Un cycle Brainstorm → Spec validée → Plan à cases à cocher → TDD strict → Review de conformité, conçu pour les devs qui construisent des SaaS pilotés par IA (générateurs, agents, outils no-code) en HTML/CSS/JS vanilla ou Node/Express, avec intégrations multi-fournisseurs (Anthropic, OpenAI, Gemini, Mistral). Exemples d'usage : "ajoute une fonctionnalité X à mon générateur", "intègre un nouveau fournisseur IA", "refonds ce module"
Run a full virtual product team from chat: PM → SA → Coder → QA → DevOps → Marketing. @mention roles, TASK-NNN tickets, and gated SDLC stages from backlog to deployed — built for solo founders who need a shippable process without hiring.
Before you write code, kill the causes of rework. A phase-gate skill that runs a pre-implementation diagnosis (clarify requirements, success criteria, non-goals, hidden risks) and sets up the dev environment (toolchain check, repo init, dependency/secret/config templates, DB/API contract, folder layout). Each gate must pass before moving on. Delivers a diagnosis report, a stack-selection doc, and a ready-to-build foundation to hand off to implementation.
Turn a rough skill idea into a structured blueprint: named, prompted, differentiated, and listing-ready.
Build a bilingual digital-product or productized-service system covering offer validation, a seven-day build plan, payment and delivery, client intake, content repurposing, launch copy, tracking, and measurable experiments.
Turn a new marketplace SKU launch from "listed and waiting" into a 30-day campaign with pre-launch prep, launch-day push, day 3-14 review and sales velocity, day 15-30 ranking consolidation, day 30+ steady-state handoff, and post-launch review. This download skill helps plan platform, budget, target rank, PPC / organic engine, review seed plan, A/B tests, handoff, and relaunch lessons.
Turn product ideas into implementation-ready plans before your AI agent writes a single line of code. AI Development Director produces structured requirements, architecture decisions, database schemas, implementation tasks, coding-agent prompts, review checklists, and launch checklists. This is not a code-generation prompt. It is the planning system that runs before code generation.
Launching doesn't have to mean failure. People might have reached their goal... and then stopped at one step. Reveal 1,000 visits → 100 signups → 10 activations → 3 payments, then isolate the next question.