专门用于在对话结束时，根据用户反馈和对话内容总结优化并迭代现有 Skills 的核心工具。它通过吸取对话中的“精华”（如成功的解决方案、失败的教训、特定的代码规范）来持续演进 Skills 库。

Generates tests from features.json test criteria with multi-framework support, coverage analysis, and features.json integration.

Use when user asks to create, write, edit, or test a skill. Also use when documenting reusable techniques, patterns, or workflows for future Claude

Search and recommend Claude Code skills from trusted marketplaces

The speed layer of AI-native marketing. This skill covers creating and deploying content in real-time—responding to trends, events, and moments as they happen with AI-generated visuals, video, and...

Help users build software using AI coding tools. Use when someone is using AI to generate code, building prototypes without deep technical skills, or exploring how non-engineers can create...

Validates that a skill or MCP implementation matches its manifest by running Codex-powered semantic comparisons across descriptions, preconditions, effects, and API surface.

The next evolution of influencer marketing: AI-generated personas that represent brands with perfect consistency, infinite availability, and zero scandal risk. This skill covers creating,...

The fusion of trend prediction and AI content generation: detecting emerging trends before they peak and generating content that rides—or creates—the wave. This is marketing alchemy, transmuting...

Claude Code skill for detecting and synchronizing Node.js version specifications across project files

Expert in creating, editing, and automating PowerPoint presentations using python-pptx and PptxGenJS. Use when generating slides programmatically, modifying presentations, or building report...

Generate CHANGELOG entries following conventional commits format with

AI-powered B2B sales workflow. Research prospects, generate outreach, create content, handle objections, prep discovery calls. Use when asked to "research a company", "write a cold email", "handle...

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.

Generate and manage text embeddings for semantic search, clustering, and similarity tasks

Guide for security-related Agent Skills including penetration testing, code auditing, threat hunting, and forensics skills.

Generate testable hypotheses. Formulate from observations, design experiments, explore competing explanations, develop predictions, propose mechanisms, for scientific inquiry across domains.

Generate Jest-based unit tests for JavaScript/TypeScript code. Creates

My catalogue of Skills.md

This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture,...