skill-authoring
Best practices for writing Claude Code skills and agents. Use when creating, improving, or troubleshooting SKILL.md or agent files.
Essential command-line tools and system utilities.
Best practices for writing Claude Code skills and agents. Use when creating, improving, or troubleshooting SKILL.md or agent files.
This skill should be used when discussing "templates", "apply template", "which template to use", "template selection", "note structure", or when helping users choose appropriate templates for different note types.
Help me create a Claude Code hook. Interviews about what to catch, then generates PreToolUse or PostToolUse hook.
Expert guidance for building production-ready tool-calling agents with Databricks Mosaic AI Agent Framework. Use when users need to create agents that orchestrate multiple data sources or APIs, implement LangChain-based agentic workflows, design Foundation Model-powered tool selection, optimize agent prompts and decision-making, or architect multi-tool agent systems. Covers agent architecture patterns, tool design best practices, Foundation Model integration, and common pitfalls.
This skill should be used when the user asks to "triage an issue", "evaluate a feature request", "should I accept this issue", "analyze GitHub issue", "review this pull request", "review this PR", "should I merge this PR", "is this PR ready", "code review this", "review this contribution", "is this in scope", "how should I respond to this issue", "decline this request", "accept this contribution", "find similar bugs", "detect patterns", "root cause analysis", "fix this bug comprehensively", "give feedback on this PR", "is this secure", "security review", or discusses whether to accept, reject, adapt, defer, merge, or redirect an external contribution (issue or PR) to a project.
Copy or sync Claude skills from ~/.claude/skills into ~/.codex/skills so they are available in Codex. Use when asked to import, migrate, copy, or sync Claude skills, or when moving skills between Claude and Codex with optional repeatable sync.
Configuring Claude Code settings.json & Security. Set up permissions (allow/deny), permission modes, environment variables, tool restrictions. Use when securing Claude Code, restricting tool access, or optimizing session settings.
Persistent context management system for web developers that never loses work between Claude Desktop sessions. Features automatic context backup, work session continuity, project state management, and comprehensive error recovery.
Эксперт по API reference документации. Используй для создания справочников по API, описания endpoints и примеров запросов.
Creating and Managing Sub-agents in Claude Code. Design agent personas, define proactive triggers, set tool permissions, structure agent files. Use when building specialized agents for code review, debugging, architecture, or domain-specific tasks.
Use when creating Claude Code plugins, writing skills, building commands, developing agents, or asking about "plugin development", "create skill", "write command", "build agent", "SKILL.md", "plugin structure", "progressive disclosure"
This skill should be used when the user asks to "create an OpenCode tool", "build an OpenCode plugin", "write a custom tool for OpenCode", "use @opencode-ai/sdk", "use @opencode-ai/plugin", "integrate with OpenCode", "create OpenCode hooks", "define tool schema", "use tool.schema", "work with OpenCode sessions", or needs guidance on OpenCode SDK patterns, plugin development, or custom tool creation.
Propose structured interpretations of underspecified requests. Use when a user's request is vague or incomplete but reasonable assumptions can be made. Rapidly prototypes intent by restating, structuring, and committing to a next action.
Setup and manage OpenAI Codex CLI authentication including ChatGPT Plus/Pro OAuth, API keys, and multi-account management. Use when configuring Codex access, switching accounts, or troubleshooting authentication.
Orchestrate autonomous agent teams to complete complex tasks. PM dynamically selects specialized agents based on task classification and enforces non-negotiable principles. Supports local and remote agents, persistent sessions, and continuous learning through skills.
Intelligently routes requests to the correct context instructions and documentation files. Use this skill to determine which AGENT.md, guide, or technical instruction file is most relevant for a user's request.
Auto-generated CLI patterns using Google Fire with class-based structure, docstring parsing, and nested classes. Use when building Python CLI applications, creating Fire CLIs, implementing auto-generated commands, designing class-based CLIs, or when user mentions Fire, Google Fire, CLI generation, docstring commands, nested command groups, or Python command-line tools.
End-to-end automated daily competition workflow. Orchestrates scrape, analyze, compose, and notify skills - all unattended for cron execution.
Create new specialized agent. Use when user wants reusable agent for repetitive pattern. Examples: code-reviewer, linter, doc-generator.
Enables Claude to interact with Gemini AI chat for quick queries, brainstorming, and alternative AI perspectives
Search local Claude Code documentation to answer implementation questions. Use when asked about Claude Code features, subagents, workflows, skills, hooks, MCP servers, plugins, settings, CLI options, headless mode, or any Claude Code capability.