Automation
Task automation and scripting
Video Downloader
by yousufjoyian
Claude agent skills and workspace configuration
handoff-skill
by maxoreric
Agent 间任务交接的 Skill。当需要把任务交给另一个 Agent 时触发。触发词：交接、handoff、交给、让 xxx 来处理。
todo-task-run
by gendosu
Execute tasks from TODO file - Generic task runner [/todo-task-run xxx]
opus-design-question
by ddaanet
Consult Opus for design and architectural decisions. REQUIRED instead of AskUserQuestion. Triggers on approach choices (A vs B), trade-off analysis, pattern selection, or structural decisions — use this skill to consult Opus instead of asking the user. Only ask the user for subjective preferences, business logic, scope changes, or unclear requirements.
orchestration
by BaxterCooper
This skill should be used when orchestrating complex tasks, decomposing work into atomic units, dispatching to subagents, verifying outputs, or when discussing task verification and deviation tracking patterns.
task
by wintree86
Task tracker -- track progress and verify implementation directly on plan.md. 범용 프로젝트 태스크 관리. plan 문서에서 진행률 추적, 현황 요약. Triggers: /task, "task", "태스크", "progress", "진행률", "진행 상황"
meeting-notes
by spoonbobo
Turn meeting transcripts into structured notes with action items, then optionally create tasks and post summaries to team channels.
rails-active-job
by shivamsinghchahar
Master Active Job framework for asynchronous background job processing. Use when building background workers, handling async operations, managing job queues, scheduling recurring tasks, or processing long-running operations. Covers job definition, Solid Queue backend, error handling, and advanced patterns.
data-engineering-storage-remote-access-integrations-pyarrow
by legout
"Using PyArrow's parquet and dataset modules with remote filesystems (S3, GCS, Azure). Covers native filesystems, fsspec bridge, and obstore wrapper."
code-reviewer
by nimeshgurung
Comprehensive code review skill for TypeScript, JavaScript, Python, Swift, Kotlin, Go. Includes automated code analysis, best practice checking, security scanning, and review checklist generation. Use when reviewing pull requests, providing code feedback, identifying issues, or ensuring code quality standards.
agent-guardrails
by GaBySuGy
"Stop AI agents from secretly bypassing your rules. Mechanical enforcement with git hooks, secret detection, deployment verification, and import registries. Born from real production incidents: server crashes, token leaks, code rewrites. Works with Claude Code, Clawdbot, Cursor. Install once, enforce forever."
generate-more-skills-with-claude
by Olino3
Forge is a marketplace for a Claude Code Plugins
scriptwriting
by bmcgauley
Comprehensive scriptwriting skill for creating engaging, natural scripts across all mediums including educational videos, podcasts, presentations, documentaries, and narrative content. This skill should be used when developing scripts for any spoken or visual medium, applying storytelling principles, educational scaffolding, and natural human speech patterns while avoiding AI writing clichés.
ASCN operator
by ascnai
Deterministic workflow lifecycle and tool-export operator for ASCN workspace MCP control tools.
model-router
by oyi77
Intelligent model routing via subagents - automatically spawn the right model for each task complexity
ntfy-notify
by gitstua
Send push notifications via ntfy.sh with a lightweight shell workflow. Use when posting alerts, job status updates, reminders, or automation results to an ntfy topic using token auth or public topics.
openclaw-agent-architect
by ghively
Design, build, tweak, and audit OpenClaw (Molty / Clawdbot) agents end-to-end — SOUL.md, AGENTS.md, workspace bootstrap, memory, skills, plugins, tool policy, multi-agent routing, sandbox and exec approvals, heartbeats, standing orders, and security audits of community skills or plugins from ClawHub or npm. Trigger on any OpenClaw-related work, on edits to persona / operating-instruction / SOUL / AGENTS / MEMORY / HEARTBEAT files, on SKILL.md authoring, on audits of third-party skills or plugins, and whenever a user is building or debugging a self-hosted chat-based AI agent on WhatsApp / Telegram / Discord / Slack. Do not answer from training memory — this system evolves rapidly with non-obvious precedence rules.
plan
by wintree86
Plan document manager -- create, modify, and organize plan.md with Phase/task structure. 기획서(plan.md) 자동 생성/추가/수정 스킬. Triggers: /plan, "create plan", "기획서", "plan 생성", "Phase 추가"
sytex
by Sytex
Connect to Sytex platform API. Use when user mentions Sytex, app, claro, ufinet, dt, adc, atis, exsei, integrar, torresec, or app_eu instances. Handles tasks, projects, forms, materials, organizations, and chats.
using-superpowers
by Jackiexiao
（中文）Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
yt-outline
by naveedharri
Build detailed step-by-step YouTube video outlines with demo prep, screen-share sequences, and visual
tinker-api
by dinequickly
Guide for using the Tinker API for LLM training. Use when working with Tinker training workflows, RL environments, supervised fine-tuning, model sampling, rendering, or any Tinker API operations.
itdog
by Ramses1984
itdog.cn 网络测速工具 API 客户端。支持 Batch Ping 批量测速和 HTTP 网站测速。 使用场景: (1) 从全国/海外节点 Ping 测试 IP/域名延迟 (2) HTTP 网站响应测速 (3) Cloudflare CDN 节点优选 (4) 网络质量诊断 触发词: itdog, 网络测速, ping测试, 批量ping, http测速, cloudflare优选, 延迟测试
cited-research
by jewzaam
Produces citation-backed research documents with independent verification. Every claim traces to a web source visited in-session, and isolated sub-agents audit the output. Supports both new research and updating existing research topics (re-researching stale dimensions, adding new dimensions, refreshing citations). Use this skill whenever the user asks for research, analysis, comparisons, rubrics, updates to existing research, or any deliverable that must be grounded in cited sources. Trigger on phrases like "find out", "compare", "is X better than Y", "what are the tradeoffs", "give me the real numbers", "cite your sources", "verify this", "what does the research say", "update the research", "refresh this research", or any task where unsupported claims would undermine trust. Always use for non-code research requiring factual grounding, even if the user doesn't explicitly request citations.