lf-discovery
Você é um especialista em produto e engenharia de software, atuando como facilitador de discovery de features em times AI-native. Seu papel é conduzir uma entrevista estruturada para coletar todo o contexto necessário antes de qualquer linha de código ser escrita.
Execute as fases abaixo em ordem, sem pular etapas. Seja direto e eficiente — faça uma pergunta por vez quando possível. Nunca invente informações: campos não respondidos viram ⚠️ Ponto em aberto.
O argumento passado pelo usuário (se houver) é: $ARGUMENTS
FASE 0 — Identificação da feature
Se $ARGUMENTS não estiver vazio:
- Use como nome/descrição inicial da feature.
- Confirme: "Vou iniciar o discovery para: [nome]. Confirma ou ajusta a descrição?"
Se $ARGUMENTS estiver vazio:
- Pergunte: "Qual feature você quer desenvolver? Descreva em 1-3 frases."
Aguarde confirmação antes de continuar.
More from twinfo-io/lifters-skills
lf-specs
Generates specs.md and wps.md after the UX/UI team delivers Figma screens. Reads the latest briefing-tech.vN.md, interactively collects one Figma URL per screen identified in the briefing, fetches design context via Figma MCP, creates briefing-tech.v(N+1).md with a Section 16 (Figma design references) and inline screen links, then generates specs.md (SPEC-XX per domain with 12 sections each and Figma URLs inline) and wps.md (work packages with dependency map). Run after /lf-new-feature once the UX/UI team has shared Figma screen URLs. Accepts optional feature folder name as argument.
16lf-new-feature
Generates the technical briefing (briefing-tech.vN.md, 15 sections) from an existing discovery.md. Can be called multiple times to iterate versions (v0 → v1 → v2). If briefing-ux.vN.md exists, uses it to populate personas and UX sections without repeating questions. Use when the user asks for /lf-new-feature or needs a technical briefing for a feature. Run /lf-specs after the UX/UI team delivers Figma screens to generate specs.md and wps.md.
16lf-design-system
Connects to Figma via MCP Server, extracts typography, colors, spacing, border radius, shadows and all design token definitions, and generates specs/design-system.md — the official design system source of truth for the project. Prompts for design system name and Figma URL if not provided as arguments. Use when the user runs /lf-design-system or wants to create or update the project's design system from Figma.
15lf-briefing-ux
Generates the UX/UI briefing from an existing discovery.md — personas, screen navigation map, per-screen specs with states and ASCII wireframes, user flows, microcopy, display rules, and visual references. Designed for the UX/UI team to start prototyping without a full technical briefing. Use after /lf-discovery and before /lf-new-feature. Produces briefings/briefing-ux.v0.md (or vN if iterating).
14lf-exec
Starts the execution of a specific work package (WP-XX) from a generated wps.md. Interactively lists available spec folders under specs/ and pending work packages (excluding completed ones), guides the developer through project update and branch creation (features/initials/semantic_name or current branch), then fires the execution prompt for the selected WP. No arguments required.
12lf-git-sync
Pulls and synchronizes all git submodules with their remotes. Detects the git root, lists all submodules, pulls the main repo, then for each submodule: pulls if on a tracked branch or runs git submodule update if in detached HEAD state. Handles merge conflicts, network errors, and missing remotes gracefully. Shows a before/after summary with branch and commit state per repo. Use when you need to sync a monorepo with submodules after a teammate pushed changes.
4