aidlc

AI-DLC (AI-Driven Development Life Cycle) workflow orchestration. Use when user says 'Using AI-DLC' or needs structured software development with requirements, design, and implementation through Inception, Construction, and Operations phases.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "aidlc" with this command: npx skills add konippi/aidlc-skill/konippi-aidlc-skill-aidlc

AI-DLC Core Workflow

AI-DLC is an adaptive software development workflow that intelligently tailors itself to your specific needs.

Activation Triggers

Use this skill when:

  • User request starts with "Using AI-DLC, ..."
  • Complex software development requiring structured planning
  • Projects needing requirements analysis, design, and implementation

MANDATORY: Rule Details Loading

CRITICAL: When performing any phase, you MUST read and use relevant content from references/ directory.

Common Rules: ALWAYS load at workflow start:

  • Load references/common/process-overview.md for workflow overview
  • Load references/common/session-continuity.md for session resumption
  • Load references/common/content-validation.md for validation requirements
  • Load references/common/question-format-guide.md for question formatting

The Three-Phase Lifecycle

INCEPTION PHASE - Planning & Architecture

Purpose: Determines WHAT to build and WHY

StageExecutionDetails
Workspace DetectionALWAYSreferences/inception/workspace-detection.md
Reverse EngineeringCONDITIONALreferences/inception/reverse-engineering.md
Requirements AnalysisALWAYSreferences/inception/requirements-analysis.md
User StoriesCONDITIONALreferences/inception/user-stories.md
Workflow PlanningALWAYSreferences/inception/workflow-planning.md
Application DesignCONDITIONALreferences/inception/application-design.md
Units GenerationCONDITIONALreferences/inception/units-generation.md

CONSTRUCTION PHASE - Design, Implementation & Test

Purpose: Determines HOW to build it

StageExecutionDetails
Functional DesignCONDITIONALreferences/construction/functional-design.md
NFR RequirementsCONDITIONALreferences/construction/nfr-requirements.md
NFR DesignCONDITIONALreferences/construction/nfr-design.md
Infrastructure DesignCONDITIONALreferences/construction/infrastructure-design.md
Code GenerationALWAYSreferences/construction/code-generation.md
Build and TestALWAYSreferences/construction/build-and-test.md

OPERATIONS PHASE - Placeholder

Purpose: How to DEPLOY and RUN it (future expansion)

See references/operations/operations.md for details.

Key Principles

  1. Adaptive Execution: Only execute stages that add value
  2. Flexible Depth: Adjust depth based on complexity (minimal/standard/comprehensive)
  3. Human-in-the-Loop: Explicit approval required at every critical decision point
  4. Complete Audit Trail: Log ALL interactions with ISO 8601 timestamps
  5. User Control: User can request stage inclusion/exclusion

Workflow Initialization

  1. Create aidlc-docs/aidlc-state.md using references/common/state-template.md
  2. Create aidlc-docs/audit.md using references/common/audit-template.md
  3. Display welcome message from references/common/welcome-message.md (once per workflow)
  4. Execute Workspace Detection
  5. Proceed through phases based on workflow plan

Directory Structure

<WORKSPACE-ROOT>/
├── [project-specific structure]
│
└── aidlc-docs/
    ├── inception/
    │   ├── plans/
    │   ├── reverse-engineering/
    │   ├── requirements/
    │   ├── user-stories/
    │   └── application-design/
    ├── construction/
    │   ├── plans/
    │   ├── {unit-name}/
    │   └── build-and-test/
    ├── operations/
    ├── aidlc-state.md
    └── audit.md

Stage Execution Pattern

All stages follow the Planning → Generation pattern:

Part 1: Planning

  1. Create plan with checkboxes for each step
  2. Generate context-appropriate questions using [Answer]: tags
  3. Collect user answers
  4. Analyze answers for ambiguities
  5. Create follow-up questions if ambiguities found
  6. Wait for explicit approval

Part 2: Generation

  1. Load approved plan
  2. Execute each step sequentially
  3. Mark checkboxes [x] immediately after completion
  4. Generate artifacts
  5. Present completion message
  6. Wait for explicit approval

Critical Rules

  • NEVER proceed without explicit user approval
  • ALWAYS log interactions in audit.md
  • NEVER summarize user input in audit log - capture complete raw input
  • Application code goes to workspace root, NEVER to aidlc-docs/
  • ALWAYS use multiple choice question format with [Answer]: tags
  • ALWAYS validate content before file creation

Reference Files

For detailed guidance, load the appropriate reference file:

Common

  • references/common/process-overview.md
  • references/common/question-format-guide.md
  • references/common/content-validation.md
  • references/common/depth-levels.md
  • references/common/terminology.md
  • references/common/session-continuity.md
  • references/common/error-handling.md
  • references/common/overconfidence-prevention.md
  • references/common/ascii-diagram-standards.md
  • references/common/state-template.md
  • references/common/audit-template.md
  • references/common/welcome-message.md
  • references/common/workflow-changes.md

Inception

  • references/inception/workspace-detection.md
  • references/inception/reverse-engineering.md
  • references/inception/requirements-analysis.md
  • references/inception/user-stories.md
  • references/inception/workflow-planning.md
  • references/inception/application-design.md
  • references/inception/units-generation.md

Construction

  • references/construction/functional-design.md
  • references/construction/nfr-requirements.md
  • references/construction/nfr-design.md
  • references/construction/infrastructure-design.md
  • references/construction/code-generation.md
  • references/construction/build-and-test.md

Operations

  • references/operations/operations.md

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

openclaw-version-monitor

监控 OpenClaw GitHub 版本更新,获取最新版本发布说明,翻译成中文, 并推送到 Telegram 和 Feishu。用于:(1) 定时检查版本更新 (2) 推送版本更新通知 (3) 生成中文版发布说明

Archived SourceRecently Updated
Coding

ask-claude

Delegate a task to Claude Code CLI and immediately report the result back in chat. Supports persistent sessions with full context memory. Safe execution: no data exfiltration, no external calls, file operations confined to workspace. Use when the user asks to run Claude, delegate a coding task, continue a previous Claude session, or any task benefiting from Claude Code's tools (file editing, code analysis, bash, etc.).

Archived SourceRecently Updated
Coding

ai-dating

This skill enables dating and matchmaking workflows. Use it when a user asks to make friends, find a partner, run matchmaking, or provide dating preferences/profile updates. The skill should execute `dating-cli` commands to complete profile setup, task creation/update, match checking, contact reveal, and review.

Archived SourceRecently Updated