Skip to content
Agentmart
Submit a tool

media115-scrape

Scrape metadata for media files — agent drives matching, code only provides tools

Skill by newcoderlife

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying media115-scrape?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/newcoderlife-media115-scrape

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Scrape metadata for media files — agent drives matching, code only provides tools

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/media115-scrape

What's inside

Skill name
media115-scrape
Description
Scrape metadata for media files — agent drives matching, code only provides tools
License
MIT
Metadata
version: 7.0
Instructions
101 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

刮削媒体文件的元数据(NFO + 海报)。**你(agent)负责判断文件是什么,代码只负责搜索和生成。**

## 核心原则

1. **你来判断,代码只是工具。** `media115 scrape` 只处理高置信度匹配(标题+年份完全吻合)。所有不确定的,由你来判断。
2. **没刮到就是没刮到。** 不要强行匹配。宁可标记为待确认,也不要用错误的元数据。
3. **文件名是最重要的线索。** 从文件名推测标题、年份、季/集、类型。文件名里有中文就用中文搜。

## Input

$ARGUMENTS — category: `电影`, `AV`, or `剧目`. Ask the user if not provided.

## Preconditions

- 115 must be logged in (`/auth`)
- SQLite cache must exist. If not, run `/sync` first.

## Step 1: 扫描待处理文件

```bash
media115 scan $CATEGORY
```

看 scan 的输出表格。关注 `Action` 列:
- `scrape` — 需要刮削
- `skip` — 已有 NFO,跳过
- `unrecognized` — 文件名无法解析,需要手动处理

## Step 2: 先跑 scrape 处理简单 case

```bash
media115 scrape $CATEGORY
```

scrape 自动处理文件名清晰、数据源精确匹配的文件。

输出里注意:
- `→ 标题 (ID)` — 自动匹配成功
- `not_found` — 没搜到
- `error` — 网络/API 错误

数据源按类型自动选择:
- `电影`/`剧目` → TMDB
- `AV` (日本) → jav321 / javfree
- `AV` (欧美, `av_west`) → ThePornDB / StashDB
- `anime` → TMDB / Bangumi

## Step 3: 审查自动匹配结果(关键步骤,不要跳过)

检查输出中每一行:

- 中文标题是否合理?"Youth.Periplous.2019" 匹配到 "Youth" 而不是 "青春环游记" 就是错的。
- 年份是否吻合?文件名里有 2019 但匹配到一部没有年份的内容说明匹配错了。
- 类型是否对?电影文件匹配到 TV show 说明错了。

**如果发现可疑匹配,立即用 `/scrape-fix` 修正。**

## Step 4: 处理 not_found 和 unrecognized

对每个失败文件,你来推理:

1. 看文件名全称,提取所有线索(标题、年份、季集号、制作组标签)
2. 猜测可能的中文名或英文名
3. 用 `scrape-fix` 指定正确的匹配:

```bash
media115 scrape-fix "猜测的文件.mkv" --search "猜测的名字"
media115 scrape-fix "猜测的文件.mkv" --search "猜测的名字" --category 剧目 # 动漫/剧目
media115 scrape-fix "SONE-001.mkv" --number "SONE-001"                    # 日本AV
```

4. 如果搜到多个结果,用年份、类型、集数等信息交叉验证
5. 如果确实搜不到匹配,告诉用户这个文件需要手动处理

**不要做的事:**
- 不要盲取第一个搜索结果
- 不要在不确定时强行匹配
- 不要用文件名中的单个英文单词去搜(太宽泛)

## Step 5: 修正错误匹配

对每个需要修正的文件,用 `/scrape-fix`:

```bash
media115 scrape-fix "Restart.2026.mkv" --tmdb-id 1664596
media115 scrape-fix "Restart.2026.mkv" --search "守护游戏"
media115 scrape-fix "T-3800040.mkv" --number "T28-003"
```

## Step 6: 报告并执行 organize

输出汇总表:

| 文件 | 匹配结果 | 置信度 | 备注 |
|------|---------|--------|------|
| xxx.mkv | 青春环游记 (tmdb:106938) | 高 | 年份+标题吻合 |
| yyy.mkv | ? | — | 未找到匹配,需用户确认 |

确认后,执行 `/organize`。

From newcoderlife/media115, MIT.

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Apr 18, 2026 (6 months ago)
Last release
Apr 18, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
7.0
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from newcoderlife

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get media115-scrape running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying media115-scrape?

CallGet help
Cite this page

media115-scrape skill. Agent Mart. https://agentmart.dev/skills/newcoderlife-media115-scrape (last updated 2026-10-24)