Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add TashanGKD/tashan-cursor-skills --skill article-image-anglesgit clone --depth 1 https://github.com/TashanGKD/tashan-cursor-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/article-image-angles)<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/article-image-angles"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/article-image-angles/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/article-image-angles"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/article-image-angles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00063 | $0.00554 |
| Opus 5.5 | $0.00025 | $0.00222 |
| Sonnet 5.5 | $0.00013 | $0.00111 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
article-image-angles scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- article-image-angles — 100% identical, 0 lines differ
What it actually says
文章配图多视角分析（article-image-angles）
定位：wechat-article-writer Step 3（生成配图）的增强版。 核心价值：把「生成一张图」变成「从多种视角选最适合的图」，提高配图质量。
激活后立即执行
Step 1 读取文章标题和核心论点（从对话上下文获取） Step 2 分析可用配图角度（至少3种，最多5种）： 常见角度类型： - 🔢 数据可视化角度：用图表/数字呈现文章核心数据 - 🎭 隐喻/类比角度：用视觉隐喻传达抽象概念 - 🔄 流程/机制角度：展示文章描述的系统/流程/循环 - ⚡ 对比/张力角度：突出文章的核心矛盾或转变 - 🌍 场景/情境角度：还原文章讨论的真实场景 Step 3 为每个角度写一段提示词（中文，适配 Qwen/GPT-4V 等图像生成模型） Step 4 向用户展示多个角度选项，等待选择 Step 5 用户确认后，用选定角度的提示词生成图片 Step 6 如有需要，根据反馈微调提示词重新生成
提示词格式规范
每个角度的提示词需包含：
- 构图描述（什么元素，如何排布）
- 风格描述（极简/插画/科技/水墨等）
- 颜色基调（与他山品牌色协调：蓝绿 rgb(111,167,170)）
- 禁止元素（文字、人脸、版权图案）
变更记录
v1.0 — 2026-03-19 — 初始创建
根因：wechat-article-writer 配图只生成一张，缺少多视角分析和用户选择环节，配图质量依赖单次提示词质量。
验证状态：🔵 待验证
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 47 lines · 63 tokens per session scan A e409bf71eaed
article-image-angles is a skill published in the GitHub repository TashanGKD/tashan-cursor-skills (22 stars, last pushed 6mo ago), licensed MIT. It adds 63 tokens to every session and 554 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sonic-setup-new-project
Sonic Cursor Skill: Bootstrap a new Android multi-module app (domain, data, core-, xml :presentation or compose :feature-) with StartupActivity (funnel) + MainActivity (app), StartupFragment start destination, Parent (InsetsMode edge-to-edge) or Compose StartupNavGraph / MainNavGraph, PlatformFirebase, Remote Config →…
sonicg-setup-new-project
OrbitalSonic Gemini Skill: Bootstrap a new Android multi-module app (domain, data, core-, xml :presentation or compose :feature-) with StartupActivity (funnel) + MainActivity (app), StartupFragment start destination, Parent (InsetsMode edge-to-edge) or Compose StartupNavGraph / MainNavGraph, PlatformFirebase, Remote…
sonic-setup-old-project
Sonic Cursor Skill: Migrates an existing production Android app to the sonic-setup-new-project architecture (multi-module Clean Architecture, MVI, Koin module/lazyModule, XML View Binding or Compose feature modules per uiFramework) while preserving product behavior. Detects MVC, MVVM, Activity-based, single-module…
sonicc-setup-old-project
OrbitalSonic Claude Skill: Migrates an existing production Android app to the sonicc-setup-new-project architecture (multi-module Clean Architecture, MVI, Koin module/lazyModule, XML View Binding or Compose feature modules per uiFramework) while preserving product behavior. Detects MVC, MVVM, Activity-based…
sonic-implement-in-app-billing
Sonic Cursor Skill: Add Google Play in-app billing to a new app — subscriptions and/or one-time products — using orbitalsonic SonicInApp v4 (https://github.com/orbitalsonic/SonicInApp), BillingDataSource, paywalls, and isAppPurchased. Use when setting up billing, IAP, premium, or subscriptions for the first time, or…
sonicg-implement-admob-ads
OrbitalSonic Gemini Skill: First-time AdMob setup with :gmaAds from orbitalsonic/Admob-Ads — place module if missing, discover mappable screens, ask which screens then which placements, wire confirmed only (RC/prefs only for those). Use when implementing ads for the first time, or @sonicg-implement-admob-ads. Not for…