Agent skills for DeepSeek Harness

Step-by-step guide for adding new pages to the Yew frontend

Blueprint for adding related-resource views to an a9s resource type -- split into CODER steps (1-7) and QA steps (8-12) with templates

Use this skill whenever the user mentions admin portal, admin panel, back office, CMS, content management, user management, CRUD…

Streamlines Adobe Animate and CreateJS development for interactive HTML5 Canvas projects through specialized debugging, component…

Optimizes Adobe Animate and CreateJS projects by identifying and fixing memory leaks, redundant event bindings, and rendering bottlenecks.

Use when the user asks to migrate, convert, compatibilize, or modernize legacy ADVPL procedural code to TLPP object-oriented classes on…

**Game** development **orchestrator.** Routes to platform-specific skills based on project needs.

When the user wants keyword research, keyword expansion, search volume, CPC, competition, long-tail opportunities, or clustering inputs…

Client-branded pitch mockups: hero, tiles, slides.

Provides comprehensive guidance and command references for the agent-browser CLI to enable AI-driven headless browser automation.

agent-browser usage patterns and conventions reference.

Browser automation and testing using Vercel's agent-browser CLI with ref-based element targeting

Interact with Channel Talk using extracted desktop app or browser credentials - read chats, send messages, search messages, manage groups

Interact with Discord servers - send messages, read channels, manage reactions

Interact with Discord servers using bot tokens - send messages, read channels, manage reactions

Agent eXperience Interface (AXI) — ergonomic standards for building CLI tools that agents use via shell execution.

Installs and manages standardized design collaboration rules in AGENTS.md to enforce disciplined AI coding practices.

Analyzes and improves AI agent collaboration environments based on the 12 principles of Agent Harness maturity.

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.