Process Library

The Babysitter Process Library is a comprehensive collection of 2,000+ pre-built process definitions (and growing) that you can use immediately or customize for your specific needs. This extensive library covers software development, business operations, scientific research, and dozens of specialized domains.

In Plain English

Think of the Process Library like a cookbook with 2,000+ recipes.

Just like how a cookbook has recipes for Italian, Mexican, Japanese, and French cuisine - the Process Library has "recipes" for building web apps, mobile apps, APIs, security audits, and much more.

You don't need to read the whole cookbook. Just tell Babysitter what you want to make:

"Build me a REST API" → Babysitter picks the right recipe automatically

"Use the TDD methodology" → You pick a specific recipe

Each recipe includes:

Ingredients (inputs you provide)

Steps (phases of work)

Quality checks (tests to ensure it's done right)

Approval points (places where you review before continuing)

Quick Start: Using the Library

Most users never need to browse the library directly. Just describe what you want:

/babysitter:call build a user authentication system with login, registration, and password reset

Babysitter automatically finds and combines the right processes. Want a specific methodology?

/babysitter:call with TDD methodology, create a REST API for managing tasks

That's it! See the sections below for details on what's available.

What is the Process Library?

The Process Library provides ready-to-use orchestration workflows for virtually any task you might encounter. Each process is:

Battle-tested: Designed with best practices and quality gates built-in
Composable: Can be combined with other processes to create complex workflows
Customizable: Extend or modify any process to match your requirements
Self-documenting: Includes clear inputs, outputs, and execution flow

Instead of writing orchestration logic from scratch, you can leverage these pre-built processes and focus on what matters: your actual work.

How Babysitter Uses the Process Library

When you describe a task to Babysitter, the agent automatically selects the most relevant processes from the library and adapts them to your specific needs. This happens in several ways:

Automatic Process Selection

Simply describe what you want to accomplish in natural language:

Use babysitter to build a Next.js app with authentication and PostgreSQL

Babysitter will:

Identify relevant processes (e.g., nextjs-fullstack-app, jwt-authentication, database-setup)
Combine and adapt them to your requirements
Execute the orchestrated workflow with quality gates

Explicit Process Selection

You can also request a specific process by name:

Use babysitter with the tdd-quality-convergence process to implement user authentication

Or:

Use babysitter with the devin methodology to build a REST API

Mix and Match

For complex tasks, Babysitter intelligently combines multiple processes:

Use babysitter to create a microservices architecture with:
- GraphQL gateway
- Kubernetes deployment
- Monitoring and alerting

This might pull from graphql-api-apollo, kubernetes-setup, monitoring-setup, and cicd-pipeline-setup processes, adapting each to work together coherently.

Customizing for Your Use Case

You can also modify existing processes or provide additional context:

Use babysitter with the security-audit process but focus specifically on
OWASP Top 10 vulnerabilities and include PCI-DSS compliance checks

The agent will take the base process and adapt it to your specific requirements.

Library Structure

The Process Library is organized into four main areas. Click any link to view the source code:

Area	Description	Link
methodologies/	Development methodologies (TDD, Agile, Devin, etc.)	Browse →
gsd/	Get Shit Done workflows	Browse →
specializations/	Domain-specific processes (30+ categories)	Browse →
tdd-quality-convergence	Featured TDD workflow	View →

Specializations Sub-Structure

Category	Description	Link
Development Processes	Web, mobile, DevOps, AI, security, etc.	Browse →
domains/business/	Finance, HR, Marketing, Sales, etc.	Browse →
domains/science/	Physics, Chemistry, Engineering, etc.	Browse →
meta/	Process creation and validation	Browse →

Browsing and Discovering Processes

Asking Claude

The easiest way to discover processes is to ask Claude:

What processes are available for web development?

Show me security-related processes in the babysitter library

Claude can browse the process library and recommend the best match for your needs.

Process Naming Convention

Process files follow a consistent naming pattern:

feature-name.js - The process definition
README.md - Category documentation
examples/ - Example inputs and usage
agents/ - Specialized agents for the category

Finding the Right Process

Start with the category that matches your domain
Review the README.md in that category for an overview
Check the JSDoc at the top of each .js file for inputs/outputs
Look at examples/ for sample usage patterns

Categories Overview

Development Processes (680+ processes)

Category	Processes	Description	Browse
web-development	66	Full-stack web development, frameworks, deployment	→
algorithms-optimization	50	Algorithm implementation, performance tuning	→
ai-agents-conversational	44	LLM applications, RAG, multi-agent systems	→
cryptography-blockchain	38	Smart contracts, DeFi, cryptographic protocols	→
security-research	37	Penetration testing, vulnerability research	→
robotics-simulation	35	ROS2, simulation, autonomous systems	→
performance-optimization	35	Profiling, optimization, benchmarking	→
network-programming	35	Protocols, distributed systems, networking	→
game-development	35	Game engines, mechanics, production	→
cli-mcp-development	35	CLI tools, MCP servers, developer tooling	→
mobile-development	31	iOS, Android, React Native, Flutter	→
embedded-systems	31	Firmware, drivers, real-time systems	→
sdk-platform-development	30	SDKs, APIs, platform engineering	→
programming-languages	30	Compilers, interpreters, language design	→
gpu-programming	30	CUDA, compute shaders, parallel processing	→
fpga-programming	30	HDL, synthesis, hardware design	→
code-migration-modernization	30	Legacy modernization, framework upgrades	→
security-compliance	29	Security standards, compliance automation	→
desktop-development	28	Electron, native apps, cross-platform	→
ux-ui-design	26	Design systems, accessibility, prototyping	→
technical-documentation	26	API docs, guides, documentation systems	→
software-architecture	25	System design, patterns, architecture reviews	→
qa-testing-automation	25	Test automation, quality assurance	→
devops-sre-platform	25	CI/CD, infrastructure, observability	→
data-science-ml	23	ML pipelines, model training, MLOps	→
data-engineering-analytics	23	Data pipelines, analytics, ETL	→
product-management	22	Roadmaps, specifications, product strategy	→
meta	10	Process creation, validation, tooling	→

Business Domains (430+ processes)

Browse all business domains →

Category	Processes	Description	Browse
decision-intelligence	33	Decision frameworks, analysis models	→
legal	28	Contract analysis, compliance, legal ops	→
operations	26	Business process optimization	→
business-strategy	26	Strategic planning, competitive analysis	→
venture-capital	25	Due diligence, portfolio management	→
supply-chain	25	Logistics, inventory, procurement	→
sales	25	Sales processes, CRM workflows	→
public-relations	25	Communications, media relations	→
marketing	25	Campaigns, analytics, content strategy	→
logistics	25	Distribution, routing, fulfillment	→
knowledge-management	25	Documentation, wikis, knowledge bases	→
human-resources	25	Recruiting, onboarding, HR processes	→
finance-accounting	25	Financial analysis, reporting, auditing	→
entrepreneurship	25	Startup workflows, business planning	→
digital-marketing	25	SEO, PPC, social media, analytics	→
customer-experience	25	CX design, feedback loops, journey mapping	→
project-management	5	Project planning, tracking, delivery	→

Science and Engineering (550+ processes)

Browse all science domains →

Category	Processes	Description	Browse
scientific-discovery	168	Research methodologies, reasoning patterns	→
quantum-computing	27	Quantum algorithms, circuit design	→
mechanical-engineering	26	CAD, simulation, manufacturing	→
computer-science	25	Theory, algorithms, formal methods	→
civil-engineering	25	Structural analysis, infrastructure	→
chemical-engineering	25	Process design, reaction engineering	→
biomedical-engineering	25	Medical devices, biomechanics	→
automotive-engineering	25	Vehicle systems, ADAS, EV	→
aerospace-engineering	25	Flight systems, propulsion, avionics	→
physics	24	Simulation, modeling, analysis	→
nanotechnology	24	Nanofabrication, characterization	→
mathematics	24	Proofs, modeling, computation	→
materials-science	24	Material characterization, discovery	→
industrial-engineering	24	Process optimization, operations research	→
environmental-engineering	24	Environmental modeling, sustainability	→
electrical-engineering	24	Circuit design, signal processing	→
bioinformatics	12	Genomics, proteomics, computational biology	→

Social Sciences and Humanities (150+ processes)

Browse social sciences domains →

Processes for research methodologies, analysis frameworks, and academic workflows in social sciences, humanities, and interdisciplinary fields.

Example Processes by Category

Web Development

Browse all web-development processes →

Process	Description	Source
nextjs-fullstack-app	Complete Next.js application	View
graphql-api-apollo	GraphQL API with Apollo	View
jwt-authentication	JWT auth implementation	View
e2e-testing-playwright	Playwright E2E testing	View
micro-frontend-module-federation	Micro-frontend architecture	View
accessibility-audit-remediation	WCAG compliance	View
docker-containerization	Docker deployment	View

AI Agents and Conversational

Browse all ai-agents-conversational processes →

Process	Description	Source
multi-agent-system	Multi-agent orchestration	View
advanced-rag-patterns	Advanced RAG implementation	View
langgraph-workflow-design	LangGraph workflows	View
conversational-memory-system	Long-term memory for agents	View
function-calling-agent	Tool-using agents	View
agent-evaluation-framework	Agent testing and eval	View
llm-observability-monitoring	LLM monitoring setup	View

Security Research

Browse all security-research processes →

Process	Description	Source
binary-reverse-engineering	Binary analysis	View
exploit-development	Exploit writing workflow	View
fuzzing-campaign	Fuzzing setup and execution	View
malware-analysis	Malware analysis workflow	View
network-penetration-testing	Network pentesting	View
capture-the-flag-challenges	CTF solving workflow	View
bug-bounty-workflow	Bug bounty methodology	View

DevOps and SRE

Browse all devops-sre-platform processes →

Process	Description	Source
kubernetes-setup	Kubernetes cluster setup	View
cicd-pipeline-setup	CI/CD pipeline creation	View
monitoring-setup	Observability stack	View
incident-response	Incident management	View
disaster-recovery-plan	DR planning and testing	View
slo-sli-tracking	SLO/SLI implementation	View
secrets-management	Secrets management setup	View

Scientific Discovery

Browse all scientific-discovery processes →

Process	Description	Source
hypothesis-formulation-testing	Scientific method	View
causal-inference	Causal analysis	View
bayesian-probabilistic-reasoning	Bayesian reasoning	View
experiment-design-reasoning	Experiment planning	View
literature-review-synthesis	Literature review	View
reproducible-research-pipeline	Reproducibility	View
systems-thinking	Systems analysis	View

Using a Pre-Built Process

Recommended: Just use /babysitter:call <request> - it selects the right process automatically:

/babysitter:call build a Next.js app with authentication, PostgreSQL database, and Vercel deployment

Babysitter will find the nextjs-fullstack-app process and configure it based on your request.

Methodologies Reference

The library includes 38+ development methodologies that can be applied to any project. Browse all methodologies →

Core Methodologies

Methodology	Description	Best For	Source
devin	Plan -> Code -> Debug -> Deploy with autonomous iteration	Full feature implementation	View
ralph	Simple iterative loop until task completion	Persistent tasks with unclear scope	View
plan-and-execute	Detailed planning phase followed by execution	Complex, well-defined features	View
tdd-quality-convergence	TDD with iterative quality scoring	High-quality, tested code	View
spec-driven-development	Executable specifications drive implementation	Enterprise, governance-heavy projects	View

Agile and Iterative

Methodology	Description	Best For	Source
agile	Sprint-based iterative development	Team-based projects	View
scrum	Full Scrum implementation with ceremonies	Scrum teams	View
kanban	Continuous flow with WIP limits	Continuous delivery	View
extreme-programming	XP practices (pair programming, TDD)	High-quality code	View
feature-driven-development	Feature-centric development	Large codebases	View

Architecture and Design

Methodology	Description	Best For	Source
top-down	Architecture-first development	New systems, clear requirements	View
bottom-up	Component-first development	Exploratory, uncertain requirements	View
domain-driven-design	DDD strategic and tactical patterns	Complex business domains	View
event-storming	Collaborative domain discovery	Domain modeling	View
evolutionary	Incremental architecture evolution	Legacy modernization	View

Specialized Approaches

Methodology	Description	Best For	Source
graph-of-thoughts	Multi-path reasoning exploration	Complex problem solving	View
adversarial-spec-debates	Red team/blue team specification	Critical systems	View
consensus-and-voting-mechanisms	Multi-agent consensus building	Distributed decisions	View
state-machine-orchestration	State-based workflow management	Complex state transitions	View
build-realtime-remediation	Real-time error detection and fixing	CI/CD pipelines	View

GSD (Get Shit Done) Workflows

Browse GSD workflows →

Workflow	Purpose	Source
new-project	Project initialization with vision capture	View
discuss-phase	Capture implementation preferences	View
plan-phase	Generate verified task plans	View
execute-phase	Parallel task execution with commits	View
verify-work	User acceptance testing	View
audit-milestone	Milestone completion verification	View
map-codebase	Brownfield project analysis	View
iterative-convergence	Quality-gated development loop	View

Customizing Processes

Extending an Existing Process

import { process as baseProcess } from './nextjs-fullstack-app.js';

export async function process(inputs, ctx) {
  // Add pre-processing
  const enhancedInputs = {
    ...inputs,
    additionalChecks: true,
    customConfig: myConfig
  };

  // Run base process
  const result = await baseProcess(enhancedInputs, ctx);

  // Add post-processing
  await ctx.task(myCustomValidation, result);

  return {
    ...result,
    customData: myCustomData
  };
}

Composing Multiple Processes

import { process as planPhase } from './gsd/plan-phase.js';
import { process as executePhase } from './gsd/execute-phase.js';
import { process as tddConvergence } from './tdd-quality-convergence.js';

export async function process(inputs, ctx) {
  // Planning with GSD
  const plan = await planPhase(inputs, ctx);

  // Execute with TDD quality gates
  const implementation = await tddConvergence({
    ...inputs,
    plan: plan.tasks,
    targetQuality: 90
  }, ctx);

  // Verify with GSD
  const verification = await executePhase({
    ...inputs,
    tasks: implementation.artifacts
  }, ctx);

  return { plan, implementation, verification };
}

Modifying Process Parameters

Most processes accept configuration through inputs:

{
  "feature": "User authentication",
  "targetQuality": 95,
  "maxIterations": 10,
  "requirements": [
    "Support OAuth2",
    "Include MFA"
  ],
  "constraints": [
    "Must use existing user table",
    "No breaking API changes"
  ]
}

Quick Reference: All Categories

Category	Count	Focus Area	Browse
scientific-discovery	168	Research reasoning patterns	→
web-development	66	Full-stack web development	→
algorithms-optimization	50	Algorithm implementation	→
ai-agents-conversational	44	LLM and agent development	→
cryptography-blockchain	38	Blockchain and crypto	→
security-research	37	Security research and testing	→
robotics-simulation	35	Robotics and simulation	→
performance-optimization	35	Performance tuning	→
network-programming	35	Network and protocols	→
game-development	35	Game development	→
cli-mcp-development	35	CLI and MCP tools	→
decision-intelligence	33	Decision frameworks	→
mobile-development	31	Mobile app development	→
embedded-systems	31	Embedded and firmware	→
sdk-platform-development	30	SDK development	→
programming-languages	30	Language implementation	→
gpu-programming	30	GPU and parallel computing	→
fpga-programming	30	FPGA design	→
code-migration-modernization	30	Code modernization	→
security-compliance	29	Security compliance	→
legal	28	Legal operations	→
desktop-development	28	Desktop applications	→
quantum-computing	27	Quantum computing	→
mechanical-engineering	26	Mechanical engineering	→
ux-ui-design	26	UX/UI design	→
technical-documentation	26	Documentation	→
software-architecture	25	Architecture design	→
qa-testing-automation	25	Test automation	→
devops-sre-platform	25	DevOps and SRE	→
data-science-ml	23	Machine learning	→
data-engineering-analytics	23	Data engineering	→
product-management	22	Product management	→
meta	10	Process tooling	→

Best Practices

Choosing the Right Process

Match your domain: Start with the specialization that matches your work
Check the methodology: Consider which methodology fits your project style
Review inputs carefully: Understand what configuration options are available
Read the examples: Look at example inputs in the examples/ directories

Customization Tips

Start simple: Use processes as-is before customizing
Layer changes: Extend rather than modify base processes
Preserve breakpoints: Keep human approval gates in critical paths
Test incrementally: Validate customizations with small inputs first

Quality Considerations

Use quality convergence: Processes with quality scoring help ensure high standards
Enable breakpoints: Human review catches issues early
Compose methodologies: Combine TDD with your domain process for better results
Track iterations: Monitor how many iterations processes require

FilesExpand file tree

process-library.md

Latest commit

History