Loading...
Loading...
Found 1,989 Skills
Hook Development Rules
Repository housekeeping workflows for AGENTS/CLAUDE architecture, progressive disclosure, and migration of legacy monolithic instruction files.
Reads images of payment statements and returns structured data. It can be called by other skills or directly by users.
Discover and document domain knowledge from a codebase into a structured knowledge file
Platform-agnostic skills including skill creation templates and best practices. Use when creating new skills or improving existing ones.
Automatically loads domain README.md context when you start working in a registered library or module. Reads architecture, public API, and patterns before touching domain-specific code. Activate when the task involves a specific library, domain path, or module the user references.
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".
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.
View and manage configurations and skills for AI agent CLI tools (Claude Code, Opencode). Use when checking config files, listing or managing skills, viewing model settings, comparing configs across tools, or performing common config operations.
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.
Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.