Loading...
Loading...
Found 6,395 Skills
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.
Detects common LLM coding agent artifacts in codebases. Identifies test quality issues, dead code, over-abstraction, and verbose LLM style patterns. Use when cleaning up AI-generated code or reviewing for agent-introduced cruft.
Orchestrate multiple worker agents to implement groomed tasks. Use when multiple ready tasks need implementation, when you want autonomous multi-task execution, or when coordinating batch development work. Keywords: coordinator, orchestrator, multi-task, parallel, workers, batch, autonomous.
Develop AI agents, tools, and workflows with Mastra v1 Beta and Hono servers. This skill should be used when creating Mastra agents, defining tools with Zod schemas, building workflows with step data flow, setting up Hono API servers with Mastra adapters, or implementing agent networks. Keywords: mastra, hono, agent, tool, workflow, AI, LLM, typescript, API, MCP.
Superdesign is a design agent specialized in frontend UI/UX design. Use this skill before implementing any UI that requires design thinking. Common commands: superdesign create-project --title "X" (setup project), superdesign create-design-draft --project-id <id> --title "Current UI" -p "Faithfully reproduce..." --context-file src/Component.tsx (faithful reproduction), superdesign iterate-design-draft --draft-id <id> -p "dark theme" -p "minimal" --mode branch --context-file src/Component.tsx (design variations), superdesign execute-flow-pages --draft-id <id> --pages '[...]' --context-file src/Component.tsx (extend to more pages). Supports line ranges: --context-file path:startLine:endLine
Create and refine OpenCode agents via guided Q&A. Use proactively for agent creation, performance improvement, or configuration design. Examples: - user: "Create an agent for code reviews" → ask about scope, permissions, tools, model preferences, generate AGENTS.md frontmatter - user: "My agent ignores context" → analyze description clarity, allowed-tools, permissions, suggest improvements - user: "Add a database expert agent" → gather requirements, set convex-database-expert in subagent_type, configure permissions - user: "Make my agent faster" → suggest smaller models, reduce allowed-tools, tighten permissions
Syncs skill metadata to AGENTS.md Auto-invoke sections. Trigger: When updating skill metadata (metadata.scope/metadata.auto_invoke), regenerating Auto-invoke tables, or running ./skills/skill-sync/assets/sync.sh (including --dry-run/--scope).
Use agent-browser to help users publish content to social media. This skill is used when users need to publish content, push articles, upload articles, or post to social platforms.
Intelligent agent for validating ERPNext/Frappe code against best practices and common pitfalls. Use when reviewing generated code, checking for errors before deployment, or validating code quality. Triggers: review this code, check my script, validate before deployment, is this correct, find bugs, check for errors, will this work.
Instructions for AI agents to create new skills and add them to the skills repository