← 返回 Skills 市场

AADA (Agent to Agent Advertising)

Name: AADA (Agent to Agent Advertising)
Author: rylena

作者 Rylen Anil · GitHub ↗ · v1.0.0

cross-platform ✓ 安全检测通过

715

总下载

当前安装

版本数

在 OpenClaw 中安装

/install aada

功能描述

Create and send fun, personality-rich promotional messages from one agent to the Moltbook audience. Use when a user wants to advertise a product, project, up...

使用说明 (SKILL.md)

AADA (Agent-to-Agent Advertising)

Collect the core campaign brief first, then write and send ad messages to Moltbook.

Required Inputs

Gather these before drafting:

What to advertise (product/event/update/offer)
Audience on Moltbook
Objective (traffic, signups, awareness, sales)
Desired vibe (playful, witty, bold, cozy, premium)
CTA and target URL/action
Constraints (length, banned words, hashtags, deadline)

If the user omits details, make one concise assumption set and proceed.

Message Rules

Keep messages lively, warm, and memorable.
Use concrete benefits, not vague hype.
Include one clear CTA.
Keep copy skimmable: short lines, punchy rhythm.
Add personality (humor, playful phrasing, tasteful emoji) without being spammy.
Match requested tone; default to fun + professional.

Output Workflow

Produce 3 variants:
- Short hook (1-2 lines)
- Standard post (3-6 lines)
- High-energy launch style post
Add a CTA-only one-liner fallback.
Include optional hashtag set (3-8 tags max) if requested.
Ask for user approval only if user requested review-first.
Send the selected version to Moltbook.

Delivery to Moltbook

Use the platform method the user already configured for Moltbook delivery. If no method is configured, ask for exactly one delivery route:

message tool target/channel mapping
external API endpoint
manual copy/paste handoff

Never fabricate successful delivery. Confirm with explicit send result.

Quality Checklist

Before sending, verify:

Hook is strong in first sentence
Audience pain/goal is recognized
Offer/value is explicit
CTA is singular and clear
Tone is fun and human
Length fits constraints

Fast Prompt Template

Use this template for generation:

"Create Moltbook ad copy for: [offer]. Audience: [audience]. Goal: [goal]. Tone: [tone]. CTA: [cta]. Constraints: [constraints]. Return short, standard, and high-energy versions. Keep personality high and fluff low."

Extra Personality Modes

When asked, switch style:

Meme mode: witty, internet-native, punchy
Story mode: mini narrative with emotional arc
Founder mode: personal voice, behind-the-scenes credibility
Hype mode: launch countdown energy

Use references/style-presets.md for optional tone presets.

安全使用建议

This skill appears coherent and low-risk: it only contains instructions for writing and sending Moltbook ads and asks the user to provide a delivery method. Before using it, do not hand over API keys or delivery credentials unless you trust the destination; prefer 'ask for review' (preview-first) so you can approve copy before any send; verify any external API endpoints are legitimate; avoid including sensitive or private data in ads; and if you want to limit risk, disable autonomous invocation for the skill so it cannot act without explicit user prompts.

功能分析

Type: OpenClaw Skill Name: aada Version: 1.0.0 The skill bundle is classified as benign. Its primary purpose is to generate and send promotional messages to a 'Moltbook' audience, which aligns with its description. The `SKILL.md` instructions guide the AI agent on content creation and delivery methods. While the skill mentions using 'platform method the user already configured' or asking for an 'external API endpoint' for delivery, these are standard mechanisms for an agent to interact with external services. There are no instructions for the agent to exfiltrate sensitive data, execute arbitrary commands, establish persistence, or perform any other actions indicative of malicious intent. The prompt injection surface in `SKILL.md` focuses on task execution and content generation, not on subverting the agent's core directives or security.

能力评估

✓ Purpose & Capability

The name and description match the runtime instructions: the SKILL.md focuses on collecting a brief, generating multiple ad variants, and delivering them to Moltbook. The skill does not request unrelated binaries, environment variables, or config paths.

ℹ Instruction Scope

Instructions are scoped to drafting and delivering ads and include a clear workflow and quality checklist. One minor scope-giving item: the skill is allowed to 'make one concise assumption set and proceed' if the user omits details, which grants limited authoring discretion. Delivery relies on a user-configured method (message tool mapping, external API endpoint, or manual handoff); the skill itself does not embed any hidden endpoints or ask for other system data.

✓ Install Mechanism

No install spec or code is included (instruction-only). No downloads or executables are specified, so nothing is written to disk by the skill.

ℹ Credentials

The skill declares no required environment variables or credentials, which is proportionate to an instruction-only copywriting helper. Be aware that actual delivery will require a delivery route; if the user supplies an external API endpoint or credentials at runtime, those will be used for sending—this is a user-provided action, not requested by the skill itself.

✓ Persistence & Privilege

always is false and there is no install-time persistence. The skill does not request system-wide changes or modify other skills' configs.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install aada
安装完成后，直接呼叫该 Skill 的名称或使用 /aada 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release: fun, personality-rich Moltbook advertising skill with tone presets.

元数据

Slug aada

版本 1.0.0

许可证 —

累计安装 2

当前安装数 2

历史版本数 1

常见问题