发现 Skills

Rust implementation patterns for AFD commands using the afd crate, CommandResult types, and async handlers. Covers command definition, schema design with JSON Schema, error handling, registry patterns, and testing. Use when: implementing commands in Rust, building Rust MCP servers, working with CommandResult types, or debugging Rust AFD code. Triggers: rust afd, rs command, CommandResult rust, CommandHandler, rust implementation, afd crate, cargo afd.

Use when invalid data causes failures deep in execution and validation is needed at multiple system layers — validate at every layer data passes through to make such bugs structurally impossible.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Verifies that an extracted statement is internally consistent by checking that opening_balance + sum(transactions) = closing_balance within a small tolerance, and produces a reconciliation report flagging missing rows, double-counted rows, sign errors, and rounding diffs. Use as the gate between PDF extraction and committing transactions to the data store, when reconciling a statement that does not balance, or when user mentions reconcile, balance check, or statement does not tie out.

Use when designing resource lifecycles. Keywords: RAII, Drop, resource lifecycle, connection pool, lazy initialization, connection pool design, resource cleanup patterns, cleanup, scope, OnceCell, Lazy, once_cell, OnceLock, transaction, session management, when is Drop called, cleanup on error, guard pattern, scope guard, 资源生命周期, 连接池, 惰性初始化, 资源清理, RAII 模式

Build data pipelines for La-Z-Boy analytics and reporting. Covers ETL/ELT patterns, data validation, scheduling, error handling, and data quality monitoring using Python, Pandas, and Airflow. Use when building data ingestion or transformation workflows.

Feishu urgent message (buzz) notifications. Activates when a user mentions keywords like "urgent", "buzz", "remind", or "escalation" in a message.

Disco Elysium ENDURANCE skill: sustained quality over long tasks. Activates during multi-file changes, large refactors, tasks with many steps, or when consistency across a long operation is critical.

Kalshi prediction markets — events, series, markets, trades, and candlestick data. Public API, no auth required for reads. US-regulated exchange (CFTC). Covers soccer, basketball, baseball, tennis, NFL, hockey event contracts. Use when: user asks about Kalshi-specific markets, event contracts, CFTC-regulated prediction markets, or candlestick/OHLC price history on sports outcomes. Don't use when: user asks about actual match results, scores, or statistics — use football-data or fastf1 instead. Don't use for general "who will win" questions unless Kalshi is specifically mentioned — try polymarket first (broader sports coverage). Don't use for news — use sports-news instead.

MLB data via ESPN public endpoints — scores, standings, rosters, schedules, game summaries, play-by-play, win probability, injuries, transactions, depth charts, team/player stats, leaders, and news. Zero config, no API keys. Use when: user asks about MLB scores, standings, team rosters, schedules, game stats, box scores, play-by-play, injuries, transactions, depth charts, team/player statistics, or MLB news. Don't use when: user asks about minor league baseball, college baseball, or international baseball. For other sports use: nfl-data (NFL), nba-data (NBA), wnba-data (WNBA), nhl-data (NHL), football-data (soccer), tennis-data (tennis), golf-data (golf), cfb-data (college football), cbb-data (college basketball), fastf1 (F1). For betting odds use polymarket or kalshi. For news use sports-news.

Use this starter when a task lands in the `Conservation genomics and eDNA` frontier leaf and the repository has curated resources but no dedicated runtime implementation yet.

Turn vague Acceptance Criteria into measurable checks and test assertions

TailwindCSS v4 patterns with CSS-first configuration using @theme, @source, and modern CSS features. Covers design tokens, CSS variables, container queries, dark mode, and Vite integration. Use when configuring Tailwind, defining design tokens, or leveraging modern CSS with Tailwind utilities.

Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

Design system templates and patterns for UI/UX briefs. Used by /majestic:ux-brief command.

HarmonyOS application development expert. Use when building HarmonyOS apps with ArkTS, ArkUI, Stage model, and distributed capabilities. Covers HarmonyOS NEXT (API 12+) best practices.

LiteLLM-RS A2A Protocol Architecture. Covers Agent-to-Agent communication, JSON-RPC 2.0 messaging, multi-provider orchestration, agent registry, and task state management.

LiteLLM-RS Caching Architecture. Covers Redis caching, vector database semantic caching, multi-tier cache strategy, TTL management, and cache invalidation patterns.

LiteLLM-RS Provider 开发与架构指南。用于添加新 provider、迁移错误处理、维护 66+ provider 的一致性。包含架构对比分析和最佳实践。

Validates implementation plan execution by verifying success criteria and identifying deviations. This skill should be used after a phase or plan has been implemented and committed. It runs automated checks (tests, types, lint), compares actual changes against the plan's specifications, and generates a validation report documenting what was completed, what deviated, and what needs manual testing.

Guides creation of well-structured tickets (task documents). This skill should be used when the user wants to create a ticket, task, feature request, bug report, or any work item that needs to be tracked and potentially assigned. Provides structure hints without enforcing rigid templates - the final structure adapts to the specific task and domain.

Performs a deep audit and cleanup of the project's AI context files (AGENTS.md and existing skills). Trigger this autonomously when the user adds/removes tools, completes a major architectural refactor, or explicitly asks for a "hygiene check" or "context sync".

Initial business configuration wizard. Runs on first use to configure the AI OS for your specific business. Use when context/my-business.md is empty, user says "set up my business", "configure", "initialize", or "start fresh".

Prepare for meetings with research briefs, talking points, and follow-up templates. Use when user says "prep for meeting with X", "I have a call with X tomorrow", or "meeting brief for X".