Mediary Scout logo

Mediary Scout

CommunityPopular
fancydirty
mediary-scout

操作本机运行的 Mediary Scout(自托管媒体获取 agent)——改配置、找片/下片、查库存与进度,全程走本地 HTTP API,无需打开桌面客户端。 Use when the user wants to find, download, or track movies / TV shows / anime through Mediary Scout, check download progress, inspect their tracked library, change Mediary settings (quality / language / LLM / drives), or trigger a patrol sweep. 触发词:「帮我找 XX」「帮我下 XX」「XX 下好了吗」「XX 下载到哪了」「我在追哪些剧」「我的库存」「缺哪几集」「把画质改成 4K」「改成中文字幕优先」「触发一次巡检」「跑一遍巡检」。 Triggers: find/download a movie/show/anime, check download or acquisition progress, list what I'm tracking, show missing episodes, change quality preference to 4K, set preferred language, trigger/force a patrol, read or update Mediary Scout config.

Overview

Publisherfancydirty
Repositorymediary-scout
Skill namemediary-scout
Stars
1.4K
Forks
94
Bundled files
1
License0BSD
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by fancydirty on GitHub. Read the source before you install it.

Installation

Install the Mediary Scout AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/fancydirty/mediary-scout.git /tmp/mediary-scout
mkdir -p .claude/skills
cp -r /tmp/mediary-scout/skills/mediary-scout .claude/skills/mediary-scout
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mediary Scout in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Mediary Scout on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Mediary Scout is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Mediary Scout — Agent 操作面

你在通过本地 HTTP API 操作用户本机运行的 Mediary Scout。所有细节(完整 schema、错误码、字段清单)在 references/api.md

1. 连接(每次先做)

发现文件在 ~/.mediary/agent.json(权限 0600),内容: { "baseUrl": "http://127.0.0.1:<port>", "token": "<hex>", "version": "<app version>" }

bash
cat ~/.mediary/agent.json
  • 文件不存在 → 用户还没启动过。让用户打开 Mediary Scout 桌面 app(首启会生成 token 并写这个文件),然后重试。
  • 文件存在但 curl connection refused → app 没在运行。让用户启动 Mediary Scout 桌面 app。
  • 文件存在且能连 → 继续。

之后所有调用都用这两个变量:

bash
TOKEN=$(jq -r .token ~/.mediary/agent.json)
BASE=$(jq -r .baseUrl ~/.mediary/agent.json)

请求统一带 -H "Authorization: Bearer $TOKEN"

2. 能力速查(用户说什么 → 调什么)

用户意图端点curl
查当前配置(画质/语言/LLM/推送…)GET /api/agent/configcurl -H "Authorization: Bearer $TOKEN" "$BASE/api/agent/config"
改配置(画质、语言、扫描时间…,传啥改啥)PUT /api/agent/configcurl -X PUT -H "Authorization: Bearer $TOKEN" -H 'Content-Type: application/json' -d '{"qualityPreference":"4K"}' "$BASE/api/agent/config"
「帮我找/下 XX」POST /api/agent/acquirecurl -X POST -H "Authorization: Bearer $TOKEN" -H 'Content-Type: application/json' -d '{"query":"进击的巨人","type":"tv","season":2}' "$BASE/api/agent/acquire"
「触发一次巡检」「跑一遍巡检」POST /api/agent/patrolcurl -X POST -H "Authorization: Bearer $TOKEN" "$BASE/api/agent/patrol"
「我在追哪些剧」「缺哪几集」「我的库存」GET /api/agent/librarycurl -H "Authorization: Bearer $TOKEN" "$BASE/api/agent/library"
「XX 下好了吗」「下载到哪了」「最近在忙啥」GET /api/agent/activitycurl -H "Authorization: Bearer $TOKEN" "$BASE/api/agent/activity?limit=20"

acquire body 字段:query(必填)、type("tv"/"movie"/null)、season(数字/null)、storageId("cs_…"/null,缺省用 primary drive)、tmdbId(数字/null,用于消歧重发)。

3. 关键规则(必须遵守)

  1. 409 歧义 → 交给用户挑,绝不瞎猜。 acquire 命中多个高分候选时返回 409 { "candidates": [top5] }。把候选(标题/年份/tmdbId)列给用户,让用户选一个,再带 "tmdbId": <所选> 重发同一 acquire。禁止自行替用户拍板。
  2. 脱敏值绝不回写。 GET config 里秘密字段只露尾 4 位或显示为 ***(如 "apiKey": "sk-***7f2a""tmdbApiKey": "***")。任何以 *** 开头或含 *** 的值都禁止写回 PUT config——服务端会 400,且回写会毁掉真凭据。
  3. 秘密字段只在用户明确给出新值时才写。 LLM apiKey、tmdbApiKey、prowlarr.apiKey、推送密钥等,只有用户在本次对话里明确提供了新的明文值,才放进 PUT body。用户没提就别碰这些字段。
  4. storages 只读。 GET config 会列出 storages(id/brand/name,不含凭据);PUT config 不接受 storages,改盘绑定要在桌面 app 里做。
  5. 未运行 / 未配置。 端点隐身(返回 404、非预期结构)时:多半是 app 没运行或该环境没配 agent token——提示用户启动桌面 app,别把 404 当「没找到片」(找片的「无匹配」也是 404,用返回体区分:有 candidates 是歧义,有 matched/status 是成功,纯 404 且带 no-token 语义是未启用)。

完整请求/响应 schema、全部错误码(404 无 token / 无匹配、401 token 错、409 候选、403 demo、400 校验)、字段级说明见 references/api.md

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Mediary Scout AI skill do?

操作本机运行的 Mediary Scout(自托管媒体获取 agent)——改配置、找片/下片、查库存与进度,全程走本地 HTTP API,无需打开桌面客户端。 Use when the user wants to find, download, or track movies / TV shows / anime through Mediary Scout, check download progress, inspect their tracked library, change Mediary settings (quality / language / LLM / drives), or trigger a patrol sweep. 触发词:「帮我找 XX」「帮我下 XX」「XX 下好了吗」「XX 下载到哪了」「我在追哪些剧」「我的库存」「缺哪几集」「把画质改成 4K」「改成中文字幕优先」「触发一次巡检」「跑一遍巡检」。 Triggers: find/download a movie/show/anime, check download or acquisition progress, list what I'm tracking, show missing episodes, change quality preference to 4K, set preferr...

Why use Mediary Scout on TypingMind?

Because you install it once and use it with any model. Mediary Scout is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Mediary Scout in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/fancydirty/mediary-scout/tree/main/skills/mediary-scout. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Mediary Scout?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Mediary Scout?

As many as you like. As long as a model supports skills, you can use Mediary Scout with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mediary Scout AI skill free?

Yes. It is published on GitHub by fancydirty under the 0BSD license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇