Transforms product documentation into sales-ready packages — a story explanation, charcoal gestural sketch art, and talking points — via a narrative-arc pipelin
复制下面这句话,粘贴给 Claude Code、Codex、Cursor 等 AI 编程工具,它会读取安装说明并在你确认后完成安装。
请阅读 https://ai.atlankj.com/install/asset/gh-sales-b321f93ed6a8 ,按照其中的说明把「Sales」安装到你(当前 AI 工具)中。执行前先告诉我将运行的命令和写入的位置,等我确认。
查看 AI 将读取的安装说明正在读取 GitHub 原文…
内容来自 GitHub 原始文件,由原作者维护。在 GitHub 查看
Before executing, check for user customizations at:
~/.claude/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/Sales/
If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.
You MUST send this notification BEFORE doing anything else when this skill is invoked.
Send voice notification:
curl -s -X POST http://localhost:31337/notify \
-H "Content-Type: application/json" \
-d '{"message": "Running the WORKFLOWNAME workflow in the Sales skill to ACTION"}' \
> /dev/null 2>&1 &
Output text notification:
Running the **WorkflowName** workflow in the **Sales** skill to ACTION...
This is not optional. Execute this curl command immediately upon skill invocation.
Turns product documentation into a sales-ready package: a story narrative that captures the value proposition, a charcoal gestural sketch that conveys the concept visually, and clear talking points. It reads the real value out of technical docs and reframes it as something a sales team can actually use in a pitch.
Product docs explain what a thing does. Sales needs to explain why it matters — and the gap between the two is where most pitches die. Hand a sales team a feature list and they read off bullet points; the buyer feels nothing and forgets it. The translation from "here's what it does" to "here's the story you'll remember" usually takes a writer and a designer and a few days, so it doesn't happen, and the product gets sold flat. This skill does that translation: it pulls the narrative arc out of the docs, finds the emotional register, and generates the narrative plus a matching visual tied directly to what's being sold.
The pipeline runs in four steps, from raw docs to a finished package:
PRODUCT DOCUMENTATION
↓
[1] STORY EXPLANATION — Extract the narrative arc (what's the real value?)
↓
[2] EMOTIONAL REGISTER — What feeling should this evoke? (wonder, determination, hope, etc.)
↓
[3] VISUAL CONCEPT — Derive scene from narrative + emotion
↓
[4] GENERATE ASSETS — Create visual + narrative package
↓
SALES-READY OUTPUT
It produces three things: sales narratives (story explanations that capture the value proposition), visual assets (charcoal sketch art that conveys the concept), and scripts (clear, succinct messaging tied to what you're selling). Internally it leans on the story-explanation narrative engine and the Art essay-art workflow for the visual.
| Workflow | Trigger | File |
|---|---|---|
| CreateSalesPackage | Full sales package — "create a sales package", product docs in, narrative + charcoal sketch + key talking points out | Workflows/CreateSalesPackage.md |
| CreateNarrative | Sales narrative only — "turn this into a pitch", "create a sales story", technical docs to compelling narrative | Workflows/CreateNarrative.md |
| CreateVisual | Visual asset only — "create a visual for this sales story", charcoal sketch for an existing narrative | Workflows/CreateVisual.md |
Input: Technical documentation about AI code review tool
Output:
This skill combines:
The goal: Sales teams get materials that are highly tied to what they're selling, clear, succinct, and effective.
Example 1: Full sales package from docs
User: "create a sales package for this product" [provides docs]
→ Extracts narrative arc using storyexplanation
→ Determines emotional register (wonder, determination, hope)
→ Generates charcoal sketch visual + narrative + talking points
Example 2: Sales narrative only
User: "turn this technical doc into a sales pitch"
→ Reads documentation and extracts value proposition
→ Creates 8-24 point story explanation in first person
→ Returns conversational narrative ready for sales scripts
Example 3: Visual asset for existing narrative
User: "create a visual for this sales story"
→ Analyzes narrative for emotional core
→ Derives scene concept from story + emotion
→ Generates charcoal gestural sketch with transparent background
After completing any workflow, append a single JSONL entry:
echo '{"ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","skill":"Sales","workflow":"WORKFLOW_USED","input":"8_WORD_SUMMARY","status":"ok|error","duration_s":SECONDS}' >> ~/.claude/LIFEOS/MEMORY/SKILLS/execution.jsonl
Replace WORKFLOW_USED with the workflow executed, 8_WORD_SUMMARY with a brief input description, and SECONDS with approximate wall-clock time. Log status: "error" if the workflow failed.