Agent 工作流

可复用的 Agent 工作流和编排模式

1330 個 Skills 可用

Skills 列表

nano-banana-pro-prompts-recommend-skill

nano-banana-pro-prompts-recommend-skill

1.8Kagent-workflows

Recommend suitable prompts from 10,000+ Nano Banana Pro image generation prompts based on user needs. Optimized for Nano Banana Pro (Gemini), but prompts also work with Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E, Flux, Stable Diffusion, and any text-to-image AI model. Use this skill when users want to: - Generate images with AI (any model — Nano Banana Pro, Gemini, GPT Image, Seedream, etc.) - Find proven AI image generation prompts and prompt templates - Get prompt recommendations for specific use cases (portraits, products, social media, posters, etc.) - Create illustrations for articles, videos, podcasts, or marketing content - Browse a curated prompt library with sample images - Translate and understand prompt techniques Also available: "ai-image-prompts" skill — a model-agnostic version of this library for universal image generation.

youmind-openlab avataryoumind-openlab
獲取
math-modeling

math-modeling

1.7Kagent-workflows

当用户要求数学建模、建模竞赛、建模分析、代码求解、结果可视化或生成数学建模论文时使用。支持完整三阶段流程、单独执行任一角色,以及在关键节点使用独立 Subagent 进行阶段内质检;默认只启用质检 Subagent,用户可明确选择额外协作。

xiaomacoltai avatarxiaomacoltai
獲取
copilot-delegate

copilot-delegate

1.7Kagent-workflows

Delegate a coding task to the GitHub Copilot CLI (`copilot`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Copilot - phrasings like "have Copilot implement X", "delegate this to copilot", "run it through Copilot CLI", or "use copilot to implement/fix/refactor" - or wants to run a queue of coding tasks through Copilot while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.

amelnagdy avataramelnagdy
獲取
propose-hypotheses

propose-hypotheses

1.7Kagent-workflows

Execute complete FPF cycle from hypothesis generation to decision

neolabhq avatarneolabhq
獲取
load-issues

load-issues

1.7Kagent-workflows

Load all open issues from GitHub and save them as markdown files

neolabhq avatarneolabhq
獲取
status

status

1.7Kagent-workflows

Display the current state of the FPF knowledge base

neolabhq avatarneolabhq
獲取
create-workflow-command

create-workflow-command

1.7Kagent-workflows

Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts

neolabhq avatarneolabhq
獲取
review-pr

review-pr

1.7Kagent-workflows

Review an existing GitHub pull request and post inline review comments on its diff. Use when the changes are on an opened PR rather than your local working tree.

neolabhq avatarneolabhq
獲取
create-ideas

create-ideas

1.7Kagent-workflows

Generate ideas in one shot using creative sampling

neolabhq avatarneolabhq
獲取
review-local-changes

review-local-changes

1.7Kagent-workflows

Review your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement suggestions. Use before committing, when nothing has been pushed yet.

neolabhq avatarneolabhq
獲取
open-prose

open-prose

1.7Kagent-workflows

Activate when the user types `prose ...`, opens a `.prose.md` file with `kind:` frontmatter, opens a `.prose` file, or asks for reusable multi-agent orchestration. Treat `prose run ...` as an in-session instruction: embody the OpenProse VM yourself; do not shell out to a `prose` binary. On activation read the Markdown contract, select a state backend, wire responsibilities, execute with host primitives, and persist run state under the selected OpenProse root. Decline for one-shot questions — a plain prompt is often the right answer.

openprose avataropenprose
獲取
judge-with-debate

judge-with-debate

1.7Kagent-workflows

Evaluate solutions through multi-round debate between independent judges until consensus

neolabhq avatarneolabhq
獲取
critique

critique

1.7Kagent-workflows

Comprehensive multi-perspective review using specialized judges with debate and consensus building

neolabhq avatarneolabhq
獲取
huashu-proofreading

huashu-proofreading

1.6Kagent-workflows

三遍审校降低AI检测率,让文章更有人味。当用户提到"AI味太重"、"像AI写的"、"降低AI检测率"、"审校"、"自然一些"时使用。

alchaincyf avataralchaincyf
獲取
huashu-design

huashu-design

1.6Kagent-workflows

设计哲学顾问,从20种风格中推荐3个方向并生成视觉Demo和AI提示词。当用户提到"设计风格"、"设计方向"、"配色方案"、"视觉风格"、"设计评审"、"推荐风格"时使用。

alchaincyf avataralchaincyf
獲取
huashu-wechat-image

huashu-wechat-image

1.6Kagent-workflows

为微信公众号文章生成高质量配图。支持封面图(2.35:1)、正文插图(16:9/4:3)、信息图。提供两条路径:AI生成(视觉创意型)和HTML渲染(文字精确型)。当用户提到"公众号配图"、"公众号封面"、"文章配图"、"正文插图"、"公众号图片"时使用此技能。

alchaincyf avataralchaincyf
獲取
huashu-script-polish

huashu-script-polish

1.6Kagent-workflows

视频脚本口语化审校,去书面腔让脚本适合说出来。当用户提到"口语化"、"太书面了"、"像说话一样"、"脚本审校"时使用。

alchaincyf avataralchaincyf
獲取
huashu-topic-gen

huashu-topic-gen

1.6Kagent-workflows

快速生成3-4个选题方向,含标题、大纲和优劣分析。当用户提到"选题"、"写什么"、"文章方向"、"题目建议"时使用。

alchaincyf avataralchaincyf
獲取
huashu-speech-coach

huashu-speech-coach

1.6Kagent-workflows

演讲与分享教练。基于Patrick Winston(MIT AI教授)的How to Speak方法论,帮助准备线下培训、技术分享、B站教程视频等演讲场景。当用户提到"演讲"、"分享"、"培训"、"讲课"、"PPT演讲"、"开场"、"结尾"、"如何讲"、"演讲结构"时使用此技能。

alchaincyf avataralchaincyf
獲取
huashu-article-edit

huashu-article-edit

1.6Kagent-workflows

标准化文章编辑流程,确保修改范围明确、进度可追踪、变更有记录。当用户说"编辑文章"、"修改文章"、"调整内容"、"改一下这篇"时使用此技能。

alchaincyf avataralchaincyf
獲取
huashu-info-search

huashu-info-search

1.6Kagent-workflows

多渠道搜索新产品新技术,交叉验证后存入知识库。当用户提到"最新信息"、"新产品"、"搜索资料"、"查资料"、"了解XX"时使用。

alchaincyf avataralchaincyf
獲取
huashu-video-outline

huashu-video-outline

1.6Kagent-workflows

快速生成2-3个视频大纲方案,含标题、封面建议和结构设计。当用户提到"视频大纲"、"视频结构"、"脚本大纲"、"视频选题"时使用。

alchaincyf avataralchaincyf
獲取
huashu-article-to-x

huashu-article-to-x

1.6Kagent-workflows

长文精简为X平台内容(200-500字),保留核心观点和个人风格。当用户提到"转微博"、"发小红书"、"社交媒体"、"缩短文章"时使用。

alchaincyf avataralchaincyf
獲取
huashu-material-search

huashu-material-search

1.6Kagent-workflows

搜索个人素材库1800+条真实经历和观点,为内容增加人味。当用户提到"个人经历"、"真实案例"、"素材"、"人味"时使用。

alchaincyf avataralchaincyf
獲取