Install
$ agentstack add skill-danielleit241-my-skills-problem-solving ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →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
- Source: danielleit241/forge
- License: ISC
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.