v1.13.0 — Apache 2.0 — ES / EN / PT

Stop Improvising.
Start Delivering.

The first specification-driven development framework made in and for Latin America. 72+ commands. 42 skills. 15 reasoning models. Zero vibe coding.

0
Commands
0
Skills
0
Reasoning Models
0
Quality Gates
Mandatory TDD OWASP Audit Blueprint Distillation 15 Reasoning Models Anthropic Skills 2.0 4 Estimation Models CodeRAG Stack Migration UI Contracts API Contracts Doctor Command Skills Marketplace Multi-role Debate Nyquist Validation Living Documentation 7 Specialized Agents

The 3 Iron Laws

Non-negotiable principles that guarantee quality in every line of code.

🧪

TDD

All code requires tests.
RED → GREEN → REFACTOR
No exceptions.

🔍

Debugging

Root cause first.
Reproduce → Isolate → Understand → Fix → Verify

Verification

Evidence before assertions.
"Tests pass" > "I think it works"

6-Phase Pipeline

Each phase with mandatory quality gates. No shortcuts.

01
📝

Specify

Gherkin specifications + auto-generated DBML schema. The foundation of everything.

02

Clarify

Auto-QA detects ambiguities. Resolution before moving forward.

03
🏗

Plan

Technical blueprint with project constitution validation.

04
🧩

Breakdown

TDD decomposition with parallelism markers for maximum efficiency.

05

Implement

RED → GREEN → REFACTOR cycle in Docker. Automated and verified.

06
🔎

Review

7-dimension peer review: performance, security, architecture and more.

Don Cheli vs. The Market

Direct comparison with the most popular frameworks in the ecosystem.

Metric BMAD
42K ⭐
GSD
39K ⭐
spec-kit
82K ⭐
Don Cheli
Commands ~20~80~10 72+
Reusable skills ~15~15~6 42
Reasoning models 15
Automatic estimation 4 models
Formal quality gates 14 6
Mandatory TDD ✓ Iron Law
PoC Mode
OWASP Audit
Stack migration
Stub detection
UI Contracts
Nyquist Validation
Multilingual (ES/EN/PT)
Anthropic Skills 2.0 ✓ Compatible
Skill Creator
Skills Marketplace

Numbers That Speak

Real performance data, token savings and feature coverage.

Feature Coverage vs Competitors

Token Savings by Phase (Skills 3-Layer Design)

Commands by Category

Software Quality Impact

20 Unique Features

Capabilities you won't find in any other framework on the market.

🧠

15 Reasoning Models

Pre-mortem, 5 Whys, Pareto, Inversion, RLM and more.

📊

4 Estimation Models

Function Points, AI Planning Poker, COCOMO, Historical.

🧪

PoC Mode

Validation with timebox and defined success criteria.

🔬

Blueprint Distillation

Behavioral reverse engineering from existing code.

📚

CodeRAG

Reference repo indexing for retrieval-augmented generation.

🛡

OWASP Audit

All 10 OWASP categories audited with severity and fixes.

🔄

Stack Migration

Vue→React, JS→TS. Planned and safe migration.

📡

API Contracts

REST/GraphQL with retry, circuit breaker and resilience patterns.

SOLID Refactoring

Guided refactoring with metrics and structured checklist.

📖

Living Documentation

ADRs, OpenAPI and Mermaid diagrams auto-generated.

📥

Captures & Triage

Capture system with automatic 5-category classification.

🧹

Auto-generated UAT

User acceptance scripts generated from specs.

🩺

Doctor Command

Automatic diagnosis and repair of git, framework and environment.

🏭

Skill Creator

Meta-skill to create, test and improve skills iteratively.

🛒

Skills Marketplace

Integrated marketplace: Anthropic, skillsmp.com, aitmpl.com.

📜

Project Constitution

Immutable principles validated at every quality gate.

📝

Formal Pseudocode

SPARC logic reasoning phase prior to implementation.

🔍

Multi-layer Validation

8 distinct checks for specification completeness.

Multi-role Debate

PM vs Architect vs QA: adversarial debate for better decisions.

📏

Adaptive Planning

6 complexity levels with auto-detection and scaling.

6 Complexity Levels

Smart auto-detection. Each level adjusts pipeline, agents and rigor.

0

Atomic

1 file, <30 min

P

PoC

Validation, 2-4h

1

Micro

1-3 files, same day

2

Standard

Multi-file, 1-3 days

3

Complex

Multi-module, 1-2 wks

4

Product

New system, 2+ wks

7 Specialized Agents

Each agent uses the optimal model for its task. Smart orchestration.

🧠

Planner

opus
🏗

Architect

opus

Executor

sonnet
🔎

Reviewer

opus
🧪

Tester

sonnet
📖

Documenter

haiku
📊

Estimator

opus

Ready in 1 Minute

Multiple installation options. Choose the one you prefer.

# Clone and install globally git clone https://github.com/doncheli/don-cheli-sdd.git cd don-cheli-sdd && bash scripts/instalar.sh --global # Initialize in your project /dc:init
# Interactive remote installation curl -fsSL https://raw.githubusercontent.com/doncheli/don-cheli-sdd/main/scripts/instalar.sh | bash -s -- --global # Or with specific language curl -fsSL https://raw.githubusercontent.com/doncheli/don-cheli-sdd/main/scripts/instalar.sh | bash -s -- --global --lang es
# Via npm npx don-cheli-sdd init
# Download, review and execute curl -fsSL https://raw.githubusercontent.com/doncheli/don-cheli-sdd/main/scripts/instalar.sh -o instalar.sh cat instalar.sh # Review before executing bash instalar.sh --global

"We don't settle for being users; we are creators, analysts, and sometimes controlled disruptors."

— Jose Luis Oronoz Troconis, creator of Don Cheli

Anywhere, Any Way

Compatible with the main AI-powered development platforms.

💻

Claude Code

Full support: 72+ commands, 43 skills, 7 agents.

Google Gemini

14 skills and 9 workflows for Antigravity (Gemini 3.1).

🖱

Cursor IDE

Full command reference via .cursorrules.

Stop improvising.
Start delivering.

Open source. Apache 2.0. Made in Latin America for the world.

Get Started Now Join the Community