Skill Directory

AI Skill Directory

Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.

personjakexiaoAPI key: unconfirmed

loom-team-manager

Act as Team Manager for Loom team, handling ticket workflow when team commands may be unavailable

download20deployed_code—star123
personjakexiaoAPI key: unconfirmed

slim-code-of-conduct

Create and implement code of conduct and collaboration policies using Contributor Covenant standards, with specialized templates for scientific research environments and academic citation. Use when es…

download20deployed_code—star123
personnvwuzaishuohuangAPI key: unconfirmed

多智能体开发

Initialize a multi-agent development system for any project. Auto-detects language/framework, creates agent templates based on user selection, orchestrator prompt, and project documentation structure.…

download20deployed_code—star0
personzkevinyAPI key: unconfirmed

多Agent安全协作(单设备)

基于 MGC 的单设备多 Agent 任务链协作方法论,通过主 Agent 调度、脚本角色编写、执行 Agent 执行,实现敏感资源零暴露的安全协作。

download19deployed_code—star0
personjakexiaoAPI key: unconfirmed

agents-md

Create and maintain AGENTS.md files for services, components, and subagents with scoped skill references and hierarchical context. Trigger: When creating AGENTS.md for a new service or component, upda…

download19deployed_code—star0
personjakexiaoAPI key: unconfirmed

research-driven-planning

Loop 1 of the Three-Loop Integrated Development System. Research-driven requirements analysis with iterative risk mitigation through 5x pre-mortem cycles using multi-agent consensus. Feeds validated, …

download19deployed_code—star221
personjakexiaoAPI key: unconfirmed

citation-verification

This skill provides reference guidance for citation verification in academic writing. Use when the user asks about "citation verification best practices", "how to verify references", "preventing fake …

download19deployed_code—star1.7K
personjakexiaoAPI key: unconfirmed

one-on-ones

Transform the most important meeting on your calendar. Master the art of 1:1s that build trust, develop people, and surface problems before they become crises. Use when: **New manager** learning to ru…

download19deployed_code—star35
personjakexiaoAPI key: unconfirmed

software-product-manager

Expert software product manager who works directly with stakeholders to understand their needs and create comprehensive product specifications. Use when users need help designing software, defining re…

download20deployed_code—star123
personStevenZhao26API key: unconfirmed

security-supervisor

安全与隐私监督员 — 全流程盯防隐私泄露、敏感信息、数据合规、权限审计

download19deployed_code—star0
personjakexiaoAPI key: unconfirmed

rss-automation

RSS feed aggregation and monitoring. Parse RSS/Atom feeds, filter entries, track new items, and integrate with notification channels for automated content monitoring.

download19deployed_code—star19
personjakexiaoAPI key: unconfirmed

using-superpowers

Use when starting any conversation. Establishes how to find and use skills, requiring skill invocation before any response.

download19deployed_code—star460
personjakexiaoAPI key: unconfirmed

skill-creation-guide

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, workfl…

download19deployed_code—star220
personjakexiaoAPI key: unconfirmed

skill-learning

Extracts actionable knowledge from external sources and enhances existing skills using a 4-tier novelty framework. Use when learning from URLs, documentation, or codebases. Proactively use when the us…

download19deployed_code—star0
personjakexiaoAPI key: unconfirmed

claude-skill-spec-audit

Audit skill SKILL.md files for compliance with the agentskills.io specification. Checks frontmatter fields (name, description, compatibility, metadata, argument-hint) and metadata sub-fields (author, …

download19deployed_code—star4
personjakexiaoAPI key: unconfirmed

reflect-skill

A skill for reflection and summary. It is triggered when a review is needed after a task is completed or failed. Trigger words: 反思, 复盘, 总结, reflect, 回顾, lessons learned.

download20deployed_code—star118
personjakexiaoAPI key: unconfirmed

Subagent System

Create and manage specialized Claude Code subagents for task-specific workflows. Use when delegating work to specialized agents, configuring agent permissions, or understanding subagent architecture a…

download20deployed_code—star0
personalexfengruiAPI key: unconfirmed

AI 自动知识工作台 Lite

让 AI 自动把一个用户授权的 Markdown 或 Obsidian 工作区构建为 Metadata-only 知识索引和离线 HTML 驾驶舱,并支持按需增量更新;默认不修改事实源,也不把笔记正文发送给模型。

download19deployed_code—star0
personjakexiaoAPI key: unconfirmed

auto-loop

Work autonomously on a task until it is complete or the human stops you, without pausing to ask permission between steps. Use when user says "/auto-loop", "loop forever", "keep going", "run overnight"…

download19deployed_code—star4
personjakexiaoAPI key: unconfirmed

template-skill

Replace with description of the skill and when Claude should use it.

download19deployed_code—star13
personjakexiaoAPI key: unconfirmed

Management

Management principles, team leadership, and organizational effectiveness.

download19deployed_code—star1
personjakexiaoAPI key: unconfirmed

todo-output-template

TODO.md file output template examples for todo-task-planning command. Provides structured checklist format with task classification, status indicators, and research rationale.

download19deployed_code—star0
personjakexiaoAPI key: unconfirmed

orchestrator

Role orchestration system for AI agents. Each role delegates to its subordinates and uses skills from skills.sh. Base skills for all roles - find-skills (search) and skill-creator (create).

download19deployed_code—star0