Build and Fix - Incrementally fix TypeScript and build errors. Run build, parse errors, fix one at a time, re-verify.

Router Module Configuration Guide

使用项目级 skill 内置的本地 Python 构建脚本执行编译、构建、重建与发布前构建验证。用户提到编译、构建、build、rebuild、重新编译、解决方案、项目、sln、csproj、发布前验证时使用。禁止切换到 dotnet、msbuild、powershell 或其他直接编译命令。

>-

Guide for building UI with Next.js App Router and shadcn/ui components. Use when creating pages, layouts, components, or installing shadcn primitives in the ROBOPRO project.

Adapt and integrate a Claude global skill into your project's development guidelines (not directly into project code).

You are running inside a Ralph loop tasked with making **Timed** a 10/10 school time-planning app.

Enforce atomic task status updates through task-tracker commands only. Prevent manual edits to NOTES.md and tasks.md that break synchronization. Auto-trigger when detecting Edit/Write attempts to task files, task completion mentions, or status update discussions. Auto-convert manual edit attempts to equivalent task-tracker commands. Validate task-tracker usage and auto-fix common mistakes.

Create hand-drawn diagrams from JSON using `excalidraw-cli`. Outputs `.excalidraw` files and shareable URLs.

Flutter 流畅动画实现指南 - 包含隐式/显式动画、Hero动画、交错动画、物理动画

Persistent multi-engine coding session manager. Wraps Claude Code, Codex, Gemini, and Cursor CLIs into headless agentic engines with 27 tools.

Interact with all Google Workspace APIs via the gws CLI. Use when managing Drive files, sending/reading Gmail, creating Calendar events, reading/writing Sheets/Docs/Slides, managing Chat spaces, contacts, Admin users/groups, Vault eDiscovery, Classroom, Apps Script, Workspace Events, or configuring the gws MCP server. Triggers on Google Workspace, gws, Drive, Gmail, Calendar, Sheets, Docs, Slides, Chat, Tasks, Meet, Forms, Keep, Admin, People, Vault, Classroom, Apps Script, Cloud Identity, Alert Center, Groups Settings, Licensing, Reseller, Model Armor, gws CLI, gws mcp, Google API, Workspace automation, npx skills add.

>

Search, render, and analyze compiled agent session traces via the `tracecc` CLI.

backend-api

You build AI-powered workflows—from simple Q&A to complex multi-agent collaboration.

| Path | Responsibility |

Suggest or manage Trekker tracking when the user talks about bugs, features, backlog items, or work that should survive this session.

Emergency compressed build-ship cycle for production issues

Master Multi Agent Rl for machine learning and AI applications. Use when implementing ML models, building AI systems, or working with data-driven solutions. This skill covers fundamental concepts, implementation techniques, best practices, and production considerations for multi agent rl.

Read `~/.claude/skills/i-frontend-design/SKILL.md` for design principles, anti-patterns, and the **Context Gathering Protocol**. Follow the protocol before proceeding — if no design context exists yet

mcp-server-authoring

Princípios de construção de servidores MCP (Model Context Protocol). Design de ferramentas, padrões de recursos e melhores práticas.

>

>

**[REQUIRED]** Use for **ALL** requests involving local Apache Polaris: setup, API queries, catalog operations, cleanup, teardown. **AUTO-ACTIVATE:** If `.snow-utils/snow-utils-manifest.md` contains `polaris-local-forge:` this skill MUST handle ALL operations including cleanup. **DO NOT** use `polaris` CLI (does not exist), curl to Polaris endpoints (needs OAuth), or docker ps checks - invoke this skill first. Triggers: polaris local, local iceberg catalog, local polaris setup, rustfs setup, create polaris cluster, try polaris locally, get started with polaris, apache polaris quickstart, polaris dev environment, local data lakehouse, replay from manifest, reset polaris catalog, teardown polaris, clean up, cleanup, delete cluster, remove resources, polaris status, list catalogs, show namespaces, list tables, show catalog, describe table, list principals, show principal roles, list views, polaris namespaces, polaris catalogs, query data, query table, query iceberg, query catalog data, show my data, show table data, show records, how many rows, count rows, count records, run sql, run query, duckdb query, select from, group by, aggregate.

Use when setting up or customizing Tailwind CSS configuration, theme customization, plugins, and build setup. Covers tailwind.config.js setup and content paths.

Evidence-based completion verification against all acceptance criteria. Must run before claiming work is done. No claims without evidence.

>

You are a helpful assistant that can assist in writing, abstracting, annotating, and summarizing Python code.

Places furniture and decorates Minecraft interiors using JSON schematics. Use when furnishing rooms, placing tables, chairs, beds, lamps, decorations, or designing interior spaces. Reference furniture_catalog.md for 80+ ready-to-use designs.

Agent Security Audit - analyzes agent for lethal trifecta, sandboxing, access control, and guardrails

Use this skill to set up Python development environment, install dependencies, and configure virtual environments. Use when user requests Python environment setup, pip package installation, or encounters missing module errors.

>

Use this skill to set up React + TypeScript development environment, create components, manage state, and configure build tools. Use when user requests React project setup, using TypeScript, or developing frontend applications.

- `src/routes/` holds SvelteKit pages; nested folders map to routes, with shared data wired through `+layout.*`.

> **Supersedes**: `loki-mode`

Active Security Enforcement. Scans code for vulnerabilities (SAST), secrets (Gitleaks), and insecure dependencies (SCA) before commit/deployment.

Use when the task asks for a visually strong landing page, website, app, prototype, demo, or game UI. This skill enforces restrained composition, image-led hierarchy, cohesive content structure, and tasteful motion while avoiding generic cards, weak branding, and UI clutter.

Use when the user wants to export conversation content to a professionally styled PDF for sharing

You are Andrew_GN, a house agent on **GoalNad Arena** — an AI-vs-AI football prediction arena on Monad blockchain. You combine data with intuition. While other agents crunch numbers or study history,

RICE-scored backlog prioritization. Use for sprint planning, feature prioritization, or backlog grooming.

Run a command in a tmux pane and continuously monitor its output, notifying the user via system notification if something fails.

Design and implement VPCs and networking. Configure subnets, route tables, and security groups. Use when setting up AWS network infrastructure.

Payments, subscriptions, invoices, and checkout with Stripe.

chatgpt

- **Category**: compute

Governance-first architect for business automations (n8n-first) who audits value, risk, and maintainability before implementation.

Trigger Pattern Always required for Solana audits - Inject Into Breadth agents, depth agents