# Problem Solving

> Use when stuck after repeated failed attempts, when conventional approaches are not producing progress, when a problem needs reframing, when an elegant simplification may remove complexity, or when complex problems require systematic step-by-step reasoning with the ability to revise thoughts, branch into alternatives, or adjust initially unclear scope. Provides collision-zone thinking, inversion,…

- **Type:** Skill
- **Install:** `agentstack add skill-danielleit241-my-skills-problem-solving`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [danielleit241](https://agentstack.voostack.com/s/danielleit241)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** ISC
- **Upstream author:** [danielleit241](https://github.com/danielleit241)
- **Source:** https://github.com/danielleit241/forge/tree/main/skills/problem-solving

## Install

```sh
agentstack add skill-danielleit241-my-skills-problem-solving
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Problem-Solving Skills

A collection of techniques for breaking through stuck points and finding elegant solutions.

## Available Sub-Skills

### Collision-Zone Thinking
**Location:** `collision-zone-thinking/SKILL.md`

Force unrelated concepts together to discover emergent properties. "What if we treated X like Y?" Revolutionary insights come from deliberate metaphor-mixing.

### Inversion Exercise
**Location:** `inversion-exercise/SKILL.md`

Flip every assumption and see what still works. "What if the opposite were true?" Exposes hidden constraints and alternative approaches.

### Meta-Pattern Recognition
**Location:** `meta-pattern-recognition/SKILL.md`

Spot patterns appearing in 3+ domains to find universal principles. Extract abstract forms that apply across domains.

### Scale Game
**Location:** `scale-game/SKILL.md`

Test at extremes (1000x bigger/smaller) to expose fundamental truths. What breaks? What survives? Extremes reveal what normal scales hide.

### Simplification Cascades
**Location:** `simplification-cascades/SKILL.md`

Find one insight that eliminates multiple components. "If this is true, we don't need X, Y, or Z." Look for unifying principles.

### Sequential Thinking
**Location:** `references/sequential-thinking.md`

Structured, revisable step-by-step reasoning via the MCP tool
`mcp__sequential-thinking__sequentialthinking`. For multi-stage analysis, design
planning, problem decomposition, or tasks with initially unclear scope where
thoughts may need revision or branching.

## When to Use

| How You're Stuck | Use This |
|------------------|----------|
| **Don't know which technique** | Use this table, then load the matching technique below |
| **Need breakthrough innovation** | collision-zone-thinking |
| **Forced by assumptions** | inversion-exercise |
| **Same issue in different places** | meta-pattern-recognition |
| **Unsure about production scale** | scale-game |
| **Complexity spiraling** | simplification-cascades |
| **Multi-step reasoning needing revision/branching** | references/sequential-thinking.md |
| **Still stuck after 2+ techniques** | escalate to the `advisor` agent |

## Quick Reference

```
Conventional solutions inadequate?  → collision-zone-thinking
"This must be done this way"?       → inversion-exercise
Same pattern 3+ places?             → meta-pattern-recognition
Will it work at scale?              → scale-game
Same thing implemented 5+ ways?     → simplification-cascades
Many interconnected steps, unclear scope, may revise? → references/sequential-thinking.md
2+ techniques tried, still no progress?  → escalate to `advisor` agent
```

## Escalation: Advisor

When two or more techniques have been applied with evidence and the problem is
still stuck, spawn the `advisor` agent (strongest model tier) instead of
cycling a third technique. Hand it a compact evidence bundle — the question,
each technique tried and why it failed, and the relevant file paths — and act
on its one-shot Advisor Report. An explicit `@advisor` mention from the user
skips this gate entirely.

## Core Philosophy

> "One powerful abstraction > ten clever hacks"

These techniques help you find the elegant solution that makes complexity unnecessary, rather than managing complexity through brute force.

## Source Notes

Provenance and adaptation details for these techniques are recorded in
`ABOUT.md` (derived from the Microsoft Amplifier project's agent patterns).

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [danielleit241](https://github.com/danielleit241)
- **Source:** [danielleit241/forge](https://github.com/danielleit241/forge)
- **License:** ISC

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-danielleit241-my-skills-problem-solving
- Seller: https://agentstack.voostack.com/s/danielleit241
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.