區塊鏈

SRE patterns for production service reliability: SLOs, error budgets, postmortems, and incident response. Use when defining reliability targets, writing postmortems, implementing SLO alerting, or establishing on-call practices. NOT for initial service development (use scaffolding skills instead).

Create Zod schemas for new entities/resources in the backend. Use when adding a new resource, creating data models, defining DTOs (CreateType, UpdateType), or setting up validation schemas. Triggers on "new schema", "add entity", "create model", "define type".

Generate Effect Schema definitions for WoW DBC tables. Use when adding new game data tables or updating existing schemas.

Master emerging technologies including blockchain, cybersecurity, QA testing, and specialized tech roles. Stay ahead with cutting-edge technologies.

Align certainty levels to evidence strength to avoid overconfidence or unwarranted hedging. Use when: (1) making definitive claims or recommendations that others will rely on, (2) when statements rest on inference or reasoning rather than verified facts, (3) before expressing confidence levels about version-specific behavior or current information, (4) when communicating risk, trade-offs, or reliability of conclusions

Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.

從規格目錄的 acceptance.yaml 生成/維護 BDD/ezSpec 測試。使用類似 Gherkin 語法，AI 自動產生 step definition（開發人員不需要手寫），驗收測試規格即為 Executable Specification。

Implement scalable CSS architecture patterns - BEM, SMACSS, ITCSS, design tokens

Complete HUMMBL Base120 mental models framework with all 120 models across 6 transformations (Perspective, Inversion, Composition, Decomposition, Recursion, Meta-Systems). Includes model selection guidance, application methodology, and validation checklist. Version 1.0-beta definitive reference.

Pytest fixture design, conftest.py hierarchy, and DRY test code patterns. Identifies duplicate fixtures, plans fixture scope, and designs conftest.py structure. Use when creating test directories, refactoring test fixtures, or reviewing test code for duplication.

Navigate a local emacs-twist/twist.nix checkout and point to relevant files for questions about twist.nix configuration, flake outputs, library functions, Home Manager integration, package build flow, or tests. Use when a user asks where something is defined or how twist.nix is wired and the answer should reference code rather than reproduce it. Ask for the repo path if it is not available.

Master Solidity smart contract development with patterns, testing, and best practices

Designs high-performing team structures using organizational psychology AND creates new skills on-the-fly when team needs unmet expertise. Expert in team composition, personality balancing, collaboration ritual design, and skill creation for missing capabilities. Use for team design, role definition, skill gap identification. Activates on 'team building', 'team composition', 'skills needed', 'what skills'. NOT for general project management or solo work planning.

Create detailed implementation plans before coding (saves tokens later)

Analyze, compare, and work with tokenizers using Unsloth tools. Compare different tokenizers, analyze token efficiency, and integrate with Unsloth models. For SuperBPE training, see the 'superbpe' skill.

Use this skill when working with the CliftonSites Supabase backend for any task including understanding database schemas, debugging issues, adding features, querying data, managing RPC functions, reviewing triggers/policies, working with the automation pipeline, security architecture (MFA authentication, RLS, SECURITY DEFINER functions, API route protection), or any database operation. Provides complete expertise on all 12 tables, 25 RPC functions, 5 triggers, RLS policies, SECURITY DEFINER functions, admin MFA authentication, internal API token validation, views, indexes, data flows, and Supabase MCP server operations.

UI component generation patterns for IntelliFill. Replaces magic/21st.dev MCP to save ~3.4k tokens.

Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases. | Sử dụng khi: đóng gói repo, pack codebase, context cho AI.

Execute the implementation plan by processing and executing all tasks defined in tasks.md

Intelligently choose between semantic and text search based on query intent. Automatically selects the best search mode (semantic for concepts, text for exact terms, symbols for definitions) and provides relevant results. Use when user wants to find code.