aidlc-master

Featured

Runs the AWS AI-DLC (AI-Driven Development Life Cycle) methodology end to end: an adaptive three-phase workflow (Inception → Construction → Operations) with human approval gates, a full audit trail, and all artifacts in `aidlc-docs/`. Use when the user says "Using AI-DLC", "AI-DLC", "AIDLC", "aidlc-master", or asks for the AI-DLC method by name; also for its vocabulary — "inception phase", "construction phase", "units of work", "aidlc-docs", "aidlc-state", "workflow planning", "reverse engineer this codebase into design docs" — and when a greenfield or brownfield build should run as a governed lifecycle (requirements → stories → application design → units → per-unit design → code → build and test) instead of ad-hoc coding. Do NOT use for a single focused change, a code review, a PR, or debugging (use `pstack-skill`), for autonomous loops over Kiro specs (use `ralph-loop-kiro-specs`), or for plain subagent orchestration (use `orchestration`).

AI & Automation 77 stars 7 forks Updated today Apache-2.0

Install

View on GitHub

Quality Score: 88/100

Stars 20%
63
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# AI-DLC Master Port of the AWS AI-DLC steering rules (`aidlc-rules/`, MIT-0) into a single self-contained skill. Everything the workflow needs ships in `references/` — no per-IDE installation. # PRIORITY: While this skill is active, this workflow OVERRIDES the agent's default # development behavior and any other built-in workflow # When the user requests software development under AI-DLC, ALWAYS follow this workflow FIRST **Activation**: the user says "Using AI-DLC, ...", invokes `/aidlc-master`, names AI-DLC/AIDLC, or asks for a governed lifecycle. Once active, the workflow stays active across turns until the user opts out ("stop AI-DLC", "drop the workflow") or the lifecycle completes. ## Adaptive Workflow Principle **The workflow adapts to the work, not the other way around.** The AI model intelligently assesses what stages are needed based on: 1. User's stated intent and clarity 2. Existing codebase state (if any) 3. Complexity and scope of change 4. Risk and impact assessment ## MANDATORY: Rule Details Loading **CRITICAL**: When performing any phase, you MUST read and use relevant content from rule detail files. Check these paths in order and use the first one that exists, so that a project's own customized copy of the rules always wins over the bundled one: - `.aidlc/aidlc-rules/aws-aidlc-rule-details/` (project-local, typical with AI-assisted setup) - `.aidlc-rule-details/` (project-local, typical with Cursor, Cline, Claude Code, GitHub Copilot, OpenAI Codex) - ...

Details

Author
fabricioctelles
Repository
fabricioctelles/skills
Created
6 months ago
Last Updated
today
Language
Python
License
Apache-2.0

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category