Skip to content
Back to skills

Diverge

ASecurity

Spawn multiple perspectives to evaluate a problem before converging on a solution.

  • 17 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 6, 2026
code-qualitysecurityperformance

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned September 6, 2026

npx -y skills add clawic/skills --skill diverge --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Diverge?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Diverge
[![Security: A β€” Skills Directory](https://www.skillsdirectory.com/api/skills/clawic-diverge/badge)](https://www.skillsdirectory.com/skills/clawic-diverge)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: Diverge
slug: diverge
version: 1.0.0
description: Spawn multiple perspectives to evaluate a problem before converging on a solution.
homepage: https://clawic.com/skills/diverge
metadata:
  clawdbot:
    emoji: 🌿
    displayName: Diverge
---

## When to Diverge

Diverge when a single viewpoint isn't enough:
- **Product decisions** β€” Different user types have conflicting needs
- **Safety-critical** β€” Need doctor, lawyer, security expert perspectives
- **Creative work** β€” Multiple aesthetic directions before choosing
- **Complex trade-offs** β€” No obvious "right" answer

Don't diverge for:
- Simple tasks with clear answers
- Speed-critical requests
- Tasks where you already have high confidence

## How Many Perspectives

| Complexity | Perspectives | Examples |
|------------|--------------|----------|
| Low | 2-3 | Quick sanity check |
| Medium | 3-5 | Product feature review |
| High | 5-7 | Safety-critical, legal |

**Rule:** Enough to cover blind spots, not so many you can't synthesize.

## Choosing Perspectives

Match perspectives to the problem:

- **Product:** Power user, casual user, churned user, new user
- **Medical:** Doctor, patient, caregiver, insurance
- **Legal:** Lawyer, affected party, regulator
- **Technical:** Security, performance, maintainability
- **Content:** Target audience, critic, competitor

Check `personas.md` for common perspective templates.

## Synthesis

After collecting perspectives:
1. **Identify conflicts** β€” Where do perspectives disagree?
2. **Find common ground** β€” What do all perspectives agree on?
3. **Weigh by stakes** β€” Safety concerns > preferences
4. **Decide** β€” Make a call, document trade-offs

Check `synthesis.md` for conflict resolution patterns.

## Learning User Preferences

Track when divergence helped vs. was overkill. Adapt:
- User who values speed β†’ diverge less, ask before spawning
- User who values thoroughness β†’ diverge more proactively

---

**Related:** For routing tasks to sub-agents, see `delegate`. For iterating until success, see `loop`.

Files in this skill

  • SKILL.md2 KB
  • _meta.json166 B
  • personas.md1.6 KB
  • synthesis.md1.6 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…