Prompts
Prompt engineering and templates
audit-context-building
by runkids
Enables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding.
consumption-tax
by kazukinagata
This skill should be used when the user needs to calculate consumption tax (消費税) or determine their tax method (2割特例, 簡易課税, or 本則課税). Trigger phrases include: "消費税を計算", "消費税の申告", "消費税申告書", "2割特例", "簡易課税", "本則課税", "課税売上", "消費税額", "インボイス", "みなし仕入率", "課税仕入".
invoice-system
by kazukinagata
This skill should be used when the user asks about the invoice system (インボイス制度), qualified invoices (適格請求書), registration numbers (登録番号), input tax credits (仕入税額控除), the 20% special measure (2割特例), the 30% special measure (3割特例), tax-exempt businesses (免税事業者), transitional measures (経過措置), small-amount exceptions (少額特例), corrected invoices (修正インボイス), or any related topics. Trigger phrases include: "インボイス", "適格請求書", "登録番号", "仕入税額控除", "2割特例", "3割特例", "免税事業者", "経過措置", "少額特例", "修正インボイス", "返還インボイス", "簡易インボイス", "インボイス登録", "T番号", "適格請求書発行事業者".
submit
by kazukinagata
This skill should be used when the user is ready to submit their tax return, needs a final review checklist, wants to know how to submit (e-Tax, mail, or in-person), or asks about common mistakes before submission. Trigger phrases include: "提出準備", "提出方法", "e-Taxで提出", "チェックリスト", "申告書の確認", "提出前の確認", "郵送で提出", "税務署に持っていく", "提出期限".
requirement-analysis
by FlameMida
提供系统化的 9 阶段需求分析与实施工作流（需求理解、代码探索、外部资源研究、澄清问题、深度分析、展示计划、实施开发、代码审查、总结）。适用于复杂功能开发、多方案对比、新技术栈研究等需要深度规划和完整实施的场景。当用户提出复杂功能开发、API设计、数据库设计且需要深度分析和外部资源研究时触发。
codex-claude-loop
by bear2u
Orchestrates a dual-AI engineering loop where Claude Code plans and implements, while Codex validates and reviews, with continuous feedback for optimal code quality
web-to-markdown
by bear2u
웹페이지 URL을 입력받아 마크다운 형태로 변환하여 저장합니다. 웹 문서를 로컬 마크다운 파일로 아카이빙하거나 정리할 때 유용합니다.
design-prompt-generator-v2
by bear2u
Advanced 7-step hierarchical design prompt generator for AI web development tools (Lovable, Cursor, Bolt). Generates domain-aware, user-journey-based design prompts with emotional design considerations. Triggers on "디자인 프롬프트", "웹 디자인", "Lovable 프롬프트", "랜딩페이지 만들어줘", or any AI web builder prompt requests.
메타-프롬프트-생성기
by bear2u
간단한 설명을 받아 단계별 병렬 처리가 가능한 구조화된 커스텀 슬래시 커맨드를 자동으로 생성합니다. 프롬프트 생성, 워크플로우 설계, 테스트 스위트 작성이 필요할 때 사용하세요.
codex-claude-cursor-loop
by bear2u
Orchestrates a triple-AI engineering loop where Claude plans, Codex validates logic and reviews code, and Cursor implements, with continuous feedback for optimal code quality
codex-claude-loop
by bear2u
Orchestrates a dual-AI engineering loop where Claude Code plans and implements, while Codex validates and reviews, with continuous feedback for optimal code quality
positioning-angles
by Salesably
Discovers differentiated market positioning using 8 proven frameworks. This skill should be used when launching a new product or service, entering competitive markets, refreshing stale positioning, or when current messaging sounds like every other competitor.
Claude Code X - Autonomous Execution Subagent
by ShunsukeHayashi
Execute Claude Code autonomously in the background for well-defined tasks, enabling parallel execution of up to 5 concurrent sessions while the user continues other work.
llm-council
by am-will
Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents.
iterion-dsl
by SocialGouv
Author, review, or debug Iterion .bot workflows and .botz bundles using the current indentation-sensitive DSL. Use for requests to create or change an Iterion workflow, design an agent graph, choose router/interaction/session modes, add tools or subbots, diagnose validation codes, or explain accepted .bot syntax.
skill-review
by dwarvesf
Review and promote skill drafts that skill-curator staged from past sessions. Use when the user runs /skill-review, says "review my skill drafts", "promote a staged skill", or asks what skills the self-improvement loop proposed. Lists drafts under ~/.claude/skill-proposals/, runs the writing-skills quality bar on each, then promotes the approved ones into ~/.claude/skills/ or rejects them.
alphaear-sentiment
by RKiding
Analyze finance text sentiment using FinBERT or LLM. Use when the user needs to determine the sentiment (positive/negative/neutral) and score of financial text markets.
session-reflect
by i9wa4
End-of-session retrospective skill. Collects today's commits and vault notes, analyzes friction patterns, and proposes improvements to CLAUDE.md and skills. Use when: - User says "session-reflect", "振り返り", or "今日の振り返り" - End of a work session - User asks for improvement proposals
agent-factory
by alirezarezvani
Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns
scrum-master-agent
by alirezarezvani
Comprehensive Scrum Master assistant for sprint planning, backlog grooming, retrospectives, capacity planning, and daily standups with intelligent context-aware reporting
hook-factory
by alirezarezvani
Generate production-ready Claude Code hooks with interactive Q&A, automated installation, and enhanced validation. Supports 10 templates across 7 event types for comprehensive workflow automation.
ask-claude
by ryoppippi
Consult Claude Code for a second opinion on implementation plans, code reviews, or problem-solving. Use when you want an independent perspective from a different AI agent before making significant decisions.
session-analytics
by spences10
Query Claude Code session analytics from ccrecall database. Use when user asks about token usage, costs, session history, or wants to analyze their Claude Code usage patterns.
codex-claude-cursor-loop
by bear2u
Orchestrates a triple-AI engineering loop where Claude plans, Codex validates logic and reviews code, and Cursor implements, with continuous feedback for optimal code quality