SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags

citadel
A single-session meta-orchestrator that parses a direction, chains existing skills, and executes multi-step tasks end-to-end without unnecessary user prompts.

box
Work with the @upstash/box SDK for sandboxed cloud containers with AI agents, shell, filesystem, and git. Use when building with Upstash Box, creating sandbo...

agent-skills
Expert knowledge for Azure Blob Storage development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, int

git-context-controller
Lean, git-backed agent memory tool that stores commit hashes + intent and provides COMMIT/BRANCH/MERGE/CONTEXT commands to reconstruct context on demand.

skills
运维 Hermes Agent 的实战 skill。适用于用户提到“运维 hermes”“排查 hermes 问题”“gateway 异常”“平台掉线”“cron 不执行”“profile 配置混乱”“skills 或 tools 不生效”“想让其他 agent 帮忙维护 hermes”时使用。基于 hermes...

claude-skill-registry
Guidelines for creating and running Claude Code CLI agents: agent JSON format, storage conventions, and execution commands.

senpai-skill
Distill a graduated lab senior into an AI Skill. Import chats, meeting notes, photos, and screenshots to build Group Memory + Persona with continuous...

officecli
A comprehensive CLI for reading, editing, validating, and automating .docx, .xlsx, and .pptx files — designed for AI agents to inspect, modify, and generate Off

claude-skill-registry
Agent orchestration library for conversational AI — coordinates LLM completions, memory, tool execution, and multi-turn flows; useful for building chat agents a

parchi
Run a local relay daemon and browser extension to control real browsers via JSON-RPC/WebSocket; includes CLI for listing agents, calling tools, and running task

tackline
Run multi-step research and analysis chains (gather, distill, rank, verify, plan) automatically; choose and orchestrate primitives based on a user goal.

citadel
Orchestrate parallel campaigns in waves: spawn isolated agents/worktrees, coordinate discoveries, validate results, and merge work — for multi-stream engineerin

reactant
A router skill that scans files for <@skill: ...> tags and dispatches each tag's prompt to the matching subagent, enabling modular in-file workflows.