发现 Skills

Use when implementing decoupled communication between nodes — a global Event Bus autoload with typed signals.

Systematic PR review response workflow with automated quality checks

Assess a plugin and create refactoring task files for parallel agent execution. Use when you need to analyze a plugin structure, score its quality, and generate a phased refactoring plan with design map and implementation tasks.

This skill should be used when the user asks to "add logging to bash script", "colorize output", "implement log levels", "CI/CD sections", "terminal colors in bash", or mentions logging functions, emoji output, collapsible CI sections, or shlocksmith.

Identify required inputs, dependencies, and uncertainties during planning. Use when generating plans or task graphs under incomplete information. Does not block plan generation; instead, it localizes gaps and creates unblock dependencies.

Orchestrates specialized agents to create high-quality Claude Code plugins. Delegates to researcher agents for domain knowledge, Explore agents for code discovery, validation agents for official docs verification, and review agents for quality checks. Use when creating new plugins or improving existing ones.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Control Eight Sleep pods (status, temperature, alarms, schedules).

Control the user's real Chrome browser via AppleScript. Write Python scripts using chrome_pilot library to browse, extract, and download web content. Invisible to anti-bot detection.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

Send bulk messages to dancers via Ballee Support chat. Use when sending apology messages, system updates, or personalized notifications to users.

Analyze and optimize database queries: EXPLAIN ANALYZE plan reading, index strategies (B-tree, GIN, GiST, partial, composite), N+1 detection in ORM code, connection pooling, and query plan regression testing.

Builds structured anime and manga prompts for Midjourney Niji mode, matching artist styles, SREF codes, and technical parameters to user requests. Activates when the user wants to create anime art, reference specific manga artists or studios, use Niji mode, or generate character reference sheets and animations.

Complete reference for WoW Retail Currency, Auction House, Token, Store, Trading Post, Black Market, Mail, and Player Trading APIs. Covers C_CurrencyInfo (currency data, tracking, backpack), Auction House (full listing/bidding/buying/selling/search/commodity), C_WowTokenPublic (WoW Token market), AccountStore (in-game shop), CatalogShop, C_PerksProgram (Trading Post — Trader's Tender), BlackMarket (BMAH), TradeInfo (player trading), MailInfo (mailbox), and related events. Use when working with currencies, auction house UI, WoW Tokens, the in-game store, Trading Post, black market, mail, or player-to-player trading.

Activate rigorous, no-nonsense advisory mode for deep analysis, research, critical review, or honest assessment. Use when the user says "advise", "advise me", "give me your honest take", "don't sugarcoat", "be brutally honest", "rigorous mode", "devil's advocate", "second opinion", "challenge this", "stress-test this", "poke holes", "what am I missing", or any variation of wanting unfiltered expert analysis. Also use when the user asks a complex research question, requests a critical review of a plan or architecture, or wants a decision evaluated with full intellectual honesty rather than encouragement.

Apply AWS IAM best practices including least privilege, execution role design, and policy patterns for serverless applications.

Python language expert for *.py files. Covers Python versions, packages (pip, conda), type hints, async/await, testing (pytest), and Pythonic patterns. Use for any Python question.

Automatically generate estimates from QTO data. Apply pricing rules to BIM quantities for cost estimates.

Analyze large-scale construction datasets. Process thousands of projects for patterns, benchmarks, and predictive insights.

Detect and analyze geometric clashes in BIM models. Identify MEP, structural, and architectural conflicts before construction.

Automated cost estimation from BIM models using DDC CWICR database with 55,719 work items. AI classification + vector search for accurate pricing.

Extract quantities from BIM/CAD data for cost estimation. Group by type, level, zone. Generate QTO reports.

Build automated BIM validation pipelines for IFC/Revit data. Continuous validation against IDS, LOD requirements, COBie, and project-specific BEP standards.