english/.opencode/skills/problem-solving/references/attribution.md

Problem-Solving Skills - Attribution

These skills were derived from agent patterns in the Microsoft Amplifier project.

Source Repository

• Name: Amplifier
• URL: https://github.com/microsoft/amplifier
• Commit: 2adb63f858e7d760e188197c8e8d4c1ef721e2a6
• Date: 2025-10-10

Skills Derived from Amplifier Agents

From insight-synthesizer agent:

• simplification-cascades - Finding insights that eliminate multiple components
• collision-zone-thinking - Forcing unrelated concepts together for breakthroughs
• meta-pattern-recognition - Spotting patterns across 3+ domains
• inversion-exercise - Flipping assumptions to reveal alternatives
• scale-game - Testing at extremes to expose fundamental truths

From ambiguity-guardian agent:

• preserving-productive-tensions - Preserving multiple valid approaches (in architecture skill)

From knowledge-archaeologist agent:

• tracing-knowledge-lineages - Understanding how ideas evolved (in research skill)

Dispatch pattern:

• when-stuck - Maps stuck-symptoms to appropriate technique

What Was Adapted

The Amplifier agents are specialized long-lived agents with structured JSON output. These skills extract the core problem-solving techniques and adapt them as:

• Scannable quick-reference guides (~60-80 lines each)
• Symptom-based discovery via when_to_use descriptions
• Immediate application without special tooling
• Composable patterns through dispatch system
• Progressive disclosure via SKILL.md + references structure

Core Insight

Agent capabilities are domain-agnostic patterns. Whether packaged as "amplifier agent" or "problem-solving skill", the underlying technique is the same.

We extracted the techniques and made them:

• Portable across contexts
• Immediately applicable
• Token-efficient through progressive disclosure
• Discoverable through symptom-matching
• Combinable for complex problems

License

Original Amplifier project uses MIT License. These adapted skills maintain attribution and follow the same open spirit.

Adaptation Notes

Changes from original:

• Converted from long-lived agent to scannable reference
• Added symptom-based dispatch system
• Removed JSON output requirements
• Focused on immediate application
• Added concrete examples
• Structured for progressive disclosure

Preserved from original:

• Core problem-solving techniques
• Recognition patterns
• Application processes
• Fundamental insights