區塊鏈

Use when decisions could affect groups differently and need to anticipate harms/benefits, assess fairness and safety concerns, identify vulnerable populations, propose risk mitigations, define monitoring metrics, or when user mentions ethical review, impact assessment, differential harm, safety analysis, vulnerable groups, bias audit, or responsible AI/tech.

Use when planning with fixed deadline or target outcome, working backward from future goal to present, defining milestones and dependencies, mapping critical path, identifying what must happen when, planning product launches with hard dates, multi-year strategic roadmaps, event planning, transformation initiatives, or when user mentions "backcast", "work backward from", "reverse planning", "we need to launch by", "target date is", or "what needs to happen to reach".

Master context engineering for AI features - the skill that separates AI products that work from ones that hallucinate. Use when speccing new AI features, diagnosing underperforming AI features, or doing quality checks before shipping. Helps PMs define what context AI needs, where to get it, and what to do when it fails. Based on the 4D Context Canvas framework.

AWS Cloud Development Kit (CDK) expert for building cloud infrastructure with TypeScript/Python. Use when creating CDK stacks, defining CDK constructs, implementing infrastructure as code, or when the user mentions CDK, CloudFormation, IaC, cdk synth, cdk deploy, or wants to define AWS infrastructure programmatically. Covers CDK app structure, construct patterns, stack composition, and deployment workflows.

Build with ZK Compression on Solana using Light Protocol. Use when creating compressed tokens, compressed PDAs, or integrating ZK compression into Solana programs. Covers compressed account model, state trees, validity proofs, and client integration with Helius/Photon RPC.

This skill should be used when the user asks about "writing specs", "specs.md format", "how to write specifications", "sprint requirements", "testing configuration", "scope definition", or needs guidance on creating effective sprint specifications for agentic development.

Use when creating test plans, reviewing test coverage, defining quality gates, writing E2E test scenarios, or validating acceptance criteria. Invoked for quality assurance, testing strategy, and verification activities.

Expert en sécurité applicative pour détecter les vulnérabilités, auditer le code, et guider les bonnes pratiques de sécurité. OWASP Top 10, authentification, autorisation, cryptographie, gestion de secrets. Utiliser pour audits sécurité, reviews de code sensible, conception de features sécurisées, ou résolution de failles.

Decision validation and thinking frameworks for startup founders. Use when you need to pressure-test a decision, validate your next steps, think through strategic options, or sanity-check your approach. Triggers on phrases like "should I", "help me think through", "is this the right move", "validate my thinking", "what am I missing". Covers fundraising, customer development, runway management, prioritization, and crypto/web3 founder challenges.

Technical research methodology with YAGNI/KISS/DRY principles. Phases: scope definition, information gathering, analysis, synthesis, recommendation. Capabilities: technology evaluation, architecture analysis, best practices research, trade-off assessment, solution design. Actions: research, analyze, evaluate, compare, recommend technical solutions. Keywords: research, technology evaluation, best practices, architecture analysis, trade-offs, scalability, security, maintainability, YAGNI, KISS, DRY, technical analysis, solution design, competitive analysis, feasibility study. Use when: researching technologies, evaluating architectures, analyzing best practices, comparing solutions, assessing technical trade-offs, planning scalable/secure systems.

Expert-level Rust systems programming for high-performance, critical systems like Reth (Ethereum execution client). Use when working on: performance optimization, systems-level code, blockchain execution layers, memory-critical paths, concurrent systems, or production-grade infrastructure requiring staff engineer precision. Specializes in: allocation reduction, redundancy elimination, prefetching, parallelization, and simplicity-first optimization.

Build and test Solidity smart contracts with Foundry toolkit. Use when developing Ethereum contracts, writing Forge tests, deploying with scripts, or debugging with Cast/Anvil. Triggers on Foundry commands (forge, cast, anvil), Solidity testing, smart contract development, or files like foundry.toml, *.t.sol, *.s.sol.

Use this skill to validate that Markdown files are in standard locations. Scans for .md files outside of predefined allowed directories and outputs warnings to prevent documentation sprawl. Triggers include "validate docs", "check markdown locations", or as part of quality checks.

Iteratively craft a CUSTOMER.md document that precisely defines your ideal customer profile (ICP). This is the foundational document from which everything else (product, features, brand) derives. Uses parallel research agents and multi-choice workflow with feedback cycles.

Repository packaging for AI/LLM analysis. Capabilities: pack repos into single files, generate AI-friendly context, codebase snapshots, security audit prep, filter/exclude patterns, token counting, multiple output formats. Actions: pack, generate, export, analyze repositories for LLMs. Keywords: Repomix, repository packaging, LLM context, AI analysis, codebase snapshot, Claude context, ChatGPT context, Gemini context, code packaging, token count, file filtering, security audit, third-party library analysis, context window, single file output. Use when: packaging codebases for AI, generating LLM context, creating codebase snapshots, analyzing third-party libraries, preparing security audits, feeding repos to Claude/ChatGPT/Gemini.

React UI component systems with TailwindCSS + Radix + shadcn/ui. Stack: TailwindCSS (styling), Radix UI (primitives), shadcn/ui (components), React/Next.js. Capabilities: design system architecture, accessible components, responsive layouts, theming, dark mode, component composition. Actions: review, design, build, improve, refactor UI components. Keywords: TailwindCSS, Radix UI, shadcn/ui, design system, component library, accessibility, ARIA, responsive, dark mode, theming, CSS variables, component architecture, atomic design, design tokens, variant, slot, composition. Use when: building component libraries, implementing shadcn/ui, creating accessible UIs, setting up design systems, adding dark mode/theming, reviewing UI component architecture.

Analyze test cases against specifications to find ambiguous assumptions. Use when tests might be making assumptions not explicitly defined in the spec. Invoke with /test-ambiguity-detector <problem> <checkpoint>.

Create a BRAND_GUIDELINES.md that defines how to communicate with your customer. Requires CUSTOMER.md to exist first. Covers voice, tone, language rules, messaging framework, and copy patterns.

Prompt engineering and optimization for AI/LLMs. Capabilities: transform unclear prompts, reduce token usage, improve structure, add constraints, optimize for specific models, backward-compatible rewrites. Actions: improve, enhance, optimize, refactor, compress prompts. Keywords: prompt engineering, prompt optimization, token efficiency, LLM prompt, AI prompt, clarity, structure, system prompt, user prompt, few-shot, chain-of-thought, instruction tuning, prompt compression, token reduction, prompt rewrite, semantic preservation. Use when: improving unclear prompts, reducing token consumption, optimizing LLM outputs, restructuring verbose requests, creating system prompts, enhancing prompt clarity.

Multimodal AI processing via Google Gemini API (2M tokens context). Capabilities: audio (transcription, 9.5hr max, summarization, music analysis), images (captioning, OCR, object detection, segmentation, visual Q&A), video (scene detection, 6hr max, YouTube URLs, temporal analysis), documents (PDF extraction, tables, forms, charts), image generation (text-to-image, editing). Actions: transcribe, analyze, extract, caption, detect, segment, generate from media. Keywords: Gemini API, audio transcription, image captioning, OCR, object detection, video analysis, PDF extraction, text-to-image, multimodal, speech recognition, visual Q&A, scene detection, YouTube transcription, table extraction, form processing, image generation, Imagen. Use when: transcribing audio/video, analyzing images/screenshots, extracting data from PDFs, processing YouTube videos, generating images from text, implementing multimodal AI features.