media-scraper-mcp: Skill for Claude Code

.claude/skills/tmdb-scrape/SKILL.md

tmdb-scrape is a skill for Claude Code from DipsySu/media-scraper-mcp. It costs 171 tokens per session (4,598 once invoked), scanned A, original, MIT.

A tool for matching local movie and TV files with TMDB, a database of film and television information, then creating metadata files or organizing the library. It can write sidecar metadata, download artwork, rename files, and arrange seasons for media players such as Jellyfin and Kodi.

In plain words
What is it for?
Use it to identify films and shows, add metadata files, find trending or similar titles, or organize episodes into season folders with NFO files and artwork.
Why use it?
It helps turn an unstructured media folder into a library with recognizable titles, artwork, and episode information. It uses a planning step and normally previews changes before operations that modify files.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is DipsySu/media-scraper-mcp's own configuration. It tells Claude Code how to work on media-scraper-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything media-scraper-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to DipsySu/media-scraper-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/DipsySu/media-scraper-mcp/main/.claude/skills/tmdb-scrape/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/DipsySu/media-scraper-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for tmdb-scrape

README.md
[![agentmods](https://agentmods.dev/badge/skills/dipsysu/media-scraper-mcp/tmdb-scrape/github.svg)](https://agentmods.dev/skills/dipsysu/media-scraper-mcp/tmdb-scrape)
Your own site
<a href="https://agentmods.dev/skills/dipsysu/media-scraper-mcp/tmdb-scrape"><img src="https://agentmods.dev/badge/skills/dipsysu/media-scraper-mcp/tmdb-scrape/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.

agentmods 80×15 button for tmdb-scrape

Your own site · 80×15
<a href="https://agentmods.dev/skills/dipsysu/media-scraper-mcp/tmdb-scrape"><img src="https://agentmods.dev/badge/skills/dipsysu/media-scraper-mcp/tmdb-scrape.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 171 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,598 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00171 $0.04598
Opus 5 $0.00086 $0.02299
Sonnet 5 $0.00034 $0.00920
Haiku 4.5 $0.00017 $0.00460

Measured 9d ago against content hash c00fe20d7555, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

tmdb-scrape 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 9d 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.

.claude/skills/tmdb-scrape/SKILL.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TMDB 本地刮削与整理 (tmdb-scrape)

用这个 skill 通过 tmdb-media MCP server 给本地影视库处理 TMDB 元数据。整体体验类似 tinyMediaManager(tmm),但更保守:默认 dry-run、默认不覆盖、执行前必须经用户二次确认。

有两种模式,区别在「动不动真实视频文件」——务必先想清楚用户要哪种:

  • ① 轻量 sidecar 刮削:只在视频旁写 metadata.json / metadata.md不动视频。 工具:plan_scrapewrite_artifacts。见下面〈sidecar 工作流〉。
  • ② 完整 organize 整理:tmm/Jellyfin 式——重命名文件夹、把分集移进 Season N/、写 tvshow.nfo + 分集 NFO、下载 poster/fanart/剧照,会重命名/移动真实视频。 工具:plan_organizeapply_organize(+ undo_organize 回滚)。见下面〈organize 工作流〉。

这个 MCP server 暴露 12 个工具:get_capabilitiesscan_media_filessearch_tmdbget_tmdb_metadataget_trendingget_recommendationsget_similarplan_scrapewrite_artifactsplan_organizeapply_organizeundo_organize。其中 write_artifacts / apply_organize / undo_organize 是破坏性(destructive)操作;其余 均为只读。

get_trendingget_recommendationsget_similar 是只读的「发现/挑片」工具,不动任何文件:

  • get_trending({ type, window?, language? }) — 趋势(windowday / week,默认 week)。
  • get_recommendations({ type, tmdb_id, language? }) — 某作品的推荐。
  • get_similar({ type, tmdb_id, language? }) — 与某作品相似的作品。

用户问「最近有什么好看的 / 帮我挑片 / 和这部类似的还有啥」时用它们浏览候选;要继续刮削或 整理某部具体作品时,再走下面的 sidecar / organize 工作流。

选哪种模式? 用户说「写元数据 / sidecar / metadata.json / 不要动我的文件」→ 模式①。 用户说「整理 / organize / 像 Jellyfin/Kodi/tmm 那样 / 重命名 / 分季文件夹 / 生成 NFO」 → 模式②。拿不准就直接问用户要不要重命名/移动视频。

核心心智模型

  • 库根目录由配置固定。AI 永远只传 library(库名)+ 可选 subpath(相对路径), 绝不传绝对路径。绝对路径既不需要也不被接受。
  • 写入是两步走 + 二次确认plan_*(只规划、不动磁盘)→ 把计划讲给用户看 → 用户确认后 → write_artifacts / apply_organize(都需 plan_id + expected_plan_hash)。
  • dry-run 是默认。低置信度的自动匹配不会写。
  • organize(模式②)会重命名/移动真实视频,每次 apply 都会落一个 run_id,可用 undo_organize 整次回滚。

sidecar 工作流(模式①,不动视频,务必按顺序)

第 1 步:永远先 get_capabilities

不带参数调用。它会告诉你:

  • libraries — 有哪些库可用、各自类型(movie / tv)。这是唯一可写的根
  • defaultLanguage / fallbackLanguage — 默认语言(通常 zh-CN)。
  • formats — 支持的 sidecar 格式(jsonmarkdown)。
  • minConfidence — 自动写入所需的最低置信度阈值。
  • videoExtensions — 识别为视频的扩展名(.mkv.mp4.avi.mov.m4v.wmv.ts)。
  • attribution — TMDB 署名文本(展示数据时应保留)。

Read the full file on GitHub · 239 lines

Changes

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.

  1. 9d ago First seen · 239 lines · 171 tokens per session scan A c00fe20d7555

Subscribe to this mod's changes

tmdb-scrape is a skill published in the GitHub repository DipsySu/media-scraper-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 171 tokens to every session and 4,598 once invoked, about $0.0009 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens

chengfeng-check-updates

An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens