Loading...
Loading...
Found 1,266 Skills
기존 PeachSolution 모듈을 test-data 패턴으로 리팩토링하는 팀 오케스트레이터 스킬. "팀 리팩토링", "레거시 코드 정리", "test-data 패턴으로 변환" 키워드로 트리거. layer=backend|frontend|all 지원, 독립 QA로 확증 편향 방지.
Refine, parallelize, and verify a draft task specification into a fully planned implementation-ready task
Systematically fix all failing tests after business logic changes or refactoring
Publish assembled videos to YouTube and other platforms. Orchestrates existing youtube-uploader, youtube-strategy, and youtube-plan-new-video skills. Use when ready to publish or plan distribution for completed videos.
What a knowledgeable local with great taste would tell you to walk to from here — fused across editorial, local-language, and crowd layers no single tool ranks together. Trigger phrases: `what should I walk to from here`, `near me with great taste`, `find the 3 places not the 40`, `kissaten near my hotel`, `viewpoint within walking distance`, `blue hour photo spot`, `use wanderlust-goat`, `run wanderlust-goat`.
Agentic OS Orchestrator. Process and execute tasks from the shared .agent/state/tasks.json queue. Use when the user asks to 'check the queue', 'process tasks', or run the heartbeat.
使用 agency-agents-zh 中文 AI 智能体角色库，为 AI 编程工具提供 215 个即插即用的专家角色
Control Room template for managing Hermes agents from one VPS agent to specialist teams and orchestrated workflows
Execute codeagent-wrapper for multi-backend AI code tasks. Supports Codex, Claude, Gemini, and OpenCode backends with agent presets, skill injection, file references (@syntax), worktree isolation, parallel execution, and structured output.
Design, test, and optimize prompts for LLM interactions. Cover prompt patterns (few-shot, chain-of-thought, ReAct), system prompt design, output formatting, prompt evaluation, and prompt optimization techniques. Triggers on "write prompt", "optimize prompt", "design system prompt", "few-shot examples", "chain of thought", "prompt evaluation", "LLM output formatting", "prompt testing", or "prompt patterns".
Deploy and run automated Attack-with-Defense (AWD) competitions where LLM-powered agents compete in real-time cybersecurity challenges
Control video generation requests before execution. Use this when the user asks for a simple clip, storyboard video, UGC video, podcast clip, reference video, talking-head, image-to-video, text-to-video, or research-handoff video and the skill must classify the request before handing it to video-request-architect and a runner such as seedance-submitter or video-batch-runner.