區塊鏈

Browse, search, and reference saved persona definitions. Use when: (1) asked to list or search existing personas, (2) starting reasoning session with expert perspective, (3) finding relevant expert viewpoint for topic, (4) checking for existing persona before creating new.

Provides categorical organization for tasks using a predefined set of seven standard tags (Work, Personal, Shopping, Health, Finance, Learning, Urgent). Enforces tag validation rules including duplicate prevention and 5-tag maximum per task.

Analyze context management, memory systems, and state continuity in agent frameworks. Use when (1) understanding how prompts are assembled, (2) evaluating eviction policies for context overflow, (3) mapping memory tiers (short-term/long-term), (4) analyzing token budget management, or (5) comparing context strategies across frameworks.

Write clear, testable requirements using User Stories and Gherkin scenarios for Manifest Logistics SaaS. Capture functional and non-functional requirements with proper acceptance criteria. Use when defining new features or documenting system behavior.

Design safe migration strategies for breaking changes by planning how systems evolve without disrupting users. Use when: (1) asked to make breaking changes to APIs, schemas, or contracts without migration planning, (2) proposals assume all callers can update simultaneously without considering external dependencies, (3) changes lack definitions of migration completion criteria or rollback strategy, (4) plans omit how old and new versions will coexist during transition.

Enforces functional TypeScript patterns with Effect ecosystem. Use when (1) writing TypeScript functions or modules, (2) defining types or schemas, (3) handling errors or async operations, (4) structuring files with section separators, or (5) creating factories, dispatch tables, or Effect pipelines.

This skill should be used when the user asks to "create user stories", "write user stories", "break down epic into stories", "define user stories", "what stories do I need", "apply INVEST criteria", "write acceptance criteria", "split a large story", "story is too big", "story splitting", or when decomposing epics into specific, valuable user stories.

Kubernetes and Helm patterns - use for deployment configs, service definitions, ConfigMaps, Secrets, and Helm chart management

TypeScript enum pattern with Castable interface for model integration. Use when creating enums with behavior methods (colors, labels), defining fixed value sets, or integrating enums with the model casting system.

Generate or update go-to-market strategy. Use when defining GTM motion, selecting channels, or planning launch.

Build document Q&A and searchable knowledge bases with Google Gemini File Search - fully managed RAG with automatic chunking, embeddings, and citations. Upload 100+ file formats (PDF, Word, Excel, code), configure semantic search, and query with natural language. Use when: building document Q&A systems, creating searchable knowledge bases, implementing semantic search without managing embeddings, indexing large document collections (100+ formats), or troubleshooting document immutability errors (delete+re-upload required), storage quota issues (3x input size for embeddings), chunking configuration (500 tokens/chunk recommended), metadata limits (20 key-value pairs max), indexing cost surprises ($0.15/1M tokens one-time), operation polling timeouts (wait for done: true), force delete errors, or model compatibility (Gemini 2.5 Pro/Flash only).

META-SKILL ORCHESTRATOR - ALWAYS-ACTIVE. Orchestrates 100% Binora Backend workflows (Django 5.0+DRF 3.14+PostgreSQL multi-tenant) through 6-phase execution (Pre-Analysis, Request Analysis, Workflow Planning, Skill Coordination, Tool Optimization, Quality Assurance). Enforces P0 CRITICAL rules (NO manual tenant_id, service layer mandatory, YOLO comments). Selects optimal model (Sonnet/Haiku). MCP-first strategy (Context7/db/github/sequential-thinking). Target: 3-5x speedup, 95%+ P1 compliance, <500 token overhead.

Analyzes bear-put-spread debit spreads for bearish directional plays with defined risk. Requires numpy>=1.24.0, pandas>=2.0.0, matplotlib>=3.7.0, scipy>=1.10.0. Use when expecting moderate price decline, comparing put spread configurations, analyzing debit spread opportunities, or evaluating defined-risk bearish positions on mid to large-cap stocks.

Build efficient, scalable Claude Code skills using progressive disclosure and token optimization. Use when creating new skills, optimizing existing skills, or learning skill development patterns. Provides templates, checklists, and working examples.

Define constraints, invariants, and laws for the system. Creates proofobligations for formal verification. Use when: specifying business rules,defining invariants, creating validation requirements, expressing laws.

Codex CLI integration for code review and consultation. Use when: (1) code needs review before commit, (2) need expert consultation on implementation approach, (3) debugging assistance needed. This skill provides Codex interaction patterns only - workflow orchestration is defined in project CLAUDE.md.

Incremental content drafting skill that writes specific sections within existing scaffolds. Supports drafting 1 section at a time or batch-drafting multiple sections with user control. Each operation stays under 10k tokens to avoid context compacting.

Implement Cross-Site Request Forgery (CSRF) protection for API routes. Use this skill when you need to protect POST/PUT/DELETE endpoints, implement token validation, prevent cross-site attacks, or secure form submissions. Triggers include "CSRF", "cross-site request forgery", "protect form", "token validation", "withCsrf", "CSRF token", "session fixation".

Diagnose where explanations skip steps or use unexplained terminology. Use when: (1) asked to identify gaps or missing steps, (2) user asks for clarification, (3) explanation uses terms before defining them, (4) instructions followed without success, (5) asked to review explanation or documentation

Integrate Gemini API with correct current SDK (@google/genai v1.27+, NOT deprecated @google/generative-ai). Supports text generation, multimodal (images/video/audio/PDFs), function calling, and thinking mode. 1M input tokens. Use when: integrating Gemini API, implementing multimodal AI, using thinking mode for reasoning, function calling with parallel execution, streaming responses, deploying to Cloudflare Workers, building chat, or troubleshooting SDK deprecation, context window, model not found, function calling, or multimodal format errors. Keywords: gemini api, @google/genai, gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite, gemini-3-pro-preview, multimodal gemini, thinking mode, google ai, genai sdk, function calling gemini, streaming gemini, gemini vision, gemini video, gemini audio, gemini pdf, system instructions, multi-turn chat, DEPRECATED @google/generative-ai, gemini context window, gemini models 2025, gemini 1m tokens, gemini tool use, parallel function calling, compositional function calling, gemini 3