Boost efficiency with task automation and organizers.
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 and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to "run" any process. Also handles Perplexity-based research and Google Sheets data tracking.
Interactive plugin setup and scaffolding tool for Claude Code plugins. Use this skill when user asks to "create plugin", "new plugin", "scaffold plugin", "setup plugin", "initialize plugin", "add command", "add skill", "add agent", "add hook", "add MCP server", or mentions creating Claude Code plugin components.
Use PROACTIVELY when creating Model Context Protocol servers for connecting AI applications to external data sources, tools, and workflows. Generates production-ready MCP servers with TypeScript/Python SDKs, configuration templates, and Claude Desktop integration. Includes testing workflow with MCP Inspector. Not for modifying existing MCP servers or non-MCP integrations.
Save notes, ideas, and content directly to Notion database. Use when Claude needs to persist conversation insights, trading notes, research findings, or any content to Notion for later reference. Triggers on phrases like "save to notion", "记录到notion", "add to my notes database".
Jeff Su's AI-Native Workflow framework (4 Habits) mapped onto Nebuchadnezzar v3.4 pipeline infrastructure. Use when: (1) "swipe file" or "what worked before" - retrieve proven email patterns by stage (2) "task mapping" or "M/AI split" or "YOU vs AI" - get decisions for stage transitions (3) "breadcrumb" or "anchor this" - link conversations to HubSpot + Git deal folders (4) "prompt library" or "battle-tested" - access working slash commands (5) "Blue Pill" - customer-facing communication (emails, proposals) (6) "Red Pill" - internal analysis (PLD, Brand Scout, Deal Snapshot) (7) Stage transitions [00→01], [02→03], [04] follow-ups, [08→09] win-backs Triggers on: "ai-native", "4 habits", "swipe", "winning email", "what worked", "task mapping", "YOU vs AI", "blue pill", "red pill"
Guides users through creating new Claude Code skills using the agent-skill-npm-boilerplate template. Use when users want to create a new skill, build a skill, make a skill, or learn how to create skills.
Guide for creating multi-phase skills with orchestrated sequential execution. Use when user wants to create a skill that runs multiple steps in sequence (like gap-finder), needs a start-* orchestrator pattern, or asks about multi-step/multi-phase skill architecture.
Automatically extracts learnings from conversation history and appends them to CLAUDE-guardrail.md. Categorizes content into Project Specs, Error Response, Coding Rules, and Tips to prevent repeated mistakes.
Consolidate learnings from action logs into project docs and skills. Use when user asks to "consolidate", "compile learnings", "summarize sessions", or update project knowledge from .claude/action-log.jsonl.
This skill should be used when the user asks to "collaborate with Codex", "use Codex for planning", "get Codex review", "delegate to Codex", "Codexと協調", "Codexにレビューを依頼", "Codexに計画を作成させたい", or mentions coordinating tasks between Claude Code and Codex CLI.
Generate prompt variations from templates. Use when creating new commands, skills, or workflows.
IDE integration tips for VS Code, JetBrains, and terminal workflows. Use when setting up Claude Code with your IDE, configuring keybindings, optimizing terminal workflows, or synchronizing file navigation. Covers extensions, split terminals, clipboard, and diff viewing.
n8n workflow automation for building analytics including SkySpark multi-agent systems, FastAPI tool servers, workflow orchestration, and automated building system alert triage
Plan execution skill with subagent parallelization, checkpoint/rollback, TodoWrite tracking, and intelligent agent routing. Triggers on execute-plan, run plan, implement plan, execute tasks.
Search past Claude Code conversation history. Use when asked to recall, find, or search for anything from previous conversations - including content discussed, links shared, problems solved, topics covered, things posted, or work done together. Triggers include "what did we do today", "summary of our work", "what did we work on", "from our conversations", "what did we discuss", "which X was about Y", "recall when we", "find where we talked about", "search history", "what did I share/post/send you about", "how did we fix", or any reference to past sessions or collaborative work.
Chrome DevTools for AI agents. Control and inspect live Chrome browsers with performance tracing, network inspection, DOM snapshots, and automated interactions. Use for web debugging, performance analysis, and browser automation.
This skill should be used when the user asks to "design MCP tool", "create tool schema", "tool best practices", "input validation", "output schema", "error handling for tools", or discusses designing individual MCP tools with proper schemas and responses.
Fast automation platform error resolver for Power Automate, n8n, Make, Zapier and other platforms. Handles common patterns like 401/403 auth errors, 429 throttling, and data format issues. Provides immediate fixes without deep research for well-known error patterns. Use when error matches common scenarios (status codes 401, 403, 404, 429, timeout, parse JSON failures). For complex or unknown errors, defer to automation-debugger skill. When the user outputs some code/json snippets and ask for a quick fix, this skill will provide immediate solutions.
Capture brainstorm discoveries that aren't in the plan — the thinking that makes this project unique
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 modes", "primary agent", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for OpenCode.
