Agents
AI agents and automation
videocut-self-update
by zrt-ai-lab
自更新 skills。记录用户反馈，更新方法论和规则。触发词：更新规则、记录反馈、改进skill
cf-tunnel
by Dwsy
Cloudflare Tunnel 一键管理工具，支持统一 Bun CLI（share + panel 合并）、端口自动避让、状态检查与自解释文档
server-status-push
by Dwsy
"检查 Linux 服务器健康状态并汇总发送给用户（支持一键文本报告）"
ralph-loop-gen
by Dwsy
"任务管理系统模板生成器 - 根据用户输入或JSON配置生成完整的任务管理结构（模板生成器，非直接执行器）"
agent-browser
by Dwsy
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
workhub
by Dwsy
工作文档枢纽，强制执行 SSOT（Single Source of Truth）原则，管理 docs/ 目录下的架构决策、设计文档、Issues（任务规划）、PRs（变更记录）。支持 GitHub 协作开发模式。
output-style-manager
by Dwsy
读取和写入输出风格目录的工具技能。当用户需要：（1）读取输出风格文件，（2）写入/创建输出风格文件，（3）管理输出风格目录，（4）解析风格文件格式时使用。
exa
by Dwsy
使用 Exa.ai API 进行高质量的互联网搜索。需要 EXA_API_KEY 环境变量。
faion-claude-code
by faionfaion
"Claude Code: skills, agents, hooks, commands, MCP servers, IDE integrations."
portfolio-project-architect
by ChunkyTortoise
"Transform service catalog into high-ticket portfolio assets with memory-persistent scoping and optimized Auto Claude handoff generation"
portfolio-project-architect-enhanced
by ChunkyTortoise
"Advanced portfolio development with Claude Code 2.1.0 agent lifecycle management, hot-reloadable skills, and parallel processing optimization"
ref-toon-format
by cuioss
TOON format knowledge and usage patterns for agent communication and memory persistence in plan-marshall marketplace
using-vit
by solpbc
Helps coding agents use vit to discover, follow, skim, and ship software capabilities (caps) over ATProto. Activates when the user mentions vit, beacons, caps, shipping, skimming, following, vetting, or social coding.
upstash-workflow-js
by upstash
Lightweight guidance for using the Upstash Workflow SDK to define, trigger, and manage workflows. Use this Skill whenever a user wants to create workflow endpoints, run steps, or interact with the Upstash Workflow client.
ralph
by kv0906
Set up and run Ralph Wiggum loop - autonomous AI coding with clean slate iterations, PRD-driven features, and CI quality gates. Use for long-running autonomous coding tasks.
ibook-builder
by Ibook000
ibook 的工程 builder 视角与执行协议。基于当前仓库中原始人格文档、GitHub 公开资料与项目、 简历履历、以及 Notion 中近期学习笔记蒸馏而成。用途：当用户提到「用 ibook 的方式」 「按 ibook 的思路」「切到 ibook 模式」「别空谈，直接做成能跑的系统」时使用。 适合 AI 应用开发、Python 后端、Agent / MCP / Skill 设计、自动化工具、交易系统、 Web 后台、AIoT 与部署落地场景。这个版本面向公开仓库，既给人看，也给模型用。
Diagrams Generator Skill
by anton-abyzov
Generate Mermaid diagrams following C4 conventions. Activates for create diagram, draw diagram, visualize, system diagram, architecture diagram, C4 diagram, context diagram, container diagram, component diagram, sequence diagram, ER diagram, entity relationship, data model, deployment diagram. Coordinates with diagrams-architect agent.
Architect
by anton-abyzov
System architect for scalable technical designs and ADRs. Use for system architecture, microservices, database design, trade-off analysis, component diagrams, tech selection.
ask-council
by doodledood
Multi-model ensemble consultation. Runs 3 models in parallel for diverse perspectives.
olore-agentskills-latest
by olorehq
Local Agent Skills documentation reference (latest). Use when asked about the Agent Skills format, creating skills, SKILL.md specification, or integrating skills into agents.
second-opinions
by vinta
Use when wanting independent review from external models before merging, committing, or finalizing architecture or plan decisions, or when the user asks for a second opinion, codex review, or gemini review
InDesign
by SFKislev
Control Adobe InDesign from the shell via Flue - ExtendScript bridges without an MCP server.
optimize-plugin
by FradSer
This skill should be used when the user asks to "validate a plugin", "optimize plugin", "check plugin quality", "review plugin structure", or mentions plugin optimization and validation tasks.
plugin-best-practices
by FradSer
Validates Claude Code plugins against architectural best practices for Agents, Skills, MCP, and Progressive Disclosure. Use when validating plugin structure, reviewing manifest files, checking frontmatter compliance, or verifying tool invocation patterns.