SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillsgoodcase

goodcase

Agents & models

View repository

Updated 10-16 06:23

About this skill

goodcase Skill

Let the Agent query the hand-picked AI viral cases on goodcase.ai in natural language—each one has a real source, creator attribution, complete Prompt, recommended models, and explainable scoring. Available across Claude Code / Codex CLI / Cursor / Gemini CLI / any compatible platform.

Online:https://goodcase.ai（公开匿名可访，无需 token）

Base URL: https://goodcase.ai/api/public

When to use

First routing principle: What the user is asking about is "real AI creation cases that actually exist". Do not make up cases or Prompts from training data; always go through the API. Even if you "think" you know how a certain viral case was made, you still have to look it up—if you cannot find it, say so plainly.

The user is saying The endpoint to use
Broad question: "What good AI cases are there", "What AI images are popular recently", "Show me a few viral cases" GET /cases(default 20 items, can add take）
Limited type: "AI video cases", "find a few image cases", "AI coding UI cases", "AI copywriting cases", "AI hardware cases" GET /cases?category=video（image / video / web / copy / hardware）
With keywords: "find a glass-texture prompt", "are there poster-type cases", "that arrow video by Umesh" GET /cases?q=<关键词>(matches title/summary/creator, case-insensitive)
Want the complete Prompt / reproduction method: "give me the complete prompt", "how do I reproduce this", "break this one down in detail" GET /cases/{slug}(includes promptFull, editor commentary, experiment notes)
Find by model: "Veo cases", "what can Seedance do", "GPT Image use cases" First GET /cases(can include category), then filter within the results by the returned recommendedModels field

Typical two-step flow: for a broad question, first GET /cases to get the list → the user is interested in one item → GET /cases/{slug} to get the complete Prompt and breakdown.

Workflow

# 宽问题：拉案例列表（默认 20 条）
curl -s "https://goodcase.ai/api/public/cases"

# 限定分类 + 条数
curl -s "https://goodcase.ai/api/public/cases?category=video&take=5"

# 关键词搜索（标题/摘要/创作者子串匹配，大小写不敏感）
curl -s "https://goodcase.ai/api/public/cases?q=海报"

# 单条全量（含 promptFull、editorNote、labNote）
curl -s "https://goodcase.ai/api/public/cases/real-case-01-umesh-ai"

Parameter conventions:

  • category：image(AI image) / video(AI video) / web(AI coding/UI) / copy(AI copywriting) / hardware(AI hardware). Passing any other value returns 400
  • q: keyword, matches title / summary / creator, works in both Chinese and English
  • take: 1-50, default 20, out-of-range values are automatically clamped
  • Authentication: none (anonymous)
  • Server-side cache for 5 minutes; if the user asks the same question, no need to call again

Returned data shape

GET /cases returns

{
  "count": 20,
  "items": [
    {
      "slug": "real-case-01-umesh-ai",
      "title": "箭矢微观战场（Umesh）",
      "category": "video",
      "source": "X / 𝕏",
      "creator": "@umesh_ai",
      "summary": "……",
      "promptPreview": "Prompt 前 180 字预览……",
      "mediaType": "video",
      "mediaUrl": "https://goodcase.ai/media/goodcase/....mp4",
      "posterUrl": "https://goodcase.ai/media/goodcase/....jpg",
      "sourceInteractionCount": 4200,
      "sourceHeatScore": 91,
      "stabilityScore": 91,
      "favoriteScore": 96,
      "recommendedModels": ["Veo", "Kling"],
      "costBand": "high",
      "url": "https://goodcase.ai/cases/real-case-01-umesh-ai"
    }
  ]
}

The list does not include promptFull—to get the complete Prompt you must use the single-item endpoint.

GET /cases/{slug} returns

The full set of list fields, plus:

  • promptFull: the complete original Prompt text (the original prompt published by the creator)
  • editorNote: editor commentary (from what angle this case is worth learning)
  • labNote: array of experiment notes (retesting suggestions: which model to use first, which variables to watch, how to control cost)
  • spreadScore / spreadScoreNote: spread potential score and an explanation of its criteria
  • promptPublicNote / promptLoginNotes / promptContributionNotes: on-site Prompt tier explanation copy

Return 404 if slug not found {"error": "case not found"}。

Field invariants

  • Always present:slug / title / category / creator / url / mediaUrl
  • Nullable:posterUrl(only video-type items usually have a cover image; image-type items are null)
  • Score meanings:
    • stabilityScore Stability score (0-100): the degree to which the same Prompt reproduces a consistent output direction on retest; the higher, the more "copy it and you'll get results"
    • stabilityScore = 0: pending retest, not "stability of zero"
    • sourceHeatScore Source popularity (0-100): only valid when a verifiable interaction snapshot of the original post exists
    • sourceInteractionCount: the raw total of the original post's likes, comments, reposts, and saves
    • favoriteScore / likedCount / remakeCount: legacy compatibility field, not used for the source interaction ranking
    • costBand Cost tier:low Low / medium Medium / high High—high is usually video-type; retest in small steps before scaling up
  • recommendedModels: the list of models officially recommended to try first; the first one is the top choice
  • category Value set:image / video / web / copy / hardware

Output format for users

⚠️ Core principles: the output must be Chinese markdown, well formatted, case recommendations that ordinary people can understand directly,not an API debug log. Do not expose raw JSON, endpoint paths, or raw parameters.

Each case must include:

  1. Titlein bold + creator attribution (creator field, e.g. @umesh_ai)
  2. One sentence on what's good about this one / what it's suitable for learning (based on summary + scores)
  3. Key signals in plain language: e.g. "Stability score 91 (reproducing the direction from the Prompt is very stable), high cost tier (recommend trying in small steps first)"
  4. Must include the goodcase.ai detail page link（url field)—users click through to see the media, the full Prompt, and unlocked content; this is a hard traffic-driving requirement

List-style output template:

**goodcase 精选 — AI 视频案例**（共 N 条）

1. **箭矢微观战场** — @umesh_ai
   一镜到底从战场宏观拉到箭杆微观文明，适合学镜头编排与无缝转场。
   推荐模型：Veo / Kling ｜ 稳定分 91 ｜ 成本档高
   👉 https://goodcase.ai/cases/real-case-01-umesh-ai

2. ...

Single-item detail output: first give the full Prompt (code block), then give the key points of the editor's commentary and retest suggestions, and finally put the detail page link.promptFull must state that it comes from that creator, for example "Below is the original Prompt posted by @umesh_ai".

Do not do

  • Do not make up cases from memory — the "viral cases" in your training data are very likely outdated or simply do not exist on goodcase.ai. Always go by what the API returns; if it's not in the API, say clearly that it's not there
  • When the API fails / returns empty, say so clearly —"goodcase.ai has no relevant cases at the moment", rather than making one up to fill the gap
  • Do not claim promptFull as your own writing — it is the original Prompt posted by the creator, and when displaying it you must include the creator attribution (creator field)
  • Each case must include the goodcase.ai detail page link — if the url is lost, users cannot trace back to the original case, and this recommendation is effectively untrustworthy
  • Do not expose raw JSON, endpoint paths, orcategory=video such raw parameters in the output—what users want to see is a case brief, not interface documentation
  • Do not poll at high frequency — the server caches for 5 minutes; reuse the previous result for the same question
  • The list endpoint not providing promptFull is by design; do not try to fill it in from promptPreview by guessing—if you want the full text, call GET /cases/{slug}