
Aidlc
- 1 installs
- 48 repo stars
- Updated April 2, 2026
- aws-samples/aws-kr-startup-samples
AI-DLC is a Claude Code skill that runs an adaptive AI-Driven Development Life Cycle workflow across inception, construction, and operations phases.
About
AI-DLC is an AI-Driven Development Life Cycle workflow skill. It runs an adaptive process across Inception (what to build and why), Construction (how to build it), and a placeholder Operations phase, executing only the stages that add value and always showing the execution plan first. A developer uses it to start a project, build an app, or expand an existing one with requirements analysis, design, and implementation. It tracks state and an audit trail in aidlc-docs/ and waits for explicit approval before each stage.
- AI-Driven Development Life Cycle: adaptive Inception, Construction, and Operations phases
- Only executes stages that add value; always shows the execution plan before starting
- Maintains session continuity and a full audit trail; never proceeds without user approval
Aidlc by the numbers
- 1 all-time installs (skills.sh)
- Ranked #14,098 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Jul 23, 2026 (Skillselion catalog sync)
aidlc capabilities & compatibility
- Capabilities
- development lifecycle · requirements analysis · code generation
- Use cases
- planning · project management · api development
- Pricing
- Free
What aidlc says it does
AI-DLC (AI-Driven Development Life Cycle) Skill
npx skills add https://github.com/aws-samples/aws-kr-startup-samples --skill aidlcAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1 |
|---|---|
| repo stars | ★ 48 |
| Last updated | April 2, 2026 |
| Repository | aws-samples/aws-kr-startup-samples ↗ |
What it does
Run an adaptive AI-DLC workflow that gathers requirements, designs, and implements an application stage by stage with approvals.
Who is it for?
Developers who want a structured, approval-gated workflow to analyze requirements, design, and implement an app.
Skip if: One-off lookups; it is a multi-stage development lifecycle, not a single answer.
When should I use this skill?
The user says 'Start AI-DLC', 'start development', 'build an app', or wants an adaptive software development workflow.
What you get
An app built through inception and construction phases with generated code, tests, and a full audit trail.
- Generated application code
- aidlc-state.md and audit.md tracking documents
By the numbers
- Three-phase workflow (Inception, Construction, Operations)
- Six-item Key Principles list
Files
AI-DLC (AI-Driven Development Life Cycle) Skill
You are now operating in AI-DLC mode - an intelligent software development workflow that adapts to your needs, maintains quality standards, and keeps you in control of the process.
User Request
$ARGUMENTS
MANDATORY: Initialization Steps
Step 1: Load Core Workflow Rules
CRITICAL: You MUST read and follow the core workflow rules:
1. Read .claude/skills/aidlc/aidlc-workflows/aidlc-rules/aws-aidlc-rules/core-workflow.md - This is your PRIMARY instruction set 2. Read .claude/skills/aidlc/aidlc-workflows/aidlc-rules/aws-aidlc-rule-details/common/process-overview.md 3. Read .claude/skills/aidlc/aidlc-workflows/aidlc-rules/aws-aidlc-rule-details/common/session-continuity.md 4. Read .claude/skills/aidlc/aidlc-workflows/aidlc-rules/aws-aidlc-rule-details/common/content-validation.md 5. Read .claude/skills/aidlc/aidlc-workflows/aidlc-rules/aws-aidlc-rule-details/common/question-format-guide.md
Step 2: Session Continuity Check
Before starting any work:
1. Check if aidlc-docs/aidlc-state.md exists 2. If EXISTS:
- Read
aidlc-docs/aidlc-state.mdto get current status - Read
aidlc-docs/audit.mdfor interaction history - Follow session-continuity.md rules to present "Welcome back" prompt
- Load all relevant artifacts from previous stages
3. If NOT EXISTS:
- This is a new project
- Display welcome message from
.claude/skills/aidlc/aidlc-workflows/aidlc-rules/aws-aidlc-rule-details/common/welcome-message.md - Proceed with Workspace Detection stage
Step 3: Execute Workflow
Follow the three-phase adaptive workflow as defined in core-workflow.md:
INCEPTION PHASE (WHAT to build and WHY):
- Workspace Detection (ALWAYS)
- Reverse Engineering (CONDITIONAL - Brownfield only)
- Requirements Analysis (ALWAYS - Adaptive depth)
- User Stories (CONDITIONAL)
- Workflow Planning (ALWAYS)
- Application Design (CONDITIONAL)
- Units Generation (CONDITIONAL)
CONSTRUCTION PHASE (HOW to build it):
- Per-Unit Loop:
- Functional Design (CONDITIONAL)
- NFR Requirements (CONDITIONAL)
- NFR Design (CONDITIONAL)
- Infrastructure Design (CONDITIONAL)
- Code Generation (ALWAYS)
- Build and Test (ALWAYS)
OPERATIONS PHASE (DEPLOY and RUN - future):
- Operations (PLACEHOLDER)
Key Principles
1. Adaptive Execution: Only execute stages that add value 2. Transparent Planning: Always show execution plan before starting 3. User Control: User can request stage inclusion/exclusion 4. Progress Tracking: Update aidlc-docs/aidlc-state.md with executed and skipped stages 5. Complete Audit Trail: Log ALL user inputs in aidlc-docs/audit.md with timestamps 6. Wait for Approval: NEVER proceed to next stage without explicit user approval
Directory Structure
All documentation goes in aidlc-docs/:
aidlc-docs/
├── inception/
├── construction/
├── operations/
├── aidlc-state.md
└── audit.mdApplication code goes in workspace root (NEVER in aidlc-docs/).
IMPORTANT
- Always load the appropriate rule detail file before executing each stage
- Rule detail files are in:
.claude/skills/aidlc/aidlc-workflows/aidlc-rules/aws-aidlc-rule-details/ - Follow the exact approval formats specified in each rule file
- Present questions in markdown files, not inline in chat
#!/bin/bash
# AI-DLC Skill Installer
# This script installs the AI-DLC skill for Claude Code
set -e
REPO_URL="https://github.com/awslabs/aidlc-workflows.git"
SKILL_DIR_NAME="aidlc"
# Colors for output
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[1;33m'
BLUE='\033[0;34m'
NC='\033[0m' # No Color
echo -e "${BLUE}"
echo "╔══════════════════════════════════════════════════════════════╗"
echo "║ AI-DLC (AI-Driven Development Life Cycle) ║"
echo "║ Skill Installer ║"
echo "╚══════════════════════════════════════════════════════════════╝"
echo -e "${NC}"
# Function to check if git is installed
check_git() {
if ! command -v git &> /dev/null; then
echo -e "${RED}Error: git is not installed. Please install git first.${NC}"
exit 1
fi
}
# Function to create directory if it doesn't exist
create_dir() {
local dir=$1
if [ ! -d "$dir" ]; then
mkdir -p "$dir"
echo -e "${GREEN}Created directory: $dir${NC}"
fi
}
# Function to install skill
install_skill() {
local base_path=$1
local skill_path="${base_path}/skills/${SKILL_DIR_NAME}"
local workflows_path="${skill_path}/aidlc-workflows"
echo -e "${YELLOW}Installing to: ${skill_path}${NC}"
# Create skill directory
create_dir "$skill_path"
# Clone or update repository
if [ -d "$workflows_path" ]; then
echo -e "${YELLOW}Repository already exists. Updating...${NC}"
cd "$workflows_path"
git pull origin main
cd - > /dev/null
else
echo -e "${YELLOW}Cloning repository...${NC}"
git clone "$REPO_URL" "$workflows_path"
fi
# Copy SKILL.md to skill directory
local skill_md_source="${workflows_path}/SKILL.md"
local skill_md_dest="${skill_path}/SKILL.md"
if [ -f "$skill_md_source" ]; then
cp "$skill_md_source" "$skill_md_dest"
echo -e "${GREEN}SKILL.md copied to: ${skill_md_dest}${NC}"
else
echo -e "${RED}Warning: SKILL.md not found in cloned repository${NC}"
fi
echo ""
echo -e "${GREEN}Installation completed successfully!${NC}"
echo -e "${BLUE}Skill installed at: ${skill_path}${NC}"
}
# Main menu
echo "Where would you like to install the AI-DLC skill?"
echo ""
echo " 1) Global installation (~/.claude/skills/aidlc)"
echo " - Available across all projects"
echo ""
echo " 2) Local installation (./.claude/skills/aidlc)"
echo " - Only available in current project"
echo ""
read -p "Enter your choice (1 or 2): " choice
check_git
case $choice in
1)
echo ""
echo -e "${BLUE}Installing globally...${NC}"
install_skill "$HOME/.claude"
echo ""
echo -e "${YELLOW}Note: Global skills are available in all your Claude Code projects.${NC}"
;;
2)
echo ""
echo -e "${BLUE}Installing locally...${NC}"
install_skill "./.claude"
echo ""
echo -e "${YELLOW}Note: Local skills are only available in this project directory.${NC}"
;;
*)
echo -e "${RED}Invalid choice. Please run the script again and select 1 or 2.${NC}"
exit 1
;;
esac
echo ""
echo -e "${GREEN}╔══════════════════════════════════════════════════════════════╗${NC}"
echo -e "${GREEN}║ Installation Complete! ║${NC}"
echo -e "${GREEN}╚══════════════════════════════════════════════════════════════╝${NC}"
echo ""
echo "To use AI-DLC, run Claude Code and type:"
echo -e " ${BLUE}/aidlc [your task description]${NC}"
echo ""
Related skills
FAQ
What are the phases?
Inception (what and why), Construction (how, including code generation and build-and-test), and a placeholder Operations phase.
Does it run every stage?
No; it uses adaptive execution and only runs stages that add value, always showing the plan and waiting for approval.