Prompts
Prompt engineering and templates
skill-creator
by mamba-mental
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.
llm-jailbreaking
by pluginagentmarketplace
Advanced LLM jailbreaking techniques, safety mechanism bypass strategies, and constraint circumvention methods
directory-tree-viewer
by djacobsmeyer
Display directory structure as a formatted tree. Use when the user needs to visualize a directory structure, analyze folder organization, or share a file tree view. Supports custom paths via the /tree command.
claude-context-manager
by AnthemFlynn
Enables autonomous context management for codebases through claude.md files. Use when creating, maintaining, or synchronizing AI agent context. Provides tools and workflows for monitoring context health, detecting staleness, and updating intelligently. Helps Claude work proactively as a context manager.
housekeeping
by jasonkneen
This skill should be used when users want to clean up, audit, or optimize their Claude configuration folders (~/.claude or .claude). It analyzes hooks, scripts, plugins, commands, and storage for token waste, redundancy, and optimization opportunities, then produces a prioritized action plan with before/after benefits.
sandbox-manager
by djacobsmeyer
Configure and manage Claude Code sandboxing for secure code execution. Use when user mentions sandboxing, security isolation, untrusted code, network restrictions, filesystem permissions, or wants to configure Claude Code security settings. Helps enable/disable sandbox mode, configure permissions, troubleshoot compatibility issues, and provide scenario-based configurations.
skill-developer
by mamba-mental
Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule.
agent-native-architecture
by hirefrank
Build AI agents on Cloudflare's edge using prompt-native architecture where features are defined in prompts, not code. Use when creating autonomous agents with Durable Objects, designing Workers services, implementing self-modifying systems, or adopting the "trust the agent's intelligence" philosophy on the edge.
code-ocr
by MHLiuLGY
使用百度 OCR 高精度含位置版将代码截图转换为文本文件，保持原始缩进。使用场景包括：(1) 将代码截图识别为可编辑文本，(2) 从截图提取代码，(3) 图片转代码文字。触发条件：用户提到"截图转文字"、"OCR"、"识别代码"、"图片转文本"、"code screenshot to text"
eld-sense-activation
by CAPHTECH
PCE (Process-Context Engine) のアクティブコンテキスト構築スキル。タスクに最適化されたコンテキストをコンパイルし、プロセス駆動の投入物を生成する。 トリガー条件: - 新しいタスクを開始する時（「この機能を実装して」） - AIにコード生成を依頼する時 - 複雑な問題解決に着手する時 - 「コンテキストを整理して」 - 「必要な情報をまとめて」
prompt-engineer
by P47Phoenix
Expert prompt optimization for LLMs and AI systems. Use PROACTIVELY when building AI features, improving agent performance, or crafting system prompts. Masters prompt patterns and techniques.
platform-setup
by Semprini
Use this skill when the user mentions VS Code, Claude Code, Copilot, or any IDE; asks about setup, installation, or configuration; asks "how do I use the agents"; asks "getting started with [platform]"; or needs help with platform-specific workflows, troubleshooting, or effective prompt patterns.
ralph-runner
by linuxlewis
Run Ralph Wiggum autonomous coding loops. Use when user asks to run ralph, start autonomous coding, execute a PRD, implement features from a task list, or wants Claude Code to work through user stories iteratively.
dual-code-review
by samChang72
Orchestrate a comprehensive code review process involving both Gemini (Antigravity) and Claude CLI, synthesizing a consensus report.
go-package-skill-creator
by ItalyPaleAle
Create skills for Go packages by fetching documentation from pkg.go.dev and generating structured SKILL.md files with usage patterns, examples, and best practices. Use when the user wants to create a skill for a specific Go package (e.g., "create a skill for github.com/lestrrat-go/jwx/v3") or needs to document how to use a Go library.
daily-knowledge-scrape
by JamesAtMoGroup
每天自動搜尋最新 AI 資訊，整理成繁體中文學習文章，並產出 Remotion 4K 影片；儲存至本地資料夾
skill-creator
by ThomasRohde
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
skill-creator
by huminglong
高效skill创建指南。当用户希望创建新的skill（或更新现有skill），以通过专业知识、特定工作流或工具集成来扩展 Claude 的能力时，应使用此项技能。
sac
by SeaVerseAI
Use sac (SeaArt CLI) to generate images, video, audio, and 3D assets, chat with LLMs, inspect task results, or manage SeaArt API credentials and config.
claude-code-pm
by cyberelf
Act as a Product Manager who gathers requirements and orchestrates Claude Code using OpenSpec protocol. Install proper skills, delegate to Claude Code in background mode, and validate completion while remaining responsive to user messages.
document-image-extractor
by MHLiuLGY
从 Word (.docx) 和 PDF (.pdf) 文档中提取图片并保存到指定文件夹。使用场景包括：(1) 从 Word 文档提取图片，(2) 从 PDF 文档提取图片，(3) 批量提取多个文档的图片，(4) 提取文档中的所有图片素材
system-prompt-clinic
by iamladi
Interactive skill that diagnoses and transforms system prompts from rule-based to reasoning-based using Constitutional AI principles
tdd
by iamladi
TDD enforcement during implementation. Reads tdd: setting from CLAUDE.md. Modes - strict (human approval for escape), soft (warnings), off (disabled). Auto-invoked by /implement.
judgment-eval
by iamladi
Evaluates agent judgment quality through scenario-based testing in-conversation