发现 Skills

Code quality analysis skill for tbdflow, covering smells, maintainability, and refactoring guidance.

Pull request authoring standards — structured descriptions, linking issues, providing test evidence, and writing good summaries. Reference when creating or describing pull requests.

Critical review (min. 5 findings). Modes: code, audit, plan. Use when: "review", "critical review", "code review", "plan review", "audit review".

Orchestrates GSD v1 end-to-end (map → discuss → plan → execute → verify) with three intelligence modes. Default: checkpoint mode (ask on architecture only). Full-auto for overnight batch runs across multiple projects. Always uses Opus-grade reasoning — never generic defaults. Use when: "gsd orchestrate", "autonomous gsd run", "over night optimize", "batch optimize projects", "gsd-orchestrate".

Master smart contract security best practices to prevent common vulnerabilities and implement secure Solidity patterns. Use when writing smart contracts, auditing existing contracts, or implementing security measures for blockchain applications.

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.

Create professional infographics using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Integrates research-lookup and web search for accurate data. Supports 10 infographic types, 8 industry styles, and colorblind-safe palettes.

Roleplay as the "Armchair Executioner" — a maximally destructive, minimally accountable peer reviewer. Use when the user asks for a peer review, wants to stress-test a paper, or invokes /mean-reviewer.

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

Strategic advisor for founders. Facilitates deep thinking through Socratic dialogue, identifies blind spots, assesses risks and opportunities, and provides guidance on strategic decisions using Extended Thinking for complex analysis.

Faz code review completo da branch — padroes, imports do design system, testes e requisitos do Jira. Usar antes de abrir PR.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Derive core problem hypotheses and root causes from customer journey analysis and customer experience research data, validate the hypotheses through problem-validation interviews, and identify business value.

Implement and debug accessible, high-performance carousel and slider components using CSS Scroll Snap and WAI-ARIA patterns.

First Principles Framework (FPF) — transdisciplinary reasoning architecture for systems engineering, knowledge coordination, and mixed human/AI teams. Use when the user mentions FPF, first principles, bounded contexts, SoTA packs, concept unification, assurance calculus, or FPF Parts A-K. Not for general philosophy or Agile unrelated to FPF.

Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.

PostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.

Connects Mux mobile (Expo web/native) to an isolated dev-server sandbox with deterministic port setup, backend pairing, and Chrome MCP interaction. Use when implementing or validating mobile features against a sandboxed Mux backend.

Use when the task requires automating a real browser. This skill is MCP-only and uses `playwright-ext` (`@playwright/mcp --extension`) to attach to the browser extension session.

MUST be used whenever fixing correctness and error handling issues in a Dune app. This skill finds AND fixes bugs, missing error states, unhandled rejections, and edge-case failures — it does not just report them. Triggers: correctness, error handling, bug fix, edge case, crash, unhandled, null, undefined, empty state, loading state, error boundary, try catch, async error, useEffect cleanup, type guard, runtime error, robustness.

Control Philips Hue lights/scenes via the OpenHue CLI.

Risk control verification — call the evaluate_risk/portfolio_risk tools to perform quantitative risk checks

Professional resume builder with PDF export, ATS optimization, and analysis capabilities. Use when users need to (1) Create new resumes from scratch, (2) Customize/tailor existing resumes for specific roles, (3) Analyze resumes and provide improvement recommendations, (4) Convert resumes to ATS-friendly PDF format. Supports chronological, functional, and combination resume formats.