nav-triz

Generates three TRIZ-based solution candidates for declared technical contradictions.

232|12|Updated Oct 10, 2025
One-click install
npx skills add https://github.com/qf-studio/navigator --skill nav-triz-qf-studio
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nav-triz
Source: https://github.com/qf-studio/navigator/tree/main/skills/nav-triz
Command: npx skills add https://github.com/qf-studio/navigator --skill nav-triz-qf-studio

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? When improving one aspect of a system worsens another (e.g., faster startup vs. higher memory use), the first idea that fits is often a compromise. This Skill forces three genuinely different solution candidates onto the table before planning, so trade-offs are resolved deliberately instead of by accident. ## Core Features & Use Cases - Contradiction-Driven Divergence: States the contradiction in technical or physical form, checks the Ideal Final Result, and inventories reusable code before proposing anything new. - Deterministic Principle Suggestion: The triz_suggest.py script keyword-ranks ~20 software-mapped TRIZ principles, picks one per separation mode (time, space, condition, level), and falls back to a generic trio when nothing matches. - Knowledge Graph Integration: Surfaces prior decisions that resolved similar tensions and captures new resolutions tagged with contradiction, separation mode, and principle. - Use Case: A nav-brief flags "improving rollback safety vs worsening codebase cleanliness" on a substantial task; the Skill produces three candidates (temporary shims, sidecar module, opt-in flag), each with cost and downside, then recommends one. ## Quick Start Ask the assistant to find alternatives for a contradiction, for example: "triz this: improving test coverage vs worsening CI runtime".

Frequently Asked Questions about nav-triz

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I resolve a technical contradiction in software design?

State the contradiction as "improving A vs worsening B", then run triz_suggest.py with that string. It returns three candidate principles from different separation modes (time, space, condition, level); draft one concrete candidate per prompt, each naming what it worsens, then recommend one.

What is TRIZ and how does it apply to software engineering?

TRIZ is a methodology mined from patents for resolving contradictions without compromise. About 20 of its 40 inventive principles transfer to software, mapping to moves like caching (prior action), feature flags (dynamization), and adapters (intermediary), organized by four separation modes.

When should I not use TRIZ divergent solving?

Skip it for routine work, quick fixes, tasks where the user already named the approach, or briefs with no declared contradiction. The Skill explicitly treats ceremony as its failure mode and instructs skipping with a one-line note when in doubt.

Does triz_suggest.py require external Python packages?

No, the script uses only the Python standard library and always exits 0. It optionally imports graph_manager from the nav-graph skill for prior decision lookup, but degrades gracefully if that module is missing.

What happens when no TRIZ principle matches my contradiction?

The script falls back to a generic trio of principles (prior action, dynamization, segmentation) and labels the output as a generic fallback. This ensures the divergence step always produces three candidates rather than returning nothing.