← 返回 Skills 市场
pauldelavallaz

AI Brand Analyzer

作者 Paul de Lavallaz · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
1867
总下载
2
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install ai-brand-analyzer
功能描述
Analyze brands to generate comprehensive brand identity profiles (JSON). Use when the user wants to analyze a brand, create a brand profile, or needs brand data for ad generation. Stores profiles for reuse across Ad-Ready, Morpheus, and other creative workflows. Can list existing profiles and update them.
使用说明 (SKILL.md)

Brand Analyzer: AI Brand Identity Profiler

Analyze any brand to generate a comprehensive brand identity JSON profile using Gemini Flash with Google Search grounding.

Overview

Brand Analyzer creates structured brand identity profiles by:

  1. Researching the brand via Google Search (official data, campaigns, visual identity)
  2. Analyzing brand behavior, visual patterns, photography style, tone of voice
  3. Generating a complete JSON profile following the standard template
  4. Storing the profile for reuse across all creative workflows

When to Use

  • User asks to "analyze a brand" or "create a brand profile"
  • Before running Ad-Ready when the brand isn't in the catalog
  • When the user mentions a brand that doesn't have a profile yet
  • To update/refresh an existing brand profile

Quick Commands

Analyze a brand and save to file

GEMINI_API_KEY="$KEY" uv run {baseDir}/scripts/analyze.py \
  --brand "Brand Name" \
  --output ./brands/Brand_Name.json

Analyze and auto-save to Ad-Ready brands catalog

GEMINI_API_KEY="$KEY" uv run {baseDir}/scripts/analyze.py \
  --brand "Heredero Gin" \
  --auto-save

The --auto-save flag automatically saves to ~/clawd/ad-ready/configs/Brands/{Brand_Name}.json

Print to stdout

GEMINI_API_KEY="$KEY" uv run {baseDir}/scripts/analyze.py --brand "Nike"

Inputs

Input Required Description
--brand Brand name to analyze
--output Optional Output file path (default: stdout)
--auto-save Optional Auto-save to Ad-Ready brands catalog
--api-key Optional Gemini API key (or set GEMINI_API_KEY env var)

Output Format

The generated JSON follows the standard brand identity template used by Ad-Ready:

{
  "brand_info": { "name", "tagline", "category", "positioning", "vision", "mission", "origin_story" },
  "brand_values": { "core_values", "brand_promise", "differentiators", "non_negotiables" },
  "target_audience": { "demographics", "psychographics" },
  "tone_of_voice": { "personality_traits", "communication_style", "language_register", ... },
  "visual_identity": { "logo", "color_system", "typography", "layout_principles" },
  "photography": { "style", "technical" },
  "campaign_guidelines": { "visual_tone", "model_casting", "product_presentation", ... },
  "brand_behavior": { "do_dont", "immutability" },
  "channel_expression": { "retail", "digital", "print" },
  "compliance": { ... }
}

Integration with Other Workflows

Ad-Ready

Brand profiles are automatically available as brand_profile options when generating ads.

Morpheus Fashion Design

Brand visual identity (colors, photography style, tone) can inform Morpheus campaigns.

Custom Workflows

Load any brand profile JSON to extract visual identity, tone of voice, or campaign guidelines for any creative task.

Analysis Methodology

The analyzer follows a 3-phase approach:

Phase 1: Official Research (via Google Search)

  • Brand website, corporate pages, official communications
  • Locks canonical data: name, founding, positioning, vision, mission, tagline

Phase 2: Campaign Research (via Google Search)

  • Google Images and Pinterest for advertising campaigns
  • Identifies 10+ distinct campaigns
  • Treats them as analytical reference material

Phase 3: Deductive Visual Analysis

  • Cross-sectional analysis of visual patterns
  • Identifies recurring photography style, color systems, typography
  • Fills visual identity fields not covered by official data

API Key

Uses Gemini API. Set via:

  • GEMINI_API_KEY environment variable
  • --api-key flag
安全使用建议
This skill appears to do what it says (generate and save brand JSON profiles), but there are several red flags you should address before installing or running it: - The skill’s registry metadata does NOT declare the GEMINI_API_KEY environment variable, yet both SKILL.md and the script require it. Confirm you are comfortable providing that API key and that the skill source is trustworthy. - The Python script advertises a dependency (google-genai) but there is no install specification. Ask how/where dependencies will be installed and consider running inside an isolated environment (container or VM) to avoid unexpected package installs. - The script and instructions require web research (Google Images, Pinterest). Confirm what data the skill will fetch and whether any downloaded images or scraped content might include sensitive material. If you want to limit network exposure, run in a sandboxed environment or on a host with controlled egress. - The script will write files to ~/clawd/ad-ready/configs/Brands by default. If you use --auto-save, check the target path (or override AD_READY_BRANDS_DIR) to avoid accidental overwrites of important files. - The provided analyze.py appears truncated in the package you gave (it ends mid-prompt). Obtain and review the complete script before running — incomplete code could hide additional behavior or simply fail at runtime. Recommended steps: request the full source, ask the publisher to update registry metadata to list GEMINI_API_KEY and dependency/install info, review the complete script for any unexpected network endpoints or uploads, and test first in an isolated sandbox.
功能分析
Type: OpenClaw Skill Name: ai-brand-analyzer Version: 1.0.0 The skill is classified as suspicious due to its file system write capabilities to user-specified paths and network access, even though these are for its stated purpose. The `scripts/analyze.py` script, when executed via `uv run` as instructed in `SKILL.md`, can write generated JSON brand profiles to an arbitrary path specified by the `--output` argument. While the content written is controlled (AI-generated JSON), the ability to write to any location the agent has permissions for is a risky capability that could be exploited in a compromised agent scenario. Additionally, it writes to a specific OpenClaw configuration directory (`~/clawd/ad-ready/configs/Brands/`) via the `--auto-save` flag and makes external API calls to Google Gemini (which uses Google Search) for its core functionality.
能力评估
Purpose & Capability
Name/description align with the included code: the script and SKILL.md both describe researching brands, generating a JSON profile, and optionally saving it into an Ad-Ready catalog. However the registry metadata declares no required environment variables or primary credential, while both SKILL.md and scripts/analyze.py expect a GEMINI_API_KEY. The script also lists a dependency (google-genai) in a comment but the skill has no install spec — these mismatches are unexpected for a networked API integration.
Instruction Scope
SKILL.md explicitly instructs the agent to conduct web research (Google Search, Google Images, Pinterest), collect at least 10 campaign assets, and use them in visual analysis. That scope is plausible for the stated purpose, but it implies network access and potentially downloading/processing images. The instructions also direct auto-saving to a specific path (~/clawd/ad-ready/configs/Brands) which means the skill will write to the user's home directory. The SKILL.md forbids inventing official data and requires canonical locking, which is operationally strict but not a security issue by itself.
Install Mechanism
There is no install specification even though scripts/analyze.py declares a dependency (google-genai>=1.0.0) in its header comments. Because the skill has a runnable Python script that expects a third-party package, an explicit install step is normally required. The absence of an install spec is an inconsistency (may cause runtime failure or require the platform to install packages implicitly). There is no download-from-URL or other high-risk installer present.
Credentials
The runtime clearly requires a GEMINI_API_KEY (SKILL.md examples and get_api_key() in the script), but the registry lists no required env vars or primary credential — this is a direct mismatch. Aside from that single API key, no other secrets are requested. The skill will also write files into the user's home directory (AD_READY_BRANDS_DIR), which is proportionate to its purpose but should be noted.
Persistence & Privilege
The skill does not request always:true and is user-invocable; it does not request system-wide configuration changes. Its only persistence behavior is auto-saving JSON files to a subdirectory under the user's home (~/clawd/ad-ready/configs/Brands or AD_READY_BRANDS_DIR). This is expected for an integration that provides reusable brand profiles and is not, by itself, excessive privilege.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install ai-brand-analyzer
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /ai-brand-analyzer 触发
  4. 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
v1.0.0: Brand identity profiler using Gemini Flash + Google Search grounding. Generates comprehensive JSON profiles for ad generation workflows (Product to Ads, Morpheus, etc).
元数据
Slug ai-brand-analyzer
版本 1.0.0
许可证
累计安装 1
当前安装数 1
历史版本数 1
常见问题

AI Brand Analyzer 是什么?

Analyze brands to generate comprehensive brand identity profiles (JSON). Use when the user wants to analyze a brand, create a brand profile, or needs brand data for ad generation. Stores profiles for reuse across Ad-Ready, Morpheus, and other creative workflows. Can list existing profiles and update them. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1867 次。

如何安装 AI Brand Analyzer?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install ai-brand-analyzer」即可一键安装,无需额外配置。

AI Brand Analyzer 是免费的吗?

是的,AI Brand Analyzer 完全免费(开源免费),可自由下载、安装和使用。

AI Brand Analyzer 支持哪些平台?

AI Brand Analyzer 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 AI Brand Analyzer?

由 Paul de Lavallaz(@pauldelavallaz)开发并维护,当前版本 v1.0.0。

💬 留言讨论