Refactor high-complexity React components in Dify frontend. Use when `pnpm analyze-component...
npx skills add neurofoo/agent-skills --skill "wrap"
Install specific skill from multi-skill repository
# Description
WRAP decision framework countering the four villains—narrow framing, confirmation bias, short-term emotion, and overconfidence. Use for major decisions or when stuck between options.
# SKILL.md
name: wrap
description: WRAP decision framework countering the four villains—narrow framing, confirmation bias, short-term emotion, and overconfidence. Use for major decisions or when stuck between options.
user-invocable: true
WRAP Decision Framework
Apply the complete WRAP framework to make a better decision by countering the four villains of decision-making.
Instructions
Work through all four phases sequentially. Each phase targets a specific cognitive bias that undermines good decisions.
Output Format
Decision: [What are we deciding?]
Context: [Key constraints and stakes]
W: WIDEN Your Options
Counter: Narrow Framing ("Should I do X?" → "What are all my options?")
Current Framing
How is the decision currently framed? (Often as "whether or not")
Expanded Options
| # | Option | Why It's Worth Considering |
|---|--------|---------------------------|
| 1 | [option] | [rationale] |
| 2 | [option] | [rationale] |
| 3 | [option] | [rationale] |
| 4 | [option] | [rationale] |
Option-Finding Techniques
- Vanishing options test: "If you couldn't do X, what would you do?"
- Opportunity cost: "What else could you do with this time/money?"
- Find someone who solved it: "Who's had this problem?"
R: REALITY-TEST Your Assumptions
Counter: Confirmation Bias (seeking evidence that confirms what we want)
Key Assumptions
| Assumption | How Would We Know If Wrong? |
|------------|----------------------------|
| [assumption 1] | [test] |
| [assumption 2] | [test] |
Consider the Opposite
For each option, what would it take to be convinced it's wrong?
Ooch
Is there a small experiment we can run to test this before fully committing?
| Option | Small Test | What We'd Learn |
|---|---|---|
| [option] | [test] | [insight] |
A: ATTAIN Distance Before Deciding
Counter: Short-term Emotion (deciding when angry, excited, or desperate)
10/10/10
| Time Horizon | How will you feel about this decision? |
|--------------|----------------------------------------|
| 10 minutes | [how you feel now] |
| 10 months | [how you'll likely feel] |
| 10 years | [long-term perspective] |
What Would I Tell My Best Friend?
If someone you loved faced this decision, what would you tell them?
P: PREPARE to Be Wrong
Counter: Overconfidence ("I'm sure this will work")
Premortem
Imagine this decision failed completely. What went wrong?
| Failure Mode | How to Prevent/Detect |
|---|---|
| [what could fail] | [safeguard] |
Tripwires
Set a future point to reconsider:
| Tripwire | Action If Triggered |
|---|---|
| [date or condition] | [what we'll do] |
Decision
Recommendation
Based on the WRAP analysis:
[Your decision and reasoning]
Key Safeguards
- [Safeguard 1]
- [Safeguard 2]
Review Date: [When to reassess]
Guidelines
- Don't skip phases—each counters a different bias
- "Should I?" is almost always narrow framing
- Look for the third option beyond the obvious two
- Ooch when you can—small tests beat big analysis
- Set tripwires before you need them
$ARGUMENTS
# Supported AI Coding Agents
This skill is compatible with the SKILL.md standard and works with all major AI coding agents:
Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.