Develop with
Superpowers

Security reconnaissance. USE WHEN recon, reconnaissance, bug bounty, attack surface. SkillSearch('recon') for docs.

Security reconnaissance. USE WHEN recon, reconnaissance, bug bounty, attack surface. SkillSearch('recon') for docs.

Reference for the NetAlertX codebase structure, key file paths, and configuration locations. Use this when exploring the codebase or looking for specific components like the backend entry point, frontend files, or database location.

Guide on security practices including CSP, rate limiting, and session security for Epic Stack

Guide on deployment with Fly.io, multi-region setup, and CI/CD for Epic Stack

DeepChat app settings modification (DeepChat 设置/偏好) skill. Activate ONLY when the user explicitly asks to change DeepChat's own settings/preferences (e.g., theme, language, font size...). Do NOT activate for OS/system settings, editor settings, or other apps.

This skill should be used when the user wants to "create a skill", "add a skill to 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.

Convert natural language questions into SQL queries. Activates when users ask data questions in plain English like "show me users who signed up last week" or "find orders over $100".

Create and review Cloudflare Durable Objects. Use when building stateful coordination (chat rooms, multiplayer games, booking systems), implementing RPC methods, SQLite storage, alarms, WebSockets, or reviewing DO code for best practices. Covers Workers integration, wrangler config, and testing with Vitest.

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 Kimi's capabilities with specialized knowledge, workflows, or tool integrations.

Writing technical articles and blog posts. Use when creating articles in docs/articles/ or blog content explaining patterns, techniques, or lessons learned.

Svelte 5 patterns including TanStack Query mutations, shadcn-svelte components, and component composition. Use when writing Svelte components, using TanStack Query, or working with shadcn-svelte UI.

Design patterns for the Langroid multi-agent LLM framework. Covers agent configuration, tools, task control, and integrations.

Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.

Show users how Continuous Claude works - the opinionated setup with hooks, memory, and coordination

Migration workflow - research → analyze → plan → implement → review

Release preparation workflow - security audit → E2E tests → review → changelog → docs

Wiring Verification

Identify failure modes before they occur using structured risk analysis

Create and use Claude Code slash commands - quick prompts, bash execution, file references