发现 Skills

Guidelines for when and how to update Claude Code skills after codebase changes. Use after completing significant features, architectural changes, or discovering new patterns/anti-patterns. NOT for every commit - only meaningful changes that affect how agents should work.

A general-purpose set of coding standards, best practices, and patterns for TypeScript, Angular, and C# development.

Designs and blueprints intentionally designed outdoor space in a live Minecraft Bedrock world — formal gardens, parks, plazas, courtyards, hedge mazes, fountains, parterres, topiary, cloister gardens, estate grounds. Covers French formal, Italian, English landscape, Mughal, Japanese, Chinese, modernist, and other traditions. Geometric and intentional — the deliberate counterpart to the naturalistic terraforming skill. Use when the user wants a garden, park, plaza, courtyard, hedge maze, fountain, or designed grounds. Part of the minecraft-builder workflow.

Step 1 of 4 of the Minecraft Bedrock MCP setup. Install and configure a Minecraft Bedrock Dedicated Server (BDS) — the foundation the MCP stack runs on. Use when the user wants to set up a dedicated Minecraft Bedrock server, start setting up Minecraft for AI/MCP control from scratch, or asks how to get a Bedrock server running so Claude can build in it.

Executes a detailed Minecraft build plan step by step — placing, filling, cloning blocks and stamping structures exactly as specified, with no redesign or improvisation. Use to carry out a plan.toon produced by the planner once it is detailed enough to follow mechanically. Part of the minecraft-builder workflow.

World of Darkness 20th Anniversary toolkit for Vampire (V20), Werewolf (W20), Mage (M20), Wraith (Wr20), Changeling (C20), Demon (D20). Creates characters, locations, items, organizations, weapons. Triggers: WoD, Vampire, Kindred, clan, ghoul, Garou, tribe, Gift, caern, Tradition, Technocracy, Sphere, rote, Arcanoi, Kithain, Art, spirit, Umbra, crossover, weapon stats, firearm, melee, ranged, Demon, Fallen, House, Lore, evocation, Earthbound, thrall, pact, apocalyptic form, Faith, Torment.

Use when making design decisions, reviewing UI for HIG compliance, choosing colors/backgrounds/typography, or defending design choices - quick decision frameworks and checklists for Apple Human Interface Guidelines

MetricKit API reference for field diagnostics - MXMetricPayload, MXDiagnosticPayload, MXCallStackTree parsing, crash and hang collection

Use when migrating from Realm to SwiftData — a comprehensive migration guide covering pattern equivalents, threading model conversion, schema migration strategies, CloudKit sync transition, and real-world scenarios.

subject segmentation, VNGenerateForegroundInstanceMaskRequest, isolate object from hand, VisionKit subject lifting, image foreground detection, instance masks, class-agnostic segmentation, VNRecognizeTextRequest, OCR, VNDetectBarcodesRequest, DataScannerViewController, document scanning, RecognizeDocumentsRequest

Build a personal gratitude practice for logging what's good, discovering patterns, and cultivating appreciation.

React and Vite performance optimization guidelines. Use when writing, reviewing, or optimizing React components built with Vite. Triggers on tasks involving Vite configuration, build optimization, code splitting, lazy loading, HMR, bundle size, or React performance.

Interacts with Gerrit code review to list changes and improve them

Extract and analyze Windows Registry hives to uncover user activity, installed software, autostart entries, and evidence of system compromise.

This skill should be used when the user wants to "create a skill", "add a skill to a plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Generate scenario-based pytest test matrices and verify coverage. Use for `/test-matrix`, Given/When/Then scenario design, variation axes, pytest parametrization scaffolds, logic-porting tests, and matrix coverage checks.

Detect unnecessary files and provide cleanup recommendations

Use this skill when you need to create, edit, or analyze Word documents (.docx), work with tracked changes and comments, or convert DOCX to other formats.

Conducts a senior-level Rust refactoring and API-design review of a crate, module, or subsystem — recovering architectural intent, identifying drift, and proposing small reviewable patches. Use whenever the user says 'review this Rust code', 'refactor this crate', 'audit our Rust API', 'this Rust module feels off', 'clean up this Rust subsystem', or asks for cohesion/idiom/API-design feedback on Rust code. Also trigger when the user mentions naming inconsistency, boolean explosion, leaky APIs, panic-prone library code, overgrown modules, parallel-API drift, or compatibility scar tissue in a Rust context — even if they don't explicitly ask for a 'review'.

Binds MewUI controls to data using ObservableValue<T> and ValueBinding<T>. Use when implementing reactive UI updates, building ViewModels, or connecting controls to data sources.

Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.

Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experimental validation including binding assays, expression testing, thermostability measurements, enzyme activity assays, or protein sequence optimization. Also use for submitting experiments via API, tracking experiment status, downloading results, optimizing protein sequences for better expression using computational tools (NetSolP, SoluProt, SolubleMPNN, ESM), or managing protein design workflows with wet-lab validation.

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.