AI Product Kit

AI Product Kit is a doc-first toolkit designed for product managers and cross-functional teams, offering end-to-end guidance from discovery to launch.

Looking for the Chinese version? See README_CN.md.

📁 Repository Structure

ROOT/
├── AGENTS.md                   # Single source of truth for agent guardrails and workflow rules
├── skills/                     # Canonical lifecycle Skills and reusable guides
│   ├── aipk_init_project/      # Project bootstrap workflow plus AGENTS enforcement scripts
│   ├── aipk_requirements/      # Research, requirements authoring, reviews, change management
│   ├── aipk_design/            # Script-driven automation (panel mapping, asset diffs, etc.)
│   ├── aipk_development/       # Engineering playbooks and implementation templates
│   ├── aipk_operations/        # Growth, launch prep, and post-launch tooling
│   ├── aipk_skill_generate/    # Standards for creating or extending Skills
│   └── aipk_tool_prompts/      # Reusable AI prompt blocks referenced by other Skills
├── docs/                       # Legacy landing pages and shared standards referenced by Skills
├── mcp/                        # Archived automation service source, documentation, and tests
├── bin/                        # Distribution-ready CLI entry points (e.g., `ai-product-kit.js`)
├── tools/                      # Release automation such as `publish-package.sh`
├── scripts/                    # Helper utilities invoked by Skills and templates
├── todos/                      # Working drafts and in-progress notes
├── test/                       # Automated coverage for CLI helpers and scripts
└── README*.md                  # Repository entry points (English + Chinese)

Documentation Standards: All documentation follows the standards defined in docs/guide_writing_standard/SKILL.md, covering document structure, content organization, formatting, and template writing guidelines.

🎯 Who This Helps

• Product managers – start in skills/aipk_requirements for market analysis, user research, and PRD templates.
• Designers – leverage skills/aipk_design for automated panel/asset workflows, and pair it with the requirements skills for context.
• Engineers – use skills/aipk_development for architecture notes and delivery checklists.
• QA teams – align with the acceptance criteria defined in skills/aipk_requirements and leverage skills/aipk_development checklists for validation.
• Operators & growth – explore skills/aipk_operations for launch, engagement, and optimization plans.

📚 Core Capabilities

• Discovery & analysis – market studies, user interviews, competitor reviews.
• Product planning – PRD templates, backlog framing, prioritization.
• Design systems – UI/UX principles, prompt and content guidelines.
• Delivery enablement – architecture references, API design, dev workflows.
• Quality practice – test plans, automation strategy, regression tooling.
• Release & operations – go-to-market, post-launch metrics, growth loops.

⚙️ Environment Requirements

• Node.js 18+ – required to run npx ai-product-kit@latest from ROOT.
• npm 9+ – provides access to the scoped package and carries your authenticated session, so the sync command can download the latest Skill bundle.

🛠️ Usage Guide

1. Sync the latest Skills from ROOT (call the explicit CLI so future additional binaries don’t break the command):

   npx ai-product-kit@latest ai-product-kit

   The command copies the newest Skill bundle (templates, scripts, and GURU_AI.md files) into your working tree. Rerun it whenever you pull updates or start a new branch.

2. Prime your agent by sending the following sentence after the sync completes:

   init project based on .claude/skill/int_project

   This prompt loads the init-project Skill documented in AGENTS.md, ensuring Codex/Cursor follows the canonical workflow every time.

3. Review the synced artifacts – open the relevant skills/aipk_<lifecycle>/SKILL.md, verify the bundled checklists and GURU_AI.md instructions match your task, and log any new deliverables in the tracker specified by AGENTS.md before editing documents.

Once the agent acknowledges the Skill load, continue with your usual prompts (for example, “Prepare the PRD for feature X using the AI Product Kit template.”)

🚀 Quick Start

Agents already know where each Skill lives because the mappings are declared in AGENTS.md. Use prompts like these to get moving quickly:

1. Draft a PRD for the AI-assisted recording feature using the latest AI Product Kit template.

2. Review the current launch checklist and tell me what’s missing for the beta cut.

3. Summarize the deltas between @panel_diff_v2 and the current AI Product Kit design standard, then propose fixes.

📦 Release Guide

1. Login to npm – run npm whoami to verify the session before releasing.

2. Execute the script – from ROOT run:

   tools/publish-package.sh --version <version>

   Optionally pass --tag beta or --dry-run; the script performs the necessary validations (auth checks, npm pack --dry-run, Skill sync) before publishing.

3. Follow the prompts – the script syncs Skills, runs npm pack --dry-run, and then publishes with npm publish --access public.

Ensure you have the necessary permissions on the npm org before running the script.

📄 License

This project is distributed under the MIT License.