Agent 工作流

toutiao-publisher

30agent-workflows

Publish or prepare articles for Toutiao/头条号, check or restore shared login state, fill Markdown drafts with inline images and covers, and optionally complete final publishing. Use for requests such as 发布到头条、检查头条登录、填充头条草稿、上传图文、人工审核 or explicitly authorized automatic publishing.

guanyang

create-agent

29agent-workflows

Bootstrap a modular AI agent with OpenRouter SDK, extensible hooks, and optional Ink TUI

openrouterteam

create-agent

29agent-workflows

Bootstrap a modular AI agent with OpenRouter SDK, extensible hooks, and optional Ink TUI

openrouterarchived

rivet-agentos

29agent-workflows

agentOS: A computer for every agent.

rivet-dev

superwall

28agent-workflows

使用 `superwall` CLI 管理应用、产品、权益、活动、付费墙、App Store Connect 和 ClickHouse 分析。还包括文档查询、仪表盘链接、SDK 源码检查以及集成、迁移、审查和仪表盘工作流。用于 Superwall API 或 CLI 任务、数据分析、SDK 设置、提供商迁移、Webhook 事件和 SDK 调试。

superwall

superwall-editor

28agent-workflows

Build and edit live Superwall paywalls from the CLI. Attach to a running browser editor session using a pairing code, list the tools the browser exposes right now, and invoke them. Covers native sw-* elements, editing workflow, design standards, and the attach/call/release lifecycle. Use whenever the user wants to design, build, modify, or review a Superwall paywall, onboarding, or web2app flow.

superwall

nx-plugins

27agent-workflows

Find and add Nx plugins. USE WHEN user wants to discover available plugins, install a new plugin, or add support for a specific framework or technology to the workspace.

nrwl

link-workspace-packages

27agent-workflows

Link workspace packages in monorepos (npm, yarn, pnpm, bun). USE WHEN: (1) you just created or generated new packages and need to wire up their dependencies, (2) user imports from a sibling package and needs to add it as a dependency, (3) you get resolution errors for workspace packages (@org/*) like "cannot find module", "failed to resolve import", "TS2307", or "cannot resolve". DO NOT patch around with tsconfig paths or manual package.json edits - use the package manager''s workspace commands to fix actual linking.

nrwl

mcp-configure

25agent-workflows

Configure the LaunchDarkly hosted MCP server during onboarding. Use when the parent LaunchDarkly onboarding skill reaches Step 4 (MCP). Supports Cursor, Claude Code, Windsurf, GitHub Copilot, and other MCP-compatible agents. OAuth authentication; no API keys for the hosted server.

launchdarkly

investigate-anything

22agent-workflows

Start-here router and tradecraft baseline for any investigation into a person, company, domain, image or selector. Sets authorised scope, turns a vague request into an answerable intelligence question, writes a collection plan, picks the right workflow for the starting selector, and applies source grading and competing-hypothesis discipline. Use for "investigate this person or company", "do OSINT on X", "where do I start", or any open-source intelligence, due diligence, background or attribution task. Applies across due diligence, fraud, threat intelligence, journalism and compliance. Reference at useosint.com/skills/investigate-anything.

useosint

video-outpainting

21agent-workflows

agentspace-so

controlnet-pose

21agent-workflows

通过 `runcomfy` CLI 在 RunComfy 上进行姿态条件生成。路由涵盖 Kling 2-6 Motion Control Pro/Standard（将参考视频的动作/分镜转移到目标角色）、社区 Wan 2-2 Animate（带姿态条件的音频驱动角色动画）以及 Z-Image Turbo ControlNet LoRA（基于 OpenPose/DWPose/canny/深度控制图像进行姿态条件图像生成）。根据视频与静态、风格化与逼真度选择正确路由。触发词包括 "controlnet"、"control net"、"pose control"、"openpose"、"DWPose"、"transfer pose"、"motion control"、"pose driven"、"character pose"、"depth control"、"canny edge"、"use this pose"，或任何明确要求基于姿态/骨架/运动/深度/canny 参考进行生成。

agentspace-so

investigate-anything

21agent-workflows

useosint

mcp-configure

20agent-workflows

在引导过程中配置 LaunchDarkly 托管的 MCP 服务器。当父级 LaunchDarkly 引导技能到达步骤 4（MCP）时使用。支持 Cursor、Claude Code、Windsurf、GitHub Copilot 以及其他兼容 MCP 的代理。使用 OAuth 认证；托管服务器无需 API 密钥。

launchdarkly

speakturbo-tts

20agent-workflows

Give your agent the ability to speak to you real-time. Talk to your Claude! Ultra-fast TTS, text-to-speech, voice synthesis, audio output with ~90ms latency. 8 built-in voices for instant voice responses. For voice cloning, use the speak skill.

emzod

day1-onboarding

AI Native Camp Day 1 온보딩. Claude와 대화하면서 Claude Code를 익힌다. "1일차", "Day 1", "온보딩" 요청에 사용.

day3-clarify

AI Native Camp Day 3 Clarify & GitHub. Clarify 플러그인으로 모호한 요구사항을 명확하게 만들고, 나만의 스킬을 만들고, PRD를 작성하여 GitHub에 첫 PR을 제출한다. "3일차", "Day 3", "clarify", "클래리파이", "PRD", "GitHub" 요청에 사용.

day4-wrap-and-analyze

AI Native Camp Day 4 Wrap & Analyze + 콘텐츠 소화. session-wrap 스킬을 직접 만들고, history-insight와 session-analyzer로 세션을 분석하고, 콘텐츠 소화 파이프라인을 체험한다. "4일차", "Day 4", "wrap", "세션 분석", "session wrap", "세션 래핑", "fetch", "콘텐츠" 요청에 사용.

session-analyzer

This skill should be used when the user asks to "analyze session", "세션 분석", "evaluate skill execution", "스킬 실행 검증", "check session logs", "로그 분석", provides a session ID with a skill path, or wants to verify that a skill executed correctly in a past session. Post-hoc analysis of Claude Code sessions to validate skill/agent/hook behavior against SKILL.md specifications.