api-generator
Frontend API Generator
Core Principles
- Recon → Plan → Execute - Always analyze repository before generating code
- Incremental changes only - Never destructive refactors
- Generate only supported infrastructure - Match existing project patterns
- Ask when uncertain - Use Interview Mode for ambiguity
- User must approve plan - No execution without confirmation
Phase 1: Project Recon (MANDATORY)
Before generating any code, analyze the repository to determine project architecture.
A. Language & Type System
- Detect if project is TypeScript or JavaScript
- Detect existing type systems:
- TypeScript interfaces/types
- zod / io-ts / yup schemas
More from hubvue/skills
prompt-interviewer
Senior Prompt Engineer and Prompt Interviewer that interviews users to refine and complete their prompts through structured analysis and iterative questioning. Use when a user has an initial prompt but needs help refining it for better LLM performance: (1) When a prompt lacks clarity or context, (2) When constraints or boundaries are missing, (3) When output formats or quality criteria are undefined, (4) When there are ambiguities or conflicting requirements
15deep-learning
Systematically learn and explain the principles of a library, framework, module, function, or code path. Use when a user wants to understand overall architecture, module responsibilities, execution flow, call chains, core data structures, design tradeoffs, implementation details, or interview-ready explanations from source code.
5context-probe
Minimal Context Sentinel Installer (All-Layers Broadcast). Installs a hard Context Sentinel rule into EVERY detected rule file to force assistant to append a sentinel token to every response. Use when (1) Installing context monitoring via /context-probe, (2) Checking installation status via /context-probe status, (3) Uninstalling via /context-probe off.
4dev-spec
Spec-driven development workflow skill for product requirement intake, engineering research, technical planning, task breakdown, implementation, testing, bugfix loop, and engineering review. Use when a user wants to run or continue a structured software delivery workflow with explicit specs, durable artifacts, and iterative implementation/testing loops.
3prompt-minifier
Minify verbose prompts into semantically equivalent minimal prompts while preserving behavior. Supports configurable output modes (prompt-only or prompt + compression report).
3skills-workflow
Interactive skills workflow for chaining multiple skills where the output of step i becomes the input of step i-1. Use when you need to: (1) Chain multiple skills together in a specific order, (2) Pass outputs between skills as inputs, (3) Execute complex multi-step workflows with traceability, (4) Run skills in dry-run mode before execution, (5) Debug or audit multi-skill workflows
3