技能 connector-tmdb

📦

connector-tmdb

Name: connector-tmdb
Author: caffeinelabs

v0.1.2 内容修订 r1 安全 ⚙️ 外部命令🌐 网络访问🔑 环境变量

Build TMDb Movie and TV Features

Movie and TV integrations often fail because generated clients hide authentication, response shapes, and unsupported operations. This skill gives Caffeine developers a tested implementation path for catalog reads, credential handling, and service limits.

支持: Claude Codex Code(CC)

🥈 82 白银

使用我的智能体安装

将此请求复制给你的智能体，其中包含权威 Skill 页面和清单。

智能体请求

Review the Skillstore skill "connector-tmdb" from https://skillstore.io/skills/caffeinelabs-connector-tmdb.md and its manifest at https://skillstore.io/api/skills/caffeinelabs-connector-tmdb/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

你的智能体仍应展示其计划，并按安全策略请求必要确认。

Agent 可读资源

当 AI Agent、爬虫或脚本需要干净上下文，而不是读取完整页面时，请使用这些链接。

Markdown 详情 GET /skills/caffeinelabs-connector-tmdb.md 已签名 manifest GET /api/skills/caffeinelabs-connector-tmdb/manifest 已签名 lockfile GET /api/skills/caffeinelabs-connector-tmdb/lockfile

测试它

正在使用“connector-tmdb”。 I need a movie search endpoint for a Caffeine app.

预期结果:

A backend plan with a protected bearer token, a bounded search request, optional-field normalization, and a stable movie result shape.

正在使用“connector-tmdb”。 Which TMDb features should my first release avoid?

预期结果:

Avoid account writes, ratings, list creation, and session creation until the generated request body is fixed.
Avoid movie recommendations because successful responses are decoded incorrectly.
Use catalog reads, TV recommendations, search, discover, and trending feeds instead.

安全审计

安全

v1 • 2026/9/23 打开版本化报告

All 127 static findings are false positives. They match Markdown code spans, documented TMDb URLs, credential terms, and Motoko identifiers in SKILL.md. No executable shell use, environment access, reconnaissance, or unauthorized network behavior is evidenced.

已扫描文件

385

分析行数

复核项

已忽略误报

风险因素

⚙️ 外部命令 (50)

🌐 网络访问 (3)

SKILL.md:25 SKILL.md:133 SKILL.md:343

🔑 环境变量 (2)

SKILL.md:60 SKILL.md:63

最新一次完成的静态与语义审计未检测到已确认的安全发现。这并不能证明该 Skill 没有副作用。

审计者: codex

分享与引用此报告

分享版本化评估报告、中性徽章、嵌入卡片和引用。Skillstore 只报告证据，不判断该 Skill 是否安全。

打开版本化报告

复制报告链接

https://skillstore.io/skills/caffeinelabs-connector-tmdb/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 徽章

[![Skillstore security assessment](https://skillstore.io/badges/skills/caffeinelabs-connector-tmdb/security.svg)](https://skillstore.io/skills/caffeinelabs-connector-tmdb?utm_source=security_passport_badge)

HTML 徽章

<a href="https://skillstore.io/skills/caffeinelabs-connector-tmdb?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/caffeinelabs-connector-tmdb/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

嵌入卡片

<iframe src="https://skillstore.io/embed/skills/caffeinelabs-connector-tmdb.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

学术引用 (APA · BibTeX · CFF)

APA 引用

caffeinelabs. (2026). connector-tmdb security audit report (audit version 1) [Author version 0.1.2]. Skillstore. https://skillstore.io/skills/caffeinelabs-connector-tmdb/audits/1

BibTeX 引用

@techreport{caffeinelabs-caffeinelabs-connector-tmdb-2026,
  author = {caffeinelabs},
  title = {connector-tmdb security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/caffeinelabs-connector-tmdb/audits/1},
  note = {Author version 0.1.2}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "connector-tmdb security audit report (audit version 1)"
version: "0.1.2"
type: report
authors:
  - name: "caffeinelabs"
date-released: "2026-09-23"
url: "https://skillstore.io/skills/caffeinelabs-connector-tmdb/audits/1"
identifiers:
  - type: other
    value: "skillstore:caffeinelabs-connector-tmdb:audit:1"
    description: "Skillstore immutable audit report identifier"

Skillstore 评分

评分依据证据置信度: 中

架构

100

可维护性

内容

社区

100

规范符合性

你能构建什么

Create a movie search

Build a search endpoint that queries TMDb, maps optional fields, and returns a stable movie record to the frontend.

Launch a catalog home page

Combine now-playing, popular, trending, or discover reads into efficient landing-page feeds with bounded response sizes.

Plan a TV detail experience

Use TV detail, credits, season, episode, and recommendation operations while avoiding unsupported movie and account writes.

试试这些提示

Start with a movie search

Show me the smallest Caffeine backend design for searching movies with tmdb-client. Include the required credential shape and a compact response record.

Add a detail page

Design a Motoko movie detail endpoint using tmdb-client. Include credits, images, and videos through one efficient request where supported.

Build a TV catalog feed

Create a TV catalog plan using search, popular, trending, discover, and recommendation operations. Mark unsupported operations and explain the response mapping.

Review integration risks

Audit this proposed TMDb integration against the connector guidance. Check credentials, replication mode, pagination, response limits, rate limits, and unsupported writes.

最佳实践

Store long-lived tokens in protected actor state and restrict credential updates to authorized callers.
Normalize optional TMDb fields at the actor boundary and bound response sizes for each endpoint.
Cache configuration data, combine related detail resources, clamp page values, and back off after rate limits.

避免

Do not hand-roll ic.http_request calls when the generated client provides the required TMDb operation.
Do not expose tokens through query methods, logs, errors, or untrusted frontend parameters.
Do not build account writes or movie recommendations as working features before fixing their generated-client defects.

常见问题

Which credential does the client support?

Use a TMDb v4 read-access token with the generated bearer configuration. The v3 API key query parameter is not supported.

Can I store the token in the frontend?

Avoid frontend storage for a production app. Keep the token in protected actor state and authorize the setter.

Which TMDb operations work reliably?

Catalog reads such as search, details, trending, discover, now playing, and most TV reads are the intended surface.

Why should I avoid account writes?

The generated request body wraps payloads incorrectly, so twelve body-carrying operations are rejected by TMDb.

Why does movieRecommendations fail?

Its generated decoder expects a primitive, while TMDb returns a paginated object. TV recommendations use a normal generated type.

How should I handle images and limits?

Prepend the configured TMDb image base to relative paths, clamp pages to 500, bound response sizes, and back off after 429 responses.

开发者详情

作者

caffeinelabs

许可证

MIT

作者版本

v0.1.2

Skillstore 修订

仓库

https://github.com/caffeinelabs/skills/tree/c6bcba620fa151e28f2366205b35703d1c1e7864/skills/connector-tmdb

引用

2aa351cb09c29b7287d263bd8ea81e9bee3b2a61

维护新鲜度

2026/9/30

使用量

0 次下载 · 0 次浏览

文件结构

📄 SKILL.md