jaan.to

Give soul to your workflow.

jaan.to handles repetitive work—PRDs, specs, test plans—so you focus on clarity, judgment, and customer empathy. Clear inputs, clean outputs, calm boundaries.

---

What is "jaan"?

"jaan" is a Persian word meaning "soul" or "life." When you say "jaan-e man" — "my soul" — you're expressing the deepest form of care.

jaan.to means "giving soul to something" — a person, a project, a product. It's the act of breathing life into work that would otherwise feel mechanical.

---

The Problem

The same request produces different outcomes depending on how you ask. Most people blame the model. The harder truth: humans are the inconsistent part.

• Request a feature → one architectural style
• Request a bug fix → different style
• Rules in your head. Standards that only appear when frustrated
• A definition of "done" that changes with your energy level

The Solution

jaan.to is a skill system that standardizes execution.

Rules written down, not in your head. Standards that exist before frustration. A definition of "done" that doesn't change with energy levels.

Four Pillars

Pillar	Without jaan.to	With jaan.to
Commands, not prompts	Ad-hoc requests with unpredictable output	Procedures with predictable results
Roles, not cleverness	One person doing everything	Different roles create different thinking
Memory, not vibes	Rules in your head	Documented in LEARN.md files
Checks, not hope	Skip steps when tired	Enforced approval checkpoints

---

Quick Start

# 1. Clone jaan.to into your project
git clone https://github.com/jaan-to/claude-code.git

# 2. Open in Claude Code and run a skill
/jaan-to-pm-prd-write "user authentication feature"

# 3. Output appears at:
# .jaan-to/outputs/pm/spec/user-auth/prd.md

---

Features

Feature	Description
Skills	Slash commands that generate consistent outputs
Context	Your team and tech context (languages, frameworks, norms)
Learning	System improves from your feedback via LEARN.md
Hooks	Automated validation and prompts
Trust	Write only to .jaan-to/, preview before save, approval checks

---

Available Skills

Now Available

Command	Role	Description	Output
/jaan-to-pm-prd-write	PM	Generate Product Requirements Document	.jaan-to/outputs/pm/spec/{slug}/prd.md
/jaan-to-data-gtm-datalayer	DATA	Generate GTM tracking code	.jaan-to/outputs/data/gtm/{slug}/tracking.md

Coming Soon (35+ Skills)

PM (Product Manager)

Command	Description
/jaan-to-pm-decision-brief	1-page decision record with options and risks
/jaan-to-pm-north-star	North star metric with drivers and guardrails
/jaan-to-pm-scope-slice	MVP vs Later slicing with milestones
/jaan-to-pm-release-review	Post-release review with KPI deltas
/jaan-to-pm-story-write	User stories with Given/When/Then

DEV (Development)

Command	Description
/jaan-to-dev-tech-plan	Technical approach with architecture and risks
/jaan-to-dev-test-plan	Dev-owned test plan with fixtures and mocks
/jaan-to-dev-api-contract	OpenAPI contract with payloads and errors
/jaan-to-dev-pr-review	PR review pack with risky files and hints
/jaan-to-dev-ship-check	Pre-ship checklist with Go/No-Go

QA (Quality Assurance)

Command	Description
/jaan-to-qa-test-cases	Test cases from acceptance criteria
/jaan-to-qa-test-matrix	Risk-based matrix across states and devices
/jaan-to-qa-bug-triage	Dedupe, severity, and repro hints
/jaan-to-qa-regression-runbook	Step-by-step regression runbook
/jaan-to-qa-release-signoff	Go/No-Go summary with evidence

UX (User Experience)

Command	Description
/jaan-to-ux-flow-spec	Flow spec with states and edge cases
/jaan-to-ux-microcopy-write	Microcopy pack with labels and errors
/jaan-to-ux-research-plan	Research plan with method and timeline
/jaan-to-ux-heuristic-review	Heuristic review with severity and fixes
/jaan-to-ux-competitive-review	Competitive teardown with opportunities

DATA (Analytics)

Command	Description
/jaan-to-data-sql-query	Ad-hoc SQL from natural language
/jaan-to-data-event-spec	GA4-ready event/param specification
/jaan-to-data-metric-spec	Metric definition with formula
/jaan-to-data-funnel-review	Funnel baseline with hypotheses

GROWTH (SEO + Content)

Command	Description
/jaan-to-growth-seo-brief	SEO content brief with keywords and structure
/jaan-to-growth-ab-plan	A/B test plan with hypothesis and metrics
/jaan-to-growth-landing-copy	Landing page copy with value props

---

How It Works

Every skill follows a two-phase workflow with human approval:

┌─────────────────────────────────────────────────────────┐
│  PHASE 1: Analysis (Read-Only)                          │
│  - Read context files                                   │
│  - Gather requirements                                  │
│  - Plan structure                                       │
└─────────────────────────────────────────────────────────┘
                          │
                          ▼
┌─────────────────────────────────────────────────────────┐
│  HARD STOP: Human Approval                              │
│  "Ready to generate? [y/n]"                             │
└─────────────────────────────────────────────────────────┘
                          │
                          ▼
┌─────────────────────────────────────────────────────────┐
│  PHASE 2: Generation (Write)                            │
│  - Generate output                                      │
│  - Quality check                                        │
│  - Preview                                              │
│  - Write to .jaan-to/                                   │
└─────────────────────────────────────────────────────────┘

Why this matters: No accidental writes. You review before anything happens.

---

Project Structure

.claude/
└── skills/              # Skill definitions (SKILL.md, LEARN.md, template.md)

jaan-to/
├── config.md            # Global settings
├── context/             # Your context (tech.md, team.md, integrations.md)
├── boundaries/          # Trust rules
└── hooks/               # Automation triggers

.jaan-to/
└── outputs/             # All generated outputs (safe zone)
    └── {role}/{domain}/{slug}/

docs/                    # User documentation
roadmaps/                # Vision and roadmap

---

Configuration

Context (Your Environment)

Customize jaan.to to know your tech and team:

<!-- jaan-to/context/tech.md -->
## Languages
- Backend: Python 3.11, FastAPI
- Frontend: TypeScript, React 18

## Infrastructure
- Cloud: AWS (ECS, RDS, S3)
- Database: PostgreSQL 15

<!-- jaan-to/context/team.md -->
## Team Size
- 2 engineers, 1 PM, 1 designer

## Sprint
- 2 weeks, story points, Monday start

Trust

All skills write only to .jaan-to/ by default. You can extend trusted paths in jaan-to/boundaries/trust-paths.md.

---

Documentation

Document	Description
Getting Started	First skill in 5 minutes
Concepts	Core ideas explained
Skills Reference	All available commands
Creating Skills	Build your own skills
Configuration	Settings and context
Vision	Philosophy and architecture
Roadmap	What's coming

---

This Is Not Replacing Teams

jaan.to standardizes execution and reduces waste. The repetitive parts get automated:

• Formatting PRDs
• Writing test matrices
• Generating boilerplate

The human parts stay human:

You Handle	jaan.to Handles
Defining the right problem	Formatting the PRD
Making trade-off decisions	Generating test cases
Understanding customers	Writing boilerplate
Knowing when "done" means done	Following templates

---

Impact

Metric	Improvement
First Draft Time	60-80% reduction
Decision Time	40% more time for decisions
Test Planning	60% automated

---

Contributing

jaan.to is open source. To extend:

1. Read Creating Skills
2. Use /to-jaan-skill-create to scaffold a new skill
3. Submit a PR

---

License

MIT License. See LICENSE for details.

---

Give soul to your workflow.