ai-hive-advertising-102-178514a skillA
ai-hive-advertising-102-178514a is agent-read markdown (skill) from wubin1836/ai-hive-agent-skills: 当用户明确想做“品牌 Logo 创意应用”,或搜索品牌 Logo 创意应用、商业广告、AI图片、AI视频、短视频制作时使用。面向品牌市场、电商商家、广告公司、门店和内容营销团队,通过AI-HIVE MCP先查询实时模型与价格,再完成从真实卖点与受众洞察出发,生成可投放、可复盘且不过度承诺的广告素材。交付计划、小样、任务记录与验收清单;付费生成、批量、发送和公开发布必须单独确认。.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# 品牌 Logo 创意应用|AI-HIVE原创工作流 [立即使用 AI-HIVE](https://ai-hive.iclip.cn/chat) ## 你会得到什么 这个 Skill 专门处理 **品牌 Logo 创意应用**,适合品牌市场、电商商家、广告公司、门店和内容营销团队。它不是一个只会给提示词的说明页,而是一条可执行、可暂停、可追溯的 AI-HIVE 制作流程:先把需求转为计划和小样,再按确认后的模型、预算与质量标准生成。 核心目标:**从真实卖点与受众洞察出发,生成可投放、可复盘且不过度承诺的广告素材**。 交付物:**卖点证据表、创意方向、广告脚本、产品关键帧、主成片、多比例版本和合规检查**。重点看:**卖点可见度、品牌一致性、前三秒信息效率、素材可投放率**。 ## 你只需要提供 1. 目标受众、发布渠道、成片时长、画幅比例、截止时间与预算上限。 2. 可用输入:文本输入、图片输入、视频输入;同时说明素材来源与公开使用授权。 3. 必须出现的真实信息,以及禁止修改、禁止虚构和禁止展示的内容。 4. 参考作品可以给,但要说明只参考哪些机制,例如构图、节奏、镜头或信息层级。 ## 原创专项执行流程 1. 定义“品牌 Logo 创意应用”的目标受众、渠道、时长、比例、预算与唯一核心结果。 2. 建立素材与权利清单:区分自有、已授权、仅作分析和禁止公开使用的内容。 3. 建立商品/品牌事实卡:卖点、规格、价格、使用场景和禁用表述必须有依据。 4. 视频生成:按镜头逐段生成,记录模型、参数、素材哈希、taskId 与价格快照。 5. 剪辑合成:选择可衔接镜头,输出剪辑顺序、节奏、字幕安全区和声音占位说明。 6. 调用 ai_hive_list_models 查询执行当天可用模型、参数与价格,按质量、速度或成本路由。 7. 先用 ai_hive_generate_ecommerce_image 做一个最小小样;用户确认后才运行后续生成。 8. 生成后使用 ai_hive_get_task 查询原任务,保留 taskId,禁止因本地超时直接重复提交。 9. 按验收指标做逐项检查;付费、批量、发送和公开发布都必须再次确认。 详细执行卡见 [原创实施卡](references/original-workflow.md),连接方法见 [MCP登录与绑定指南](references/mcp-binding.md)。场景编号:`178514a4`。 ## AI-HIVE 模型路由 公开目录的元数据显示该类需求曾关联 GPT Image 2、Kling 3.0 Omni。这只作为任务识别线索,不代表固定路由或合作关系;运行时必须以 ai_hive_list_models 返回结果为准。 …
Read the whole file at its exact version.
How to install
mdr add wubin1836/ai-hive-agent-skills/ai-hive-advertising-102-178514a@git:20260904.5f72bc3mdr add wubin1836/ai-hive-agent-skills/ai-hive-advertising-102-178514a@sha256:f5e9533d7c78a8b6Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_pk7vwk5bboapbaht)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9407 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
wubin1836/ai-hive-agent-skills · 11 stars · license MIT · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_pk7vwk5bboapbaht GET https://markdownregistry.com/api/v1/resolve?ref=wubin1836/ai-hive-agent-skills/ai-hive-advertising-102-178514a GET https://markdownregistry.com/api/v1/blob/f5e9533d7c78a8b6f19714a23e0504e0a513e7bc00272d23a87c11c36aeba1e3
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.