Agent skills for Windsurf (legacy)

Expert in Claude Agent SDK development. Use when users ask about SDK API, agent configuration, MCP servers, hooks, permissions, file…

Set up a repository for effective agent-assisted development.

Use when reviewing SKILL.md files for structure and trigger quality.

Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs.

Use when mapping code paths, entrypoints, and likely hot files before profiling.

Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence.

Creates, tests, and refines platform-agnostic AI agent skills using a test-driven RED-GREEN-REFACTOR methodology.

When the user wants to create SEO-driven pages at scale using templates and data.

Interact with Telegram through TDLib - authenticate, inspect chats, and send messages

Builds, converts, and deploys pages to a Bricks Builder WordPress site using the agent-to-bricks CLI (`bricks`).

Local pre-action trust boundary for agents before installing skills, enabling tools/MCP servers, exposing secrets, or approving risky…

Use whenever the user's own funds or wallet are involved — balances, portfolio, transfers, swaps, bridging, staking, lending, or x402…

MUST load BEFORE any mcp__plugin_agent-web-interface_browser__* tool call (navigate, snapshot, click, type, find, get_element, get_form…

Interact with WhatsApp - send messages, read chats, manage conversations

Safely read, edit, and execute notebooks on a standalone or remote Jupyter Server through HTTP Sessions and WebSocket kernel channels.

Pull the latest Agentic-Z template improvements (agents, skills, conventions, docs) from upstream into your clone, without touching your…

Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using…

Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging.

A comprehensive verification system for Claude Code sessions.

Set up codebase intelligence for AI agents.

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state…