Lov Bp Deck logo

Lov Bp Deck

Organization
lovstudio
lov-bp-deck

Turn an approved investor BP outline into a clean, professional slide deck with deliberate style selection, real product evidence, charts, branding, PPTX/PDF, and a full-deck preview. Use when the narrative already exists and the user wants PPT production, visual style exploration, slide regeneration, or export. Trigger on "把 BP 大纲做成 PPT", "选择 BP 风格", "生成融资 PPT", "重做第几页", "BP deck", "pitch deck design", "render investor slides", or "export BP PDF".

Overview

Publisherlovstudio
Repositoryskills
Skill namelov-bp-deck
Stars
67
Forks
17
Bundled files
3
LicenseMIT
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.

  • 3 bundled files

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

  • Open source

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

Installation

Install the Lov Bp Deck 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/lovstudio/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/bp-deck .claude/skills/lov-bp-deck
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lov Bp Deck 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 Lov Bp Deck 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 Lov Bp Deck 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.

BP 大师 · BP Master

Produce the presentation after the investment narrative is approved. This skill owns style selection, visual specification, rendering, export, and final-image QA; it does not invent missing business evidence.

Input Gate

Required:

  • approved outline.md or equivalent page-by-page narrative;
  • evidence/source notes for core claims;
  • project/company name.

Recommended:

  • brand logo and primary color;
  • real product screenshots;
  • founder/team photos;
  • source data for charts;
  • website/contact destination and QR asset.

If the outline lacks a clear product definition, financing ask, or source-backed core numbers, stop and recommend lov-bp-outline before rendering.

Output Contract

text
business-plan/
├── outline.md
├── assets/
├── deck-manifest.md
├── 01-slide-cover.png
├── ...
├── project-bp.pptx
├── project-bp.pdf
└── project-bp-preview.png

Workflow (MANDATORY)

Step 0: Resolve input and dependency

Resolve this skill directory as SKILL_DIR and locate the user's approved outline. Resolve lov-any2deck through the active Agent Skills environment; do not assume an author's private installation path.

Read references/user-config.md and references/charts-and-visuals.md.

Step 1: Lock the narrative

Do not rewrite the storyline during style exploration. Check:

  • 12–15 slides unless the user explicitly chooses otherwise;
  • one conclusion per slide;
  • evidence IDs/source notes on core claims;
  • chart type and exact data mapping;
  • no placeholder or fabricated metric.

Send evidence blockers back to bp-outline. Small copy corrections may be recorded in deck-manifest.md and applied without changing the thesis.

Step 2: Select style with minimal friction

Infer style from brand, audience, reference images, and the outline. If the user has not selected a direction, use AskUserQuestion once with 2–3 concrete options.

Recommended first option for seed-stage investors:

Clean editorial — white/warm-gray background, one brand color, dark conclusion headlines, real screenshots, consulting-grade charts, and restrained decoration.

Alternative options:

  • Product keynote — more whitespace and product/demo emphasis;
  • Consulting report — denser evidence and chart emphasis;
  • Reference-led — derive a design system from a supplied visual reference.

If the user says “按推荐方案” or “不要问”, use clean editorial.

Step 3: Write deck-manifest.md

Record before rendering:

  • outline path and version;
  • audience, language, slide count, and presentation duration;
  • style name, palette, typography, spacing, and safe margins;
  • logos, screenshots, photos, data, and QR assets;
  • naming convention;
  • expected PPTX/PDF/preview paths;
  • any slide intentionally marked illustrative.

Step 4: Generate with lov-any2deck

Invoke lov-any2deck using the approved outline and chosen style. Preserve the BP page order and evidence notes. Use 16:9, body text at least 20 pt, and a single dominant visual per page.

Prefer:

  • real product screenshots and user scenes;
  • process diagrams and evidence ladders;
  • source-backed charts with axes, units, dates, legends, and notes;
  • simple cover and one clear final contact action.

Avoid stock-photo filler, decorative card walls, gradients, tiny source text, fake dashboards, and unsourced growth curves.

Step 5: Export and inspect

Produce editable PPTX, PDF, all slide images, and one full-deck preview. Review every page at presentation size:

  • no clipped/overlapping text or broken CJK;
  • title/body/source hierarchy is consistent;
  • logos are optically balanced;
  • images are not stretched;
  • chart values match the evidence ledger;
  • product screenshots are genuine and legible;
  • QR codes decode from the final rendered slide;
  • PPTX and PDF page counts match;
  • filenames include project, document type, and date/version.

Regenerate only affected slides. Record the result in deck-manifest.md.

Step 6: Handoff

Return PPTX, PDF, preview, manifest, and any unresolved visual risks. Recommend lov-bp-polish for an adversarial final review.

Recommended Next Step

text
$lov-bp-polish ./business-plan/project-bp.pdf --full

Runtime context (shared)

运行前读取本 Skill 包的 skill.yaml,由宿主提供 skill-runtime/v1 上下文。字段解析顺序为:当前请求、项目上下文、个人 Preferences、品牌 Profile、通用默认值。

  • 只使用 Manifest 声明的字段;Profile 保存公开品牌事实,Preferences 保存个人工作偏好。
  • required: true 字段缺失时,按 Manifest 的问题配置向用户提出一个聚焦问题;用户明确同意后再保存回答。
  • 报错提供可复制的 context_id、字段路径与来源,诊断内容避开秘密、完整私人路径和原始配置。

通用反馈闭环

用户在 Skill 驱动任务中提出修改意见时,继续当前产物前必须执行:

  1. 先判断意见是 task-specific(仅本次)还是 reusable(可跨任务复用)。
  2. task-specific 只修改当前任务,不改 Skill。
  3. reusable 先确定作用域:领域规则先更新对应 canonical Skill;适用于所有 Skill 的规则先更新共享规范。
  4. 完成规则更新、版本、lint 与分发核验后,再把修改应用到当前任务。
  5. reusable 修改会使此前的“确认”“继续”“发吧”失效;完成当前产物修改和回读后必须停下,等待用户下一步指示,不自动进入发布、提交或其他外部写入。

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 Lov Bp Deck AI skill do?

Turn an approved investor BP outline into a clean, professional slide deck with deliberate style selection, real product evidence, charts, branding, PPTX/PDF, and a full-deck preview. Use when the narrative already exists and the user wants PPT production, visual style exploration, slide regeneration, or export. Trigger on "把 BP 大纲做成 PPT", "选择 BP 风格", "生成融资 PPT", "重做第几页", "BP deck", "pitch deck design", "render investor slides", or "export BP PDF".

Why use Lov Bp Deck on TypingMind?

Because you install it once and use it with any model. Lov Bp Deck 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 Lov Bp Deck in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/lovstudio/skills/tree/main/skills/bp-deck. 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 Lov Bp Deck?

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 Lov Bp Deck?

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

Is the Lov Bp Deck AI skill free?

Yes. It is published on GitHub by lovstudio under the MIT 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 👇