Claude Code

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

Trip planning for nomadic families: multi-stop trips, Schengen/visa, climate, destinations.

City-scoped Bushdrum event search for agents with list_cities and search_events.

专业合同审核 Skill，基于合同审核工作区成熟经验，提供7步工作流、终稿三件套、风险六维度评价

Async message queue for AI agents. Self-provision queues, push/poll messages, no signup.

MCP server for automated web accessibility scanning with Playwright and Axe-core.

Remove the visible Doubao (豆包) AI watermark from images. Use when asked to remove Doubao watermarks, clean Doubao-generated images, or process images with the "豆包AI生成" watermark.

Localized Markdown and MDX content guide for Better Translate projects.

Fetches real question papers for ANY university worldwide via AI web search, or generates university-style question papers with proper formatting. Uses LLM web search as the primary method (no single-site dependency, works for any university). Falls back to automated scripts for SPPU. Supports ALL …

Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.

Send transactional emails from AI agents via Truncus. Validate, track delivery, and manage domains.

Provides read access to your GKE and Kubernetes resources.

Top-level conductor skill that routes Solana tasks across four specialized sub-skills: orquestra-researcher (program discovery), orquestra-pda-explorer (account resolution), orquestra-tx-builder (transaction construction), and orquestra-signer (sign + send via @orquestradev/signer-mcp). Use when a …

Rust 测试模式，包括单元测试、集成测试、异步测试、属性测试、mocking 和覆盖率。遵循 TDD 方法论。

Use for rigorous pull request, branch, patch, or diff review. Runs focused review subagents for correctness, security/reliability, tests, docs/API behavior, and release risk, then synthesizes actionable findings.

MCP Server for Binge-watch/MoonTV/LunaTV

Standard workflow for OpenSCAD parts that deboss a three-line info stamp on a print-bed face: JSON config per product folder, generate stamp_generated.scad, and export STLs. Use when adding or changing print stamps, print-stamp-config.json, export scripts, or CI for 3D prints.

Diagnoses and fixes common frontend issues including Ant Design deprecations and API failures. Invoke when user reports console warnings, UI crashes, or requests project maintenance.

You are the master controller of the AI Dev Factory. You coordinate all other agents, track project state, and ensure the pipeline runs in the correct order from idea to shipped product.

Review completed implementation work and update task status.

Expert guidance for building rich text editors with Tiptap - a headless, framework-agnostic editor built on ProseMirror. Use when creating custom nodes, marks, or extensions for Tiptap, implementing input rules or paste rules, working with the Tiptap commands API, building React integrations with u…

Roboflow computer vision for AI assistants: datasets, annotation, versioning, workflows, inference.

Configure and troubleshoot Hyprland safely in this dotfiles repo. Use when adding or changing monitor, bind, input, workspace, window rule, layer rule, layout, animation, env, startup, or runtime behavior in `.config/hypr/*.conf`, and when diagnosing config errors, layer-shell stacking/input issues…

Inference with Caffe2. running models.

Run E2E tests or interactive browser verification. Triggers on: 'run e2e', 'e2e test', 'browser test', 'check in browser', 'verify UI', 'interactive test'.

Create or update ProjectK documentation per Documentation-Rules — ADR (architecture) / DDR (design-art decision) with numbering scan, system docs with required sections, frontmatter, link-not-duplicate. Use when asked to write an ADR, DDR, decision record, or any Docs/ page.

Guide for debugging OhMyCode issues. Use when user reports errors, unexpected behavior, or connection problems.

Generate, validate, and interpret static A2UI v0.8 JSON for interactive UI surfaces. Use when an agent needs to call publish_a2ui, author A2UI messages, check whether generated A2UI JSON is valid, or handle normalized userAction replies from interactive UI callbacks.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable sk…

Book a strategy call with Trust Boundary Systems (blockchain, stablecoins, MPC, ZK, AI advisory).