跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
演示文稿

before-after

Generate emotional Before/After transformation grids for products, lectures, and offers. Chainable from humane:jtbd output. Uses empathy mapping, first-person voice, somatic markers, and valence scoring to produce grids ready for landing pages, slides, and messaging. This skill should be used when the user wants to articulate the transformation their product/service creates, build a before/after grid, or chain from a JTBD interview into emotional copywriting. Triggers on before/after grid, transformation grid, "what's the transformation", landing page transformation section, emotional copywriting, chain from JTBD.

glebis · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add glebis/humane-agentic-design --skill before-after

技能说明


name: before-after description: Generate emotional Before/After transformation grids for products, lectures, and offers. Chainable from humane:jtbd output. Uses empathy mapping, first-person voice, somatic markers, and valence scoring to produce grids ready for landing pages, slides, and messaging. This skill should be used when the user wants to articulate the transformation their product/service creates, build a before/after grid, or chain from a JTBD interview into emotional copywriting. Triggers on before/after grid, transformation grid, "what's the transformation", landing page transformation section, emotional copywriting, chain from JTBD. handoffs:

  • to: jtbd when: the transformation claim has no evidence behind it in the corpus accepts:
  • from: jtbd

Before/After Transformation Grid

Announce at start: "I'm using the humane:before-after skill to capture the felt transformation as a before/after grid."

Generate emotionally precise Before/After grids that capture the felt transformation a product, lecture, or service creates. Not feature lists — lived experience shifts.

When to invoke

  • "Build a before/after grid"
  • "What's the transformation?"
  • "Chain this JTBD into a before/after"
  • "I need a landing page transformation section"
  • After completing a humane:jtbd interview, as a natural next step

Mode selection

ModeInputFlow
Chained (preferred)Path to <corpus_root>/<slug>/jtbd.jsonAuto-map → present draft → sharpen
StandaloneNoneQuick interview (3 questions) → draft → sharpen

<corpus_root> throughout is the setup setting of that name — default ~/jtbd, but read the configured value. Writing to the default when the user has moved their corpus scatters the bundle across two roots.


Chained Mode: JTBD → Grid

When a jtbd.json path is provided (or exists from the current session):

Step 1: Auto-map dimensions

Extract dimensions from JTBD data using this mapping:

JTBD fieldGrid dimension
switch_forces.pushPrimary BEFORE state
switch_forces.pullPrimary AFTER state
switch_forces.habitBEFORE — inertia/stuckness dimension
switch_forces.anxietyBEFORE — fear dimension (flip to confidence in AFTER)
problem.what_hurtsBEFORE — pain dimension
needs.functional[]AFTER — capability dimensions
needs.emotional[]AFTER — feeling dimensions
jtbd.outcomeAFTER — north star
jtbd.situationBEFORE — triggering context

Generate 5-9 dimensions. Each dimension gets a short label (2-4 words).

Step 2: Draft the grid with emotional depth

For each dimension, write BEFORE and AFTER cells using these techniques:

First-person voice: Always "I..." not "The user..."

  • BEFORE: "I check my API dashboard with dread every morning"
  • AFTER: "I glance at costs once a week, casually"

Somatic markers: Include body-level experience where natural

  • BEFORE: "My stomach drops when I see 'service unavailable'"
  • AFTER: "I shrug — the fallback kicks in, I keep working"

Behavioral evidence: What they actually DO, not just feel

  • BEFORE: "I google alternatives at 2am but never install anything"
  • AFTER: "I have three providers configured and tested"

Inner monologue: What they'd say out loud

  • BEFORE: "What if they ban my country next week?"
  • AFTER: "Even if they do, I'm covered"

Emotional valence scoring: Rate each dimension's shift from -3 (deeply negative) to +3 (deeply positive). Most BEFORE states sit at -1 to -3. Most AFTER states at +1 to +3. The delta indicates transformation intensity.

Step 3: Present and sharpen

Present the draft grid as a markdown table. Then ask targeted questions to increase emotional precision:

  • "For [dimension X] — what does this feel like in the body? Chest tight? Shoulders up?"
  • "In the BEFORE state of [dimension Y] — what would you literally say to a friend over coffee?"
  • "Is the AFTER for [dimension Z] relief (absence of pain) or genuine excitement (presence of new energy)?"
  • "Which of these dimensions hits hardest? Which feels lukewarm?"

Apply edits. Remove lukewarm dimensions. Intensify the strongest ones.

Step 4: Polish pass — Emotion Modulation

Review the completed grid through these lenses:

Contrast ratio: Each row should have clear negative→positive movement. If both cells feel neutral, either sharpen or cut.

Specificity gradient: At least 3 dimensions should include a specific named thing (a tool, a moment, a number, a sensation). Generic grids don't land.

Empathy mapping check: Across the full grid, verify coverage of:

  • Think (beliefs, mental models)
  • Feel (emotions, physical sensations)
  • Do (behaviors, actions)
  • Say (inner monologue, things they'd tell others)

If any quadrant is missing across all dimensions, add one dimension that covers it.

Temporal variety: Mix immediate states ("right now I feel..."), habitual states ("every Monday I..."), and identity states ("I am the kind of person who...").


Standalone Mode

When no JTBD input exists:

Quick interview (3 questions, one at a time)

  1. "Who is transforming, and what's the situation they're stuck in?"
  2. "What's painful about today — what do they feel, do, and say?"
  3. "After your thing works — what's different? Not features. How does Tuesday morning feel different from before?"

Then proceed to Step 2 (Draft) using the interview answers as dimension seeds.


Output format

Markdown table (always produced)

## Before/After: [Project Name]

| Dimension | BEFORE (-valence) | AFTER (+valence) |
|-----------|-------------------|------------------|
| **Label** | First-person felt state | First-person felt state |

JSON structure (produced on request or when saving to <corpus_root>/<slug>/)

{
  "project": "slug",
  "dimensions": [
    {
      "label": "Provider dependency",
      "
阅读完整来源 ↗