Loading...
Loading...
Found 1,276 Skills
Explicitly save important knowledge to auto-memory with timestamp and context. Use when a discovery is too important to rely on auto-capture.
Memory health dashboard showing line counts, topic files, capacity, stale entries, and recommendations.
Design and apply AI personas for specialized contexts — project-specific voices, domain expert modes, or custom interaction styles. Use when creating custom personas, adapting communication style for specific projects, or designing role-based AI behaviors. Triggers on "페르소나", "persona", "역할 설정", "톤 설정", "voice", "캐릭터", "role definition".
Archive completed plans from plans/active/ to plans/completed/, supplement verification results and completion time. Suitable for calling after implementation is finished.
Collaborate on document creation and refinement. Merges contributions, manages versions, and produces unified documents from multiple sources.
Record and manage meeting notes with intelligence. Organizes meeting documentation with action items, decisions, and follow-ups.
Organize and categorize files into logical structures. Creates folder hierarchies, renames files systematically, and consolidates related data.
Multi-path parallel product analysis with cross-model test-time compute scaling. Spawns parallel agents (Claude Code agent teams + Codex CLI) to explore product from multiple perspectives, then synthesizes findings into actionable optimization plans. Can invoke competitors-analysis for competitive benchmarking. Use when "product audit", "self-review", "发布前审查", "产品分析", "analyze our product", "UX audit", or "信息架构审计".
Provides information about how to create, structure, install, and audit Agent Skills, Plugins, Antigravity Workflows, and Sub-agents. Trigger this when specifications, rules, or best practices for the ecosystem are required.
This skill should be used when the user asks to "analyze skill quality", "evaluate this skill", "review skill quality", "check my skill", or "generate quality report". Evaluates local skills across description quality, content organization, writing style, and structural integrity.
Save current session state to Apple Notes at session end. Triggers on handoff, bye, done, wrap up, or Chinese equivalents. Multi-agent architecture with private (per-agent) and shared (cross-agent) notes. Three-tier memory: Active, Archive, Long-term. Use whenever the user wants to end a session, save progress, or says anything indicating they are done for now.
Invoke parallel document-specialist agents for external web searches and documentation lookup