Loading...
Loading...
Found 175 Skills
Orchestrate audio team: audio-director + sound-designer + technical-artist + gameplay-programmer for full audio pipeline from direction to implementation.
Autonomous research agent that reads RESEARCH.md, infers what's needed, dynamically adjusts TODOs, and delegates to the right skill. Supports opt-in BFS mode for autonomous design space search. Respects a configurable supervision policy (presets: manual / checkpointed / autonomous / wild) governing notifications, approval gates, resource limits, and idea-change handling. Proactively surfaces gaps and asks before acting. Trigger phrases: "start research", "continue project", "what's next?", "explore design space", "autoresearch".
Analyze completed development work to identify automation and systematization opportunities. Use after finishing features, fixing bugs, or completing code reviews. Triggers on "analyze for automation", "what can we automate", "compound opportunities", "systematize".
TDD 기반 C#/.NET 개발. 테스트 먼저 작성 후 구현. Red-Green-Refactor 순서 강제. 서브에이전트에 위임.
Use just for command running and task automation. Prefer Justfiles over Makefiles. Keep recipes simple - delegate complex logic to scripts rather than embedding in recipes.
Delegate tasks to the cost-effective opencode/glm-5 model. Use when you need inexpensive task execution, simple research, or delegating work that doesn't require the most powerful models.
Generates project context (code structure + architecture intent). Use when starting sessions, understanding codebase structure, onboarding to a project, after major refactoring, or delegating complex work to agents.
High-level workflows for managing work using Fizzy cards — start, work on, complete, and delegate cards using the Fizzy CLI.
Verifies the agent's current work against a specific question by analyzing unstaged changes, staged changes, recent commits, and codebase context. Answers succinctly for a senior audience. Use when user says "/check", "verify that", "confirm that", "check if", "is X done?", or asks about current session changes.
Delegate a sub-task to Claude Code via the Agent Client Protocol (ACP). Use this skill whenever you want to hand off work to Claude — complex agentic coding with MCP tool access, detailed multi-file refactors, tasks requiring Claude's reasoning style, or anything where Claude's strengths give an advantage. Also invoke when the user asks you to "ask Claude", "use Claude for this", or "run this through Claude". The script handles subprocess lifecycle and ACP session setup; you just provide the prompt and read stdout.
Execute Google Gemini CLI for large-context code analysis, multimodal reasoning, and repository-scale reviews. Also use for delegating tasks requiring 1M token context windows or Gemini-specific capabilities.
Use OpenAI Codex from inside Claude Code for code reviews, adversarial reviews, and delegating tasks to Codex as a subagent.