Total 50,961 skills, AI & Machine Learning has 8536 skills
Showing 12 of 8536 skills
Felo AI real-time web search for questions requiring current/live information. Triggers on current events, news, trends, real-time data, information queries, location queries, how-to guides, shopping, or when Claude's knowledge may be outdated.
Why build on Ethereum specifically. The AI agent angle — ERC-8004, x402, composability, permissionless deployment. Use when a user asks "should I build on Ethereum?", "why blockchain?", or when an agent needs to recommend a chain for a project.
LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization
Optimize a prompt through a critique-compress pipeline with semantic equivalence verification at each stage. Applies think-critically to improve the prompt, then compress-prompt to reduce it, validating that behavior is preserved after each transformation.
AI e-commerce customer service assistant that supports order query, product recommendation, and ticket processing. It can use Playwright MCP to automatically operate the e-commerce backend to query real order status.
Graduate a workflow insight from learned/<topic>.md into AGENTS.md as a permanent constraint. Use when a lesson is stable enough to apply to every future session.
Use when working with Anthropic Claude Agent SDK. Provides architecture guidance, implementation patterns, best practices, and common pitfalls.
Create or update AgentSkills for CoWork-OSS. Use when designing, structuring, or packaging skills. Supports JSON format with requirements, installation specs, and metadata.
AI office content generator by AnyGen. Create professional slides, documents, websites, diagrams, data tables, and research reports from natural language prompts. Triggers: make PPT/slides/deck, generate document/report, draw diagram/flowchart/architecture/mind map/UML/ER diagram/sequence diagram/org chart/whiteboard, build website, organize data into table, analyze earnings, write deep research, visualize structure/process/flow. Output: auto-downloaded local file + online task URL.
Recursive codebase analysis using the RLM paradigm. Use when: analyzing large codebases (100+ files), investigating cross-cutting patterns, recursive decomposition of complex code questions, scanning for issues across entire repos. Triggers: analyze this codebase, how does X work across the codebase, scan all files for Y, recursive analysis, RLM.
Validates Stories/Tasks or context via parallel multi-agent review (Codex + Gemini). Merges findings, debates, applies fixes. GO/NO-GO verdict.
Align-and-Do Protocol (AAD). Use for smaller tasks that don't need formal specs or plans.