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.
curl -O https://raw.githubusercontent.com/DipsySu/media-scraper-mcp/main/.claude/skills/tmdb-scrape/SKILL.mdgit clone --depth 1 https://github.com/DipsySu/media-scraper-mcpWrote 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/dipsysu/media-scraper-mcp/tmdb-scrape)<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.
<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>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 | $0.00171 | $0.04598 |
| Opus 5 | $0.00086 | $0.02299 |
| Sonnet 5 | $0.00034 | $0.00920 |
| Haiku 4.5 | $0.00017 | $0.00460 |
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.
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_scrape→write_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_organize→apply_organize(+undo_organize回滚)。见下面〈organize 工作流〉。
这个 MCP server 暴露 12 个工具:get_capabilities、scan_media_files、search_tmdb、
get_tmdb_metadata、get_trending、get_recommendations、get_similar、plan_scrape、
write_artifacts、plan_organize、apply_organize、undo_organize。其中
write_artifacts / apply_organize / undo_organize 是破坏性(destructive)操作;其余
均为只读。
get_trending、get_recommendations、get_similar 是只读的「发现/挑片」工具,不动任何文件:
get_trending({ type, window?, language? })— 趋势(window为day/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(json、markdown)。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)。
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.
- 9d ago First seen · 239 lines · 171 tokens per session scan A c00fe20d7555
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.
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.
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…
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.
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).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
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.