Design e Frontend

Esta skill de red-teaming adversário ataca código, sistemas, estratégias e planos para descobrir falhas de segurança, lógicas, suposições incorretas e riscos não considerados. Ela é ativada quando o usuário deseja que seu trabalho seja rigorosamente desafiado.

Avoid unnecessary useRef in React. Prefer HTML standard features, declarative libraries, state, or custom hooks. Use when writing or reviewing React components.

Use when designing REST endpoints, defining error envelopes, setting a versioning or deprecation policy, choosing pagination shape, adding idempotency to mutations, reviewing API contracts, or when two services need a stable interface between them.

(Industry standard: Review and Critique Pattern) Primary Use Case: Iterative generation paired with adversarial review, continuing until an 'Approved' verdict is reached. Orchestrated adversarial review loop. Use when: research, designs, architectures, or decisions need to be reviewed by red team agents (human, browser, or CLI). Iterates in rounds of research → bundle → review → feedback until app

Guidelines for shell commands. Avoid `cat`, `find`, `grep`, `head`, and `tail`; prohibit `rm` (use `trash` instead). Use when invoking shell commands via Bash.

Digestão de restrição in silico, detecção de extremidades compatíveis, design de primers (modelos de Tm) e simulação de gel.

LLM generation pipeline expertise covering prompt engineering, structured output validation, queue-based async processing, SSE real-time progress, and multi-mode generation strategies. Covers Vercel AI SDK, LangChain, LangGraph, vector databases, and RAG patterns. Trigger keywords: AI generation, LLM pipeline, prompt engineering, structured output, Zod schema, BullMQ, SSE, RAG, vector database, em

Use this skill to capture a human phase-gate sign-off through chat rather than requiring the user to manually edit the gate markdown file. Prompts the user with the artifact path, collects a work-item URL (REQ / ticket / CR) as the non-trivial acknowledgment, validates the URL shape against the ticket system configured in `config/tools.json`, and writes the signed gate file at `.claude/sdlc/gates/

Systematic unmet-needs discovery engine that maps gaps between market demand and existing solutions with quantified opportunity scores. Use when: find opportunities, unmet needs, market gaps, opportunity discovery, what should we build, where is the whitespace.

Use this skill when the user runs /start, says "start", "enable the SDLC workflow", "I want to build", "I want to fix", "set up", "get started", or otherwise signals they want to activate or re-enable the SDLC workflow. Handles three distinct paths based on marker state — fresh install (opt-in activation), re-enable after suspension (reconciliation), and already-enabled (hand off to /plan). Power

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs, when task are finished - requires running verification commands and confirming output before making any success claims; evidence before assertions always

BRIDGE Development Pipeline — a multi-agent pipeline that transforms business requirements into delivered technical solutions with client-ready deliverables. Built for development agencies, consultancies, fractional engineering teams, and any team that needs to go from requirements to delivery faster. MUST trigger on: any development request, meeting transcripts, requirement summaries, emails or c