Qifei Proposal V2

Community

chenxupeng1990-eng

qifei-proposal-v2

公司提案总控：把品牌需求做成有观点、能打动评审、可视觉化交付的竞争性提案或提案模块（比稿、品牌提案、营销方案 PPT、飞书提案母稿、提案视觉与讲稿、导出 PNG/PDF/PPTX）。按项目阶段渐进加载规则，内置策略、内容、视觉、评审与导出门禁，支持 Codex、API Agent 与本地运行环境。也用于品牌手册、品牌视觉画册这类以视觉表现为主的演示文件（视觉表现型路径：整页生图、文字一并画入）。用户说“做提案”“比稿”“写方案 PPT”“继续这个提案项目”“做提案里的某个模块”“做品牌手册”“做品牌画册”时使用。不用于通用文档排版、单张海报或与提案无关的 PPT 美化。已有确认的页面大纲和视觉方向、只需要出页面时，用 proposal-ppt-production。

Overview

Publisher	chenxupeng1990-eng
Repository	`qifei-proposal-skill`
Skill name	`qifei-proposal-v2`
Stars	74
Forks	4
Bundled files	129
Links	Skill source Repository

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.
129 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by chenxupeng1990-eng on GitHub. Read the source before you install it.

Installation

Install the Qifei Proposal V2 AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/chenxupeng1990-eng/qifei-proposal-skill/tree/codex/qifei-proposal-base/skills/qifei-proposal-v2
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/chenxupeng1990-eng/qifei-proposal-skill/tree/codex/qifei-proposal-base/skills/qifei-proposal-v2

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

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/chenxupeng1990-eng/qifei-proposal-skill.git /tmp/qifei-proposal-skill
mkdir -p .claude/skills
cp -r /tmp/qifei-proposal-skill/skills/qifei-proposal-v2 .claude/skills/qifei-proposal-v2

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Qifei Proposal V2 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 Qifei Proposal V2 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 Qifei Proposal V2 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.

公司提案总控 V2

V1 $qifei-proposal 已弃用并从仓库移除，一律使用 V2。V2 沿用 V1 的项目结构和机器校验器，把执行规则拆成阶段包，避免无关规则同时占用上下文。

永久规则

完整读取本文件与 agent.md。
先按 references/task-modes-and-runtime.md 确定 task_mode 和任务性质 task_nature：开项目时先问用户这份 PPT 要“强逻辑叙述”（persuasive）还是“视觉表现力”（visual_showcase），按需求给出建议和理由，由用户选定，写进策划书的“表达方式”并用 init_project.py --task-nature 记录（问法见 runtime 说明 1.1 节）；运行 doctor.py --project <项目目录>（同时输出本阶段的提案记忆；doctor 看不到 Agent 自己的工具，能生图时加 --image-provider <名称>，能看图时加 --visual-understanding，有 Codex 原生浏览器评论时加 --native-comments，见 runtime 说明第 3 节），向用户说明本次能交付到哪一步。doctor 列出能力缺口（GAP）时，不得默认降级：先逐项问用户能否按列出的办法补齐，补齐后重跑 doctor；用户明确选择暂不补齐，才运行 doctor.py --project <项目目录> --accept-gap <缺口> --by <Owner> 记录，此后缺失的能力只阻塞依赖它的阶段（见 references/environment-degradation.md）。doctor 输出 UPDATE 行时，用一两句大白话转告用户有新版本、更新了什么、说“更新提案 skill”就能更新；不打断当前任务，不自动更新。用户要更新时运行 python3 scripts/update_skill.py run，完成后提醒用户重启 Agent；用户不想再收到提醒时运行 update_skill.py off。
Python可用后运行 python3 scripts/check_suite_dependencies.py；完整套件缺失时停止，环境能力缺失按Doctor结果路由。
读取项目 AGENTS.md 与 project-state.json，以 phase 选择且只选择一个当前阶段包。
完整读取当前阶段包；只读取该阶段包明确列出的 reference，不预读未来阶段。提案记忆按 references/proposal-memory.md 使用，Agent 只需记住两个命令：Owner 在对话里给出可复用的更正时，当场运行 proposal_memory.py note；换阶段时运行 proposal_memory.py advance --project <项目目录> --to <新阶段>，按输出写候选、读新阶段记忆，再改 phase。记忆校准判断，不是事实；doctor.py 和 validate_project.py 会带出记忆并检查是否读过。用户要求关闭记忆时运行 proposal_memory.py off（全局生效）；doctor.py 显示提案记忆已关闭时，跳过 note 和 advance。
当前阶段产物必须通过 python3 scripts/validate_project.py <项目目录>；机器通过不等于 Owner 批准。
Proposal Owner 是唯一阶段批准者。口头确认、评论关闭、写入成功或 Agent 自检不能替代客观门禁。
用户已确认的项目事实、策略与场外决定是只读权威；不得在后续审查中重新审判。
对外内容必须有立场、观点和决策推动；中立、保守或只做风险判断不能替代策划。
内容权威由任务模式决定：完整提案默认工作台（可选飞书），继承模块沿用父项目，独立模块可选工作台、飞书或本地Markdown。
不跨阶段执行，不因任务简单、用户连续说“确认”或已有文件而补记批准；视觉、校准、并行生产和讲稿的专门规则只在对应阶段包中生效。

阶段路由

`project-state.json.phase`	必须读取的阶段包
`intake`, `requirements`	phase-packs/01-intake-brief.md
`strategy`, `project_agents`	phase-packs/02-strategy-outline.md
`manuscript`	phase-packs/03-manuscript-feishu.md
`full_redteam`, `content_frozen`	phase-packs/04-full-draft-review.md
`visual_direction`	phase-packs/05-visual-direction.md
`design_calibration`, `design_system`	phase-packs/06-design-calibration.md
`generation`, `review`	phase-packs/07-page-production-review.md
`speaker_notes`, `qa`, `export`	phase-packs/08-speaker-export.md

未知 phase 立即停止，不猜测阶段。

通用命令

bash
python3 scripts/doctor.py --task-mode <full_deck|inherited_module|standalone_module> --project <项目目录> --json
python3 scripts/init_project.py --project <项目目录> --name <项目名> --owner <Owner> --task-mode <模式>
python3 scripts/validate_project.py <项目目录>

其余命令仅在对应阶段包要求时使用。

Bundled files

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

and 69 more files.

Frequently asked questions

What does the Qifei Proposal V2 AI skill do?

Why use Qifei Proposal V2 on TypingMind?

Because you install it once and use it with any model. Qifei Proposal V2 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 Qifei Proposal V2 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/chenxupeng1990-eng/qifei-proposal-skill/tree/codex/qifei-proposal-base/skills/qifei-proposal-v2. 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 Qifei Proposal V2?

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 Qifei Proposal V2?

As many as you like. As long as a model supports skills, you can use Qifei Proposal V2 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Qifei Proposal V2 AI skill free?

It is published on GitHub by chenxupeng1990-eng. 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

Diffs

openclaw

OrganizationPopular

Use the diffs tool to produce real, shareable diffs (viewer URL, file artifact, or both) instead of manual edit summaries.

Feishu Doc

Feishu document read/write workflows. Activate when the user mentions Feishu docs, cloud docs, or docx links.

Feishu Drive

Feishu cloud-storage and comment workflows. Activate when the user mentions cloud space, folders, Drive files, or document comments.

Feishu Wiki

Feishu knowledge-base navigation workflows. Activate when the user mentions a knowledge base, wiki, or wiki link.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

公司提案总控 V2

永久规则

阶段路由

通用命令

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now