AI-Ready Documentation Generator
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md and install @user_f2df858a/docs-for-ai-dev into your AI assistant.
About this skill
Problem
When asking LLMs to implement software from requirements, failures often come from broken traceability: features, interfaces, tasks, error handling, and state storage are disconnected; field types and enum strategies are vague, so the AI guesses. This skill generates an AI-consumable documentation set for desktop, web, API, CLI, library, and mobile projects.
How It Works
It starts with Step 0: project type detection, selects a matching stack profile, then emits structured docs:
- D01 to D09 universal docs covering overview, feature design, architecture, API design, development guide, task lists, error handling, state persistence, and an AGENTS.md entry point.
- U01 to U03 for UI projects, including design system, pixel-level visual specs, and interaction flows.
- Optional docs for security/performance, deep analysis, multi-phase tasks, or i18n.
The core principle is full-chain traceability: every feature must have complete data model interfaces in D02, then map to tasks, testable identifiers, interface registrations, and state ownership. The skill emphasizes complete annotations, consistent enum strategy, design token mappings, and deployment completeness, reducing any, placeholder types, and ambiguous descriptions.
Boundaries
This fits engineering projects where requirements, architecture, and tasks will be executed by AI, especially when interface contracts, configuration, error codes, and artifacts must be explicit. It is not a marketing copywriter and cannot infer missing business facts; if the source requirements lack critical constraints, human review is still required. For UI projects, page states, breakpoints, accessibility, and design tokens must be available to produce usable pixel-level specs.
Use Cases
- After receiving a new product requirement, compile goals, data models, interfaces, and acceptance criteria into task docs for AI implementation.
- When building a web admin UI, turn page states, breakpoints, component specs, and interaction flows into pixel-level UI specifications for AI coding.
- Before refactoring an API service, verify that endpoint registrations, error codes, state persistence, and deployment rollback stay consistent in the docs.
- When maintaining a localized desktop app, include auth, credential management, performance targets, and i18n structure in the dev documentation set.
Best For
- Engineers who turn product requirements into AI-executable dev docs and need consistent interfaces, tasks, and state ownership chain across docs.
- Architects maintaining front-end pages and backend services who need design tokens, endpoint registrations, and deployment constraints documented in the doc set.
- Indie developers using AI agents to build desktop apps who need full config, error handling, and release artifact details set.
- Senior developers auditing AI-generated code who require traceable docs without placeholder types or broken references across the documentation set files.
Related Skills
Creates themed learning sites by generating flashcards, lessons, quizzes, index, and progress pages into a deployable website.
End-to-end mathematical optimization modeling with Gurobi and Python, covering data validation, code generation, solving, result analysis, and iterative revision.
Executes an Eversheet Web CDP login using externally supplied baseUrl, username, and password, then verifies the page reaches a logged-in home state.
Clarify product goals, user flows, pages, data, and permissions, then output an implementation-ready development prompt and lightweight spec.