跳到正文
FunCoding

搜索

搜索文档、Skill 和 MCP

blog-cover-generator

Use when the user asks to generate a blog cover image, thumbnail, or article header. Automatically uses modern typography, brand logos, and Google Search grounding to create beautiful 16:9 images with Gemini 3.1 Flash Image Preview.

AI 与智能体674skills/blog-cover-image-cli/SKILL.md

安装

把这段话发给 Claude Code、Codex 或 Cursor。智能体会先检查安全性,你确认后才安装。

读取 https://funcoding.ai/skills/varnan-tech/opendirectory/blog-cover-image-cli/install.md ,按里面的步骤帮我安装这个 Skill。

SKILL.md

Blog Cover Generator Skill

This skill provides AI agents with the ability to generate stunning, minimalist, technical blog cover images using the blog-cover-image-cli. The CLI leverages Gemini 3.1 Flash Image Preview, automatically fetches brand logos from domains, uses local aesthetic reference images, and employs Google Search grounding to inject real-time context.

Setup & Configuration

Agent Pre-requisites: Before using this tool, verify it is installed. If blog-cover-cli --help fails, install it globally:

npm install -g blog-cover-image-cli

If the user wants you to generate an image and you haven't set up the API key yet, you must first configure the CLI using a Gemini API Key. The CLI stores this securely via the conf package.

# 1. Set your Gemini API Key (Required for image generation)
npx -p blog-cover-image-cli blog-cover-cli config set-key <YOUR_GEMINI_API_KEY>

# 2. Set your Brandfetch Client ID (Required to fetch high-res logos)
npx -p blog-cover-image-cli blog-cover-cli config set-brandfetch-id <YOUR_BRANDFETCH_CLIENT_ID>

# Check your keys (masked)
npx -p blog-cover-image-cli blog-cover-cli config get-key
npx -p blog-cover-image-cli blog-cover-cli config get-brandfetch-id

Usage: Generating an Image

When a user asks for a cover image (e.g., "Create a cover image for my blog about Vercel v0"), you should use the generate command.

npx -p blog-cover-image-cli blog-cover-cli generate -t "The Title of the Blog Post" -l "example.com"

Arguments

  • -t, --title <text>: (Required) The title text to display on the cover image. Do not use excessively long titles (keep it under 3 lines of text visually).
  • -l, --logo <domain>: (Optional but recommended) The domain to fetch the brand logo from (e.g., vercel.com, google.com, cursor.com). The CLI automatically converts WebP/SVG/AVIF to PNG for compatibility.
  • -o, --output <path>: (Optional) The file path where the generated image will be saved. If omitted, the CLI automatically saves it to an output/ directory in the current working folder (e.g., ./output/vercel-cover.png).

Examples

Example 1: Cursor

npx -p blog-cover-image-cli blog-cover-cli generate -t "Why Cursor is the Ultimate AI Code Editor" -l "cursor.com"

Example 2: Lovable

npx -p blog-cover-image-cli blog-cover-cli generate -t "Building Apps in Minutes with Lovable" -l "lovable.dev"

Example 3: Custom Output Path

npx -p blog-cover-image-cli blog-cover-cli generate -t "Mastering React in 2026" -l "reactjs.org" -o "./assets/react-cover.png"

How It Works Under the Hood

As an agent, you should know what the CLI is doing so you can inform the user:

  1. Logo Fetching: It fetches logos from Brandfetch and processes them via sharp.
  2. References: It loads curated reference images from its examples/ directory to ensure the output is always a clean, minimalist white background with bold typography.
  3. Grounding: It has googleSearch tools enabled, meaning if the title relates to a recent event, Gemini can look it up before generating the image.
  4. Text Enforcement: It forces Gemini to output the exact title string using typographic placement rules.

Edge Cases / Troubleshooting

  • No API Key Error: If you see an API key error, run the config set-key command.
  • Logo Fetch Warning: If the CLI says Warning: Could not fetch logo, it will still generate the image but without the logo. You do not need to crash or stop.
  • Strict Modality Limits: Because it uses Gemini's experimental image models, generation may occasionally fail due to strict safety filters. If this happens, notify the user.

相似的 Skill

brand-guidelines
anthropics/skills180k

brand-guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

AI 与智能体

internal-comms
anthropics/skills180k

internal-comms

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

AI 与智能体

template-skill
anthropics/skills180k

template-skill

Replace with description of the skill and when Claude should use it.

AI 与智能体

mcp-builder
anthropics/skills180k

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

AI 与智能体

algorithmic-art
anthropics/skills180k

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

AI 与智能体

academy-guide
anthropics/skills180k

academy-guide

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

AI 与智能体