aws-samples/aidlc
gen-ai/claude-code-skills-aidlc-workflows/SKILL.md
AI-Driven Development Life Cycle workflow. Use when user says "Using AI-DLC...", "AI-DLC로...", "Start AI-DLC", "start development", "build an app", "create a project", or wants intelligent adaptive software development workflow with requirements analysis, design, and implementation phases.
$ install --global
skillsauthnpx skillsauth add aws-samples/aws-kr-startup-samples aidlcInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 20, 2026, 3:18 PM1.5s1 file scanned
SKILL.md
- name:
- aidlc
- description:
- AI-Driven Development Life Cycle workflow. Use when user says "Using AI-DLC...", "AI-DLC로...", "Start AI-DLC", "start development", "build an app", "create a project", or wants intelligent adaptive software development workflow with requirements analysis, design, and implementation phases.
- disable-model-invocation:
- false
- user-invocable:
- true
- argument-hint:
- [task-description]
- allowed-tools:
- Read, Write, Edit, Glob, Grep, Bash, Task, AskUserQuestion, TodoWrite
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:
- Read
.claude/skills/aidlc/aidlc-workflows/aidlc-rules/aws-aidlc-rules/core-workflow.md- This is your PRIMARY instruction set - Read
.claude/skills/aidlc/aidlc-workflows/aidlc-rules/aws-aidlc-rule-details/common/process-overview.md - Read
.claude/skills/aidlc/aidlc-workflows/aidlc-rules/aws-aidlc-rule-details/common/session-continuity.md - Read
.claude/skills/aidlc/aidlc-workflows/aidlc-rules/aws-aidlc-rule-details/common/content-validation.md - 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:
- Check if
aidlc-docs/aidlc-state.mdexists - 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
- Read
- 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
- Adaptive Execution: Only execute stages that add value
- Transparent Planning: Always show execution plan before starting
- User Control: User can request stage inclusion/exclusion
- Progress Tracking: Update
aidlc-docs/aidlc-state.mdwith executed and skipped stages - Complete Audit Trail: Log ALL user inputs in
aidlc-docs/audit.mdwith timestamps - 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.md
Application 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
Related Skills
openclaw/openclaw-secret-scanning-maintainer
development
VerifiedTrustedCommunity
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
357,764SKILL.mdUpdated Apr 15, 2026
openclaw/openclaw-release-maintainer
development
VerifiedTrustedCommunity
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
357,764SKILL.mdUpdated Apr 10, 2026
openclaw/openclaw-qa-testing
development
VerifiedTrustedCommunity
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
357,764SKILL.mdUpdated Apr 10, 2026
openclaw/openclaw-parallels-smoke
development
VerifiedTrustedCommunity
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.
357,764SKILL.mdUpdated Apr 10, 2026