creating-skills
Expert knowledge on creating Agent Skills for Claude Code. Use when designing or creating SKILL.md files, understanding Skill structure, or implementing progressive disclosure patterns.
Boost efficiency with task automation and organizers.
Expert knowledge on creating Agent Skills for Claude Code. Use when designing or creating SKILL.md files, understanding Skill structure, or implementing progressive disclosure patterns.
Comprehensive data science, machine learning, and AI guide covering Python, deep learning, NLP, LLMs, prompt engineering, and MLOps. Use when building AI models, data pipelines, or machine learning systems.
Publish and share Claude Artifacts with Projects, Cursor, and downstream agents. Use when a user wants to "save", "share", or "finalize" a generated artifact.
Captures valuable insights and documents them in CLAUDE.md. Auto-triggers when: discovering gotchas or unexpected behavior, completing significant features, fixing complex bugs, making architectural decisions, having "aha moments", or when someone says "I wish I'd known this earlier".
Create or update Claude skills with specialized knowledge and workflows. Use for new skills, skill references, skill scripts, optimizing existing skills, extending Claude's capabilities.
タスクの性質を LLM ベースで深く分析し、適切な executor(claudecode/codex/coderabbit/user)を判定する専門 Skill。キーワードベースの単純判定を置き換える。
Analyze Context Lake entities and fix frontmatter issues. Use when asked to run frontmatter cleanup, fix missing fields, validate frontmatter against schema, or standardize entity metadata.
Use to identify and prepare the next logical story based on project progress. Creates comprehensive story files with full technical context.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
This skill should be used when the user asks to 'extract a skill from a conversation', 'convert conversation to skill', 'create skill from chat history', 'generate skill from session', or mentions extracting reusable workflows from Claude Code conversations. Uses Fabric AI patterns to distill conversations into actionable skills.
Reviews Claude configuration files for security, structure, and prompt engineering quality. Use when reviewing changes to CLAUDE.md files (project-level or .claude/), skills (SKILL.md), agents, prompts, commands, or settings. Validates YAML frontmatter, progressive disclosure patterns, token efficiency, and security best practices. Detects critical issues like committed settings.local.json, hardcoded secrets, malformed YAML, broken file references, oversized skill files, and insecure agent tool access.
Use this agent for audits, debugging nasty bugs, deep research, getting second opinions on approaches, reviewing commits for correctness, or analyzing complex problems. Invoke when you need advanced reasoning about difficult issues. Use PROACTIVELY when encountering complex bugs, architectural decisions, or when a thorough review would prevent future issues.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Manage persistent notes and todos using the nb note-taking system. This skill should be used when capturing cross-session learnings, technical decisions, deferred tasks, or codebase patterns that should persist beyond the current conversation. Use proactively after solving bugs, making architectural decisions, or discovering important patterns. Triggers on requests like "what did I learn yesterday", "check my notes", "what learnings do I have about X", or "capture insights". Do NOT use for tracking current work-in-progress (use TodoWrite for that).
Use this skill when asked to "create a plugin", "build a new plugin", "make a Claude Code plugin", "scaffold plugin", "plugin structure", "add commands/agents/skills/hooks to plugin", or when helping with plugin development.
Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.
Guide for creating effective skills. Use when users want to create or update a skill that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Expert guidance for interacting with Azure AI Search using the REST API. Use this skill when you need to create, manage, or query search indexes, knowledge bases, knowledge sources, upload documents, perform full-text/vector/hybrid searches, or implement agentic retrieval via REST. Covers data plane operations for the 2025-11-01-preview API version.
Meta-skill that learns new capabilities from NPM and pip package registries. Use when user asks to integrate with a service (e.g., "I need to use Asana"), mentions an API we don't have a skill for, or explicitly invokes "/skill upskill <package>". Automatically searches NPM and pip, installs packages globally to ~/.claude/, and generates skill documentation. DEFAULT: Any time system needs to use an API, check package registries first.