Pick Movie Theater logo

Pick Movie Theater

Community
AlphaMao1
pick-movie-theater

按影片版本、用户位置、具体影厅能力、当前场次与证据,推荐值得去的影院、具体影厅和选座区域。用于用户询问一部电影应该看什么厅、IMAX/杜比/CINITY/CGS/ScreenX/4DX/LED 等格式怎么选、附近或全城最佳影院、某场次是否匹配影片版本,以及有无选座截图时坐哪里。

Overview

PublisherAlphaMao1
RepositoryAlphaMao_Skills
Skill namepick-movie-theater
Stars
131
Forks
33
Bundled files
15
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.

  • 15 bundled files

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

  • Open source

    Published by AlphaMao1 on GitHub. Read the source before you install it.

Installation

Install the Pick Movie Theater 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.
    https://github.com/AlphaMao1/AlphaMao_Skills/tree/main/skills/pick-movie-theater
  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/AlphaMao1/AlphaMao_Skills.git /tmp/AlphaMao_Skills
mkdir -p .claude/skills
cp -r /tmp/AlphaMao_Skills/skills/pick-movie-theater .claude/skills/pick-movie-theater
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pick Movie Theater 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 Pick Movie Theater 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 Pick Movie Theater 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.

选影院、影厅与座位

给用户一个能直接购票的结论,同时保留影片版本、具体影厅、场次、证据和搜索覆盖边界。不要把影院品牌、影厅理论能力或社交热度直接当成影片在当前场次中的真实体验。

核心边界

  • 不依赖付费 API。
  • 不要求登录态。
  • 不要求用户提供选座截图。
  • 不维护或假设存在预建的全国影院、影厅事实库;每次从公开来源搜索。
  • 不要求 Cookie、密码或 token,不绕过登录、验证码或反爬限制。
  • 不执行购票、锁座、点赞、收藏、关注、评论或发布。
  • 影片版本、影院、具体影厅、场次是四个不同对象;上层能力不能自动传递给下层。

只要已有“影片名称”和能限定城市的“位置”,就开始核心流程。日期缺失时搜索下一批可公开确认的场次并标明时间窗口;偏好缺失时采用画面、声音、交通和证据质量平衡的模式。只有影片重名、城市不明或限制条件会实质改变结论时才追问。

按需读取参考资料

每次运行先读取:

  1. references/film-version-card.md:建立带地区和日期边界的影片版本卡。
  2. references/source-and-evidence-policy.md:给字段和结论分级,处理冲突与时效。
  3. references/search-playbook.md:从全城发现候选并执行覆盖审计。
  4. references/hall-and-screening.md:核验影院、具体影厅和场次。
  5. references/format-taxonomy.md:区分所有效果型格式、购票标签和普通用户选择逻辑。
  6. references/decision-and-output.md:过硬门槛、排序并生成用户结果。

进入选座步骤时读取 references/seat-selection.md。只有维护或验收本 Skill 时读取 references/requirements-traceability.md。

工作流

1. 解析请求

提取影片、位置、日期、最大通勤时间、人数和偏好。识别避免 3D、动感、喷水、眩晕、强音量、字幕仰视等限制。截图和用户链接只作为可选补充。

把场次状态统一标为:

  • 当前可确认:可重新打开的官方/票务排片在同一影片区块内同时定位到日期、影院、影厅和版本标注。
  • 条件式候选:影厅能力可确认,但当前排片或影片版本仍待核验。
  • 理论最佳:只说明能力上限,不暗示当前可购。

2. 建立影片版本卡

先查影片端,再查影院端。区分拍摄/创作格式、专用后期或母版、当地发行版本、当前场次实际可取得的版本。对每个字段写明“已确认/合理推断/未知”,并记录地区、日期和来源。

3. 划分发现范围与推荐范围

默认在整个城市发现优质候选,不因用户只给出区县而停止在区县内。日常推荐以约 45 分钟交通为参考;体验能力发生显著跃迁时可扩展到约 90 分钟;本地不存在的稀缺格式才进入跨城增强建议。路线不可得时使用距离或行政区近似并明确标注。

4. 多入口召回候选

先按 references/search-playbook.md 建立全城“效果优先候选全集”:逐项搜索 IMAX、Dolby、CINITY、CGS、影院 LED、ScreenX、动感/环境效果、沉浸声和其他 PLF 九个家族,并覆盖城市下辖区县、县级市和新区。不能用一次宽泛搜索代表全部家族已经覆盖,也不能因影片暂时没有某格式就跳过本地候选发现。

再执行影片/格式官方入口、口碑、近期升级和候选滚雪球。普通网页和公开社交页面承担发现与补漏;不让单一社交帖子证明技术规格。固定检查“院线电影资料库”时只使用其微博渠道,不重复检查同一运营者的小红书渠道。

去重影院别名、旧名和同址名称。候选进入深入核验层后,再搜索影院全名、厅号、设备、银幕、升级、排片和负面体验,避免对全市普通影院做无差别穷举。

5. 核验具体影厅与场次

为每个候选建立字段级事实表。首选必须尽可能落到具体影厅;无法确认厅号时明确暴露,不把同一影院其他厅的能力继承过来。核对公告日期、改名、改厅号、设备升级和过期排片。

票务页混排多部影片时,把目标影片标题到下一影片标题之间视为一个影片区块。日期、时间、影院、厅号和购票标签必须来自同一区块;搜索摘要、页面其他影片或页面级推荐位中的字段不得跨区块拼接。只有搜索引擎索引快照而原始页无法重新核对时,降为条件式候选。

营销名称只产生待核验线索。按 references/format-taxonomy.md 拆成投影、光源、分辨率、机型数量、有效画幅、银幕、声音、影片专用版本和认证状态。

对任何格式家族都不能只输出品牌名。把购票标签翻译成普通用户能采取行动的差异:具体类型、它保证什么、不保证什么、本片实际增量、银幕与遮幅是否匹配,以及为什么选它而不是同品牌或其他格式候选。

6. 过硬门槛并排序

先应用四个门槛:

  1. 当地有该影片版本,或明确标为待确认。
  2. 具体影厅能呈现决定推荐的增量。
  3. 有对应场次,或明确输出为条件式候选。
  4. 决定性字段证据足够且未被更新信息推翻。

门槛通过后,再比较影片增量、画面、声音、观看几何、当前可用性、交通、价格、用户偏好和证据风险。证据风险足以改变结论时降级排名或改成条件式建议;不要用品牌总分覆盖门槛。

7. 给出选座建议

没有截图也继续。优先取得银幕方向、总排数、座位图、银幕尺寸和座位距离;数据允许时可运行:

powershell
python -X utf8 scripts/decision_support.py seat --screen-width-m 20 --seat-distance-m 20 --lateral-offset-m 0 --screen-top-delta-m 5

输出平衡首选区、更沉浸区、更舒适区和应避开的风险区,并标明是计算、可靠推断还是通用经验。没有足够几何和余座信息时不精确到具体座号。

用户自愿提供清晰选座截图时,才识别当前可售座位并给首选、前后排备选和多人连座备选。截图模糊、裁切或状态不明时降低精度;注明核查时间,不承诺座位仍可售。

8. 执行证据与覆盖审计

决定首选前检查每个决定性事实。可把事实包传给:

powershell
python -X utf8 scripts/decision_support.py evidence --input evidence.json

所有声称有具体排片的候选先保留同区块字段绑定,再运行:

powershell
python -X utf8 scripts/decision_support.py screenings --input screenings.json

有无效绑定时删除错误场次并重新核验;只有搜索索引快照时按脚本结果降为条件式。把场次绑定审计结果放入覆盖包。

搜索停止前记录入口、格式家族、新增候选、候选状态和受阻来源,并可运行:

powershell
python -X utf8 scripts/decision_support.py coverage --input coverage.json

只有官方相关入口已检查、九个效果型格式家族逐项完成、规定入口已执行、连续两个独立补漏入口零新增、其余候选均已核验或标为未解决,且场次绑定审计没有跨影片/跨区块错误时,才写“本轮优质候选搜索达到饱和”。永远不要声称所有影院零遗漏。

默认输出

按以下顺序给结果,开头先说用户下一步该买什么:

  1. 直接结论:影院、具体影厅、日期/场次状态、推荐格式。
  2. 首选及取舍:本片实际多得到什么,交通、价格或舒适上付出什么。
  3. 更近/更稳/更便宜的备选:只列真正合格的方案。
  4. 格式差异翻译:用户在票务页会看到什么标签、候选实际是哪一代/哪种能力、为什么不是“都一样”。
  5. 选座:平衡、沉浸、舒适和避雷区域;有截图时再给当前具体座位。
  6. 关键依据:决定性事实、来源链接、发布日期或核查日期、证据等级和置信度。
  7. 覆盖说明:九个效果型格式家族、搜索入口、停止原因、受阻来源、未确认项和购票前复核动作。

只有高热度候选容易让用户误选时才列“不推荐”,并给出可验证原因。没有合格方案时直接说明,不为凑数量编造三个推荐。

失败降级

  • 没有相关候选:说明已覆盖入口,并给普通厅或扩大范围的下一步。
  • 来源不可访问:写“来源不可访问”,不要写成“没有相关内容”。
  • 有候选但参数不足:保留为待核验候选,列出缺的决定性字段。
  • 影厅能力可确认但排片不明:输出条件式候选,要求购票前核对具体厅号和版本。
  • 票务页混排多片或只能取得搜索索引快照:保留为排片线索;不能证明同区块绑定或无法重开原页时输出条件式候选。
  • 有场次但真实版本不明:引用票务标注,但不把标注升级成已确认能力。
  • 有座位图但当前余座不明:只给区域,不猜具体可售座位。

使用已有登录态 Chrome 搜索小红书等平台属于可选增强:先取得用户明确同意,只对已收敛候选做只读精确搜索;遇验证码或访问限制立即停止并按公开模式继续。

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 Pick Movie Theater AI skill do?

按影片版本、用户位置、具体影厅能力、当前场次与证据,推荐值得去的影院、具体影厅和选座区域。用于用户询问一部电影应该看什么厅、IMAX/杜比/CINITY/CGS/ScreenX/4DX/LED 等格式怎么选、附近或全城最佳影院、某场次是否匹配影片版本,以及有无选座截图时坐哪里。

Why use Pick Movie Theater on TypingMind?

Because you install it once and use it with any model. Pick Movie Theater 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 Pick Movie Theater in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AlphaMao1/AlphaMao_Skills/tree/main/skills/pick-movie-theater. 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 Pick Movie Theater?

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 Pick Movie Theater?

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

Is the Pick Movie Theater AI skill free?

It is published on GitHub by AlphaMao1. Check the repository for licensing terms. 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 👇