code
/plugin marketplace add rsmdt/the-startup
Install PluginInstall plugin from marketplace
/plugin install start@the-startup
Install PluginInstall plugin from marketplace
/plugin install team@the-startup
πŸ“– Extracted from docs: rsmdt/the-startup
8Installs
-
AddedFeb 4, 2026

Skill Details

SKILL.md

Overview

The Agentic Startup

Ship faster. Ship better. Ship with The Agentic Startup.

Release

Downloads

GitHub Stars

Mentioned in Awesome Claude Code

---

Table of Contents

  • [πŸ€– What is The Agentic Startup?](#-what-is-the-agentic-startup)
  • [πŸš€ Quick Start](#-quick-start)
  • [πŸ“– The Complete Workflow](#-the-complete-workflow)
  • [🎯 Which Command Should I Use?](#-which-command-should-i-use)
  • [πŸ“¦ Plugins](#-plugins)
  • [🎨 Output Styles](#-output-styles)
  • [πŸ“Š Statusline](#-statusline)
  • [🎯 Philosophy](#-philosophy)
  • [πŸ“š Documentation](#-documentation)

---

πŸ€– What is The Agentic Startup?

The Agentic Startup is a spec-driven development framework for Claude Code. Create comprehensive specifications before coding, then execute with parallel specialist agentsβ€”Y Combinator energy meets engineering discipline.

Key Features:

  • Native Claude Code Integration β€” Marketplace plugins with zero configuration
  • Spec-Driven Development β€” PRD β†’ SDD β†’ Implementation Plan β†’ Code
  • Parallel Agent Execution β€” Multiple specialists work simultaneously
  • Quality Gates β€” Built-in validation at every stage

Installation

Requirements: Claude Code v2.0+ with marketplace support

```bash

curl -fsSL https://raw.githubusercontent.com/rsmdt/the-startup/main/install.sh | sh

```

This installs the core plugins, configures the default output style, and sets up the [statusline](#-statusline) with a customizable config file.

Manual Installation

```bash

# Add The Agentic Startup marketplace

/plugin marketplace add rsmdt/the-startup

# Install the Start plugin (core workflows)

/plugin install start@the-startup

# (Optional) Install the Team plugin (specialized agents)

/plugin install team@the-startup

```

After installation:

```bash

# (Optional) Create project governance rules

/start:constitution # Auto-enforced during specify, implement, review

# Switch output styles anytime

/output-style start:The Startup # High-energy, fast execution (default)

/output-style start:The ScaleUp # Calm confidence, educational

```

---

πŸš€ Quick Start

Create a specification and implement it:

```bash

# Create a specification

/start:specify Add user authentication with OAuth support

# Execute the implementation

/start:implement 001

```

That's it! You're now using spec-driven development.

---

πŸ“– The Complete Workflow

The Agentic Startup follows spec-driven development: comprehensive specifications before code, ensuring clarity and reducing rework.

All Commands at a Glance

```

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”

β”‚ SETUP (optional) β”‚

β”‚ β”‚

β”‚ /start:constitution β–Ί Create project governance rules β”‚

β”‚ (auto-enforced in BUILD workflow) β”‚

β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

β”‚

β–Ό

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”

β”‚ BUILD (primary flow) β”‚

β”‚ β”‚

β”‚ /start:specify ────► Create specs (PRD + SDD + PLAN) β”‚

β”‚ β”‚ ↳ Constitution checked on SDD β”‚

β”‚ β–Ό β”‚

β”‚ /start:validate ───► Check quality (3 Cs framework) β”‚

β”‚ β”‚ ↳ Constitution mode available β”‚

β”‚ β–Ό β”‚

β”‚ /start:implement ──► Execute plan phase-by-phase β”‚

β”‚ β”‚ ↳ Constitution + drift enforced β”‚

β”‚ β–Ό β”‚

β”‚ /start:review ─────► Multi-agent code review β”‚

β”‚ β”‚ ↳ Constitution compliance checked β”‚

β”‚ β–Ό β”‚

β”‚ /start:document ───► Generate/sync documentation β”‚

β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

β”‚

β–Ό

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”

β”‚ MAINTAIN (as needed) β”‚

β”‚ β”‚

β”‚ /start:analyze ────► Discover patterns & rules β”‚

β”‚ β”‚

β”‚ /start:refactor ───► Improve code (preserve behavior) β”‚

β”‚ β”‚

β”‚ /start:debug ──────► Fix bugs (root cause analysis) β”‚

β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

```

Step-by-Step Walkthrough

#### Step 1: Create Your Specification

```bash

/start:specify Add real-time notification system with WebSocket support

```

This creates a specification directory with three documents:

```

docs/specs/001-notification-system/

β”œβ”€β”€ product-requirements.md # What to build and why

β”œβ”€β”€ solution-design.md # How to build it technically

└── implementation-plan.md # Executable tasks and phases

```

The spec cycle may take 15-30 minutes. Claude will research your codebase, ask clarifying questions, and produce comprehensive documents. The process naturally involves multiple back-and-forth exchanges.

#### Step 2: Handle Context Limits (Resume Pattern)

Large specifications may approach Claude's context window limits. When this happens:

```bash

# Start a new conversation and resume where you left off

/start:specify 001

```

The resume pattern:

  • Pass the spec ID (e.g., 001) instead of a description
  • Claude reads the existing spec files and continues from there
  • You can reset context as many times as needed
  • Each document (PRD β†’ SDD β†’ PLAN) can be completed in separate sessions if needed

Pro tip: If Claude suggests "you may want to reset context", do it! The quality of output improves with fresh context.

#### Step 3: Validate Before Implementation

```bash

/start:validate 001

```

This quality gate checks:

  • Completeness - All sections filled, no missing details
  • Consistency - No contradictions between documents
  • Correctness - Requirements are testable and achievable

Validation is advisoryβ€”it provides recommendations but doesn't block you.

#### Step 4: Execute the Implementation

```bash

/start:implement 001

```

Claude will:

  1. Parse the implementation plan
  2. Execute phases sequentially (with your approval between phases)
  3. Run tests after each task
  4. Use parallel agents within phases for speed

Large implementations may also need context resets. Simply run /start:implement 001 again in a fresh conversationβ€”Claude tracks progress in the spec files.

#### Step 5: Review and Ship

```bash

/start:review

```

Four parallel specialists review your code:

  • πŸ”’ Security - Authentication, authorization, input validation
  • ⚑ Performance - Query optimization, memory management
  • ✨ Quality - Code style, design patterns, maintainability
  • πŸ§ͺ Tests - Coverage gaps, edge cases

---

🎯 Which Command Should I Use?

Decision Tree

```

What do yo

More from this repository10

πŸͺ
rsmdt-the-startupπŸͺMarketplace

Comprehensive agentic framework for Claude Code

🎯
implementation-planning🎯Skill

Generates a detailed, step-by-step implementation roadmap for software development projects, breaking down technical specifications into actionable tasks and milestones.

🎯
api-contract-design🎯Skill

Designs and validates API contract specifications, ensuring clear interface definitions, request/response schemas, and adherence to best practices before implementation.

🎯
task-delegation🎯Skill

Intelligently distributes complex tasks among specialized AI agents, breaking down work into optimized subtasks with clear ownership and parallel execution potential.

🎯
bug-diagnosis🎯Skill

Diagnoses software bugs by systematically analyzing error logs, code context, and potential failure points to identify root causes and recommend precise fixes.

🎯
architecture-selection🎯Skill

Helps developers systematically evaluate and select the most appropriate software architecture for a project based on specified requirements, constraints, and best practices.

🎯
requirements-elicitation🎯Skill

Extracts and clarifies product requirements through systematic questioning, stakeholder interviews, and comprehensive requirement documentation, ensuring clear and precise project scope definition.

🎯
safe-refactoring🎯Skill

Automatically analyzes and performs code refactoring with minimal risk, ensuring code structure is improved while maintaining existing functionality and preventing potential runtime errors.

🎯
code-quality-review🎯Skill

Performs comprehensive automated code quality analysis, identifying potential issues, style violations, and improvement opportunities across different programming languages and frameworks.

🎯
implementation-verification🎯Skill

Verifies the correctness and quality of code implementations by running comprehensive tests, checking against original specifications, and identifying potential implementation discrepancies or errors.