发现 Skills
为真实工作流程挑选经过整理的 Skill,连接、安装并开始使用。
plugin-setup-creator
Create a shareable Claude Code plugin package containing your commands, hooks, output styles, status lines, and agents. Use it when you want to package and distribute your Claude Code customizations, create team plugins, or export your personal setup.
laravel-debug
Debug Laravel application issues using browser logs, tinker, database queries, and systematic troubleshooting. Use this when encountering errors, unexpected behavior, or performance issues.
conflict-detector
Expertise in detecting file conflicts during parallel work. Signals conflicts to Theia orchestrator via MCP.
code-quality
Code quality guidelines including naming, structure, and maintainability. This skill should be used when writing or reviewing code to ensure it meets quality standards. Use proactively when discussing naming conventions, code smells, readability, Sandi Metz rules, method length, class size, comments, refactoring for clarity, or maintainability concerns. (user)
brand-positioning
Develop brand positioning strategy using proven frameworks. Use when defining or refining how a brand is perceived in the market.
spec-driven-development
Guide feature development through a structured four-phase workflow: Requirements (EARS syntax), Technical Design, Task Planning, and Implementation. Use when starting a new feature, planning a complex change, converting a feature request into actionable specs, or ensuring traceability from requirements through code. Triggers on spec, requirements, design document, task breakdown, implementation plan, or feature planning.
claude-plugin-sync
Syncs active Claude Code plugins (skills and agents) to Copilot CLI. Use this skill at session start, when the user mentions Claude plugins, when skills or agents seem missing, when the user asks about available capabilities, or when troubleshooting why a skill isn't working.
tiktok-profile-videos
TikTok user profile video scraper: input a TikTok username → output the user's profile info plus paginated video list with full metadata (engagement stats, music, video meta). Use when user mentions TikTok profile scraping, scrape TikTok user videos, get TikTok creator videos, extract TikTok profile data, TikTok user posts, TikTok account video collection, collect TikTok profile page videos, TikTok creator video list, TikTok creator data, TikTok profile scraper, tiktok user scraper, tiktok creator scraper. Also applies to influencer research, competitor analysis, content archiving for a specific TikTok creator, or extracting all posts from a TikTok account.
mcp-generate
Generate MCP server configuration for Zeph. Use when the user asks about adding MCP servers, configuring MCP tools, or integrating external tool providers.
design
Create PRDs through structured decision-tree interviews — designing, speccing, scoping. Walks every branch of the design tree, sweeps for gray areas, writes a PRD.
generate-clients
Generates C# and TypeScript clients for BymseRead.Service.
Task Decomposition
You break goals into actionable tasks.
dedupe
Deduplication reference — exact matching, fuzzy matching, hash-based dedup, Bloom filters, and data quality. Use when removing duplicate records, files, or data entries.
create-custom-dagster-component
Create a custom Dagster Component with demo mode support, realistic asset structure, and optional custom scaffolder using the dg CLI. Use this skill if there is no Component included in an existing integration or if Dagster does not have the integration.
analyzing-component-quality
Expert at analyzing the quality and effectiveness of Claude Code components (agents, skills, commands, hooks). Assumes the component is already technically valid. Evaluates description clarity, tool permissions, auto-invoke triggers, security, and usability to provide quality scores and improvement suggestions.
opencode-agents
Create and configure custom OpenCode agents (primary and subagents) with specialized prompts, tools, permissions, and models. Use when the user wants to create, modify, or configure OpenCode agents, or mentions agent modes, tool permissions, or task delegation.
lottie-bodymovin
Use when implementing Disney's 12 animation principles with Lottie animations exported from After Effects
sound-effects
Generate sound effects from text descriptions using ElevenLabs. Use when creating sound effects, generating audio textures, producing ambient sounds, cinematic impacts, UI sounds, or any audio that isn't speech. Supports looping, duration control, and prompt influence tuning.
threejs-materials
Three.js materials - PBR, basic, phong, shader materials, material properties. Use when styling meshes, working with textures, creating custom shaders, or optimizing material performance.
refactor-risk-assess
[Code Quality] Evaluates risk level of proposed refactoring changes. Use to assess dependencies, blast radius, rollback difficulty, and determine if changes are safe to proceed.
capacitor-mcp
Model Context Protocol (MCP) tools for Capacitor mobile development. Covers Ionic/Capacitor component APIs, plugin documentation, CLI commands, and AI-assisted development via MCP. Use this skill when users want to integrate AI agents with Ionic/Capacitor tooling.
lmstudio-subagents
Reduces token usage from paid providers by offloading work to local LM Studio models. Use when: (1) Cutting costs—use local models for summarization, extraction, classification, rewriting, first-pass review, and brainstorming when local quality suffices, (2) Avoiding paid API calls for high-volume or repetitive tasks, (3) No extra model configuration—just-in-time model loading and REST API integration work with your existing LM Studio setup, (4) Local-only or privacy-sensitive work. Requires LM Studio 0.4+ with server (default :1234). No CLI required.
spend-optimizer
Audit subscriptions AND optimize credit card rewards. Analyzes bank CSVs to find recurring charges, categorize spend, identify which card each charge should be on, and calculate potential rewards. Use when user says "audit subscriptions", "optimize my cards", "maximize rewards", or "analyze my spending". Outputs interactive HTML with subscription management and card optimization.
homeassistant-yaml-dry-verifier
Verify Home Assistant YAML for DRY and efficiency issues by detecting redundant trigger/condition/action/sequence structures and repeated blocks across automations, scripts, and packages. Use when creating, reviewing, or refactoring YAML in config/packages, config/automations, config/scripts, or dashboard-related YAML where duplication risk is high.