Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计通过

ideogram-data-handling表意文字数据处理

Agent Skill

用于辅助数据整理、表格处理、CSV/Excel 分析、指标计算和图表准备。它适合让 Agent 清洗字段、汇总数据、发现异常、生成统计口径或把分析结果转成可读说明。使用时需要确认数据来源、字段含义和时间范围,避免把样本数据当全量事实;涉及敏感数据、导出文件或批量写回时,应先确认权限和脱敏边界。

总安装

539

周安装

22

GitHub Stars

2,120

下载量

174
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:ideogram-data-handling(表意文字数据处理)
来源仓库:https://github.com/jeremylongshore/claude-code-plugins-plus-skills
仓库路径:skills/ideogram-data-handling
安装命令:
npx skills add https://github.com/jeremylongshore/claude-code-plugins-plus-skills --skill ideogram-data-handling
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/jeremylongshore/claude-code-plugins-plus-skills --skill ideogram-data-handling

简介

ideogram-data-handling 用于辅助数据整理、表格处理和指标计算,适合清洗字段、汇总数据或生成统计说明。

  • 适用于 CSV/Excel 分析、异常识别和图表准备等数据处理任务。
  • 使用时需确认数据来源与字段含义,避免将样本当作全量事实。
  • 涉及敏感数据或批量写回时,应先确认权限与脱敏边界。
  • 通过 npx skills add 命令安装,需评估是否会触发文件读写或网络请求。

SKILL.md

Ideogram Data Handling

Overview

Manage generated image assets from Ideogram. Covers prompt metadata tracking, image asset lifecycle management, download and local storage patterns, and generation history for brand consistency auditing.

Prerequisites

  • Ideogram API key
  • Image storage (local filesystem, S3, or GCS)
  • Understanding of image formats and metadata
  • Asset management process defined

Instructions

Step 1: Track Generation Metadata

interface GenerationRecord {
  id: string;
  prompt: string;
  negativePrompt?: string;
  model: string;
  aspectRatio: string;
  seed?: number;
  imageUrl: string;
  localPath?: string;
  generatedAt: string;
  expiresAt: string; // Ideogram URLs are temporary
}

const generationHistory: GenerationRecord[] = [];

async function generateWithTracking(prompt: string, options: any = {}) {
  const response = await fetch('https://api.ideogram.ai/generate', {
    method: 'POST',
    headers: {
      'Api-Key': process.env.IDEOGRAM_API_KEY!,
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      image_request: {
        prompt,
        model: options.model || 'V_2',
        aspect_ratio: options.aspectRatio || 'ASPECT_1_1',
        magic_prompt_option: 'AUTO',
      },
    }),
  });

  const result = await response.json();
  const image = result.data?.[0];

  if (image) {
    const record: GenerationRecord = {
      id: `gen_${Date.now()}`,
      prompt,
      model: options.model || 'V_2',
      aspectRatio: options.aspectRatio || 'ASPECT_1_1',
      seed: image.seed,
      imageUrl: image.url,
      generatedAt: new Date().toISOString(),
      expiresAt: new Date(Date.now() + 3600000).toISOString(), // ~1hr  # 3600000 = configured value
    };
    generationHistory.push(record);
    return record;
  }

  throw new Error('No image generated');
}

Step 2: Download and Persist Images

import { writeFileSync, mkdirSync, existsSync } from 'fs';
import { join } from 'path';

async function downloadImage(record: GenerationRecord, outputDir: string) {
  mkdirSync(outputDir, { recursive: true });

  const response = await fetch(record.imageUrl);
  if (!response.ok) throw new Error(`Download failed: ${response.status}`);

  const buffer = Buffer.from(await response.arrayBuffer());
  const filename = `${record.id}.png`;
  const filePath = join(outputDir, filename);

  writeFileSync(filePath, buffer);
  record.localPath = filePath;

  return filePath;
}

// Download immediately since URLs expire
async function generateAndPersist(
  prompt: string,
  outputDir = './generated-images'
) {
  const record = await generateWithTracking(prompt);
  await downloadImage(record, outputDir);
  return record;
}

Step 3: Asset Lifecycle Management

import { unlinkSync, existsSync } from 'fs';

function cleanExpiredAssets(
  records: GenerationRecord[],
  retentionDays = 30
) {
  const cutoff = Date.now() - retentionDays * 86400000;  # 86400000 = configured value
  const results = { kept: 0, deleted: 0 };

  for (const record of records) {
    if (new Date(record.generatedAt).getTime() < cutoff) {
      if (record.localPath && existsSync(record.localPath)) {
        unlinkSync(record.localPath);
      }
      results.deleted++;
    } else {
      results.kept++;
    }
  }

  return results;
}

Step 4: Generation History Export

function exportGenerationHistory(records: GenerationRecord[]) {
  return records.map(r => ({
    id: r.id,
    prompt: r.prompt,
    model: r.model,
    seed: r.seed,
    generatedAt: r.generatedAt,
    hasLocalCopy: !!r.localPath && existsSync(r.localPath),
  }));
}

function findByPrompt(records: GenerationRecord[], searchTerm: string) {
  return records.filter(r =>
    r.prompt.toLowerCase().includes(searchTerm.toLowerCase())
  );
}

Error Handling

IssueCauseSolution
Expired image URLURLs last ~1 hourDownload immediately after generation
Disk space fullToo many stored imagesRun retention cleanup regularly
Missing metadataNot tracked at generation timeUse generateWithTracking wrapper
Duplicate promptsSame prompt run multiple timesCheck history before regenerating

Examples

Batch Generate and Store

async function batchGenerateAssets(prompts: string[]) {
  const results = [];
  for (const prompt of prompts) {
    const record = await generateAndPersist(prompt);
    results.push(record);
    await new Promise(r => setTimeout(r, 3000)); // Rate limit  # 3000: 3 seconds in ms
  }
  return results;
}

Resources

Output

  • Configuration files or code changes applied to the project
  • Validation report confirming correct implementation
  • Summary of changes made and their rationale

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

34.27%
按下载量换算60

Claude

29.82%
按下载量换算52

Cursor

18.12%
按下载量换算32

Gemini CLI

9.14%
按下载量换算16

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills