triz
Applies TRIZ cross-domain analogical reasoning to find solutions from adjacent fields. Use when stuck on a problem and needing inventive perspectives.
How do I install this agent skill?
npx skills add https://github.com/athola/claude-night-market --skill trizIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill implements a TRIZ-based reasoning framework for inventive problem solving. It utilizes a local Python module to analyze problems and suggest analogies from adjacent fields. No security issues or malicious patterns were detected.
- Socketpass
No alerts
- Snykwarn
Risk: MEDIUM · 1 issue
What does this agent skill do?
TRIZ Cross-Domain Analysis
When To Use
- Stuck on a problem and need perspectives from other domains
- Exploring cross-domain analogies for inventive solutions
When NOT To Use
- Standard code search or literature review (use other tome channels)
- Problems with obvious, well-known solutions
Apply Altshuller's Theory of Inventive Problem Solving to find solutions from adjacent fields.
Depth Levels
| Depth | Fields | Analysis |
|---|---|---|
| light | 1 | Ideality and contradiction |
| medium | 2 | Ideality, contradiction, field mapping |
| deep | 3 | Adds principle suggestions and separation |
| maximum | 5 | Adds distant fields |
Workflow
Run the catalogue steps first. One command returns, per ranked candidate, the contradiction record, its ideal final result, the physical-contradiction check, the five reformulation probes, and the near resolutions or separation axes where they apply:
PYTHONPATH="${CLAUDE_PLUGIN_ROOT}/src" python3 -m tome.channels.triz analyze --topic "<topic>" --domain <domain>
- State the Ideal Final Result: the function delivered without the system existing. Ask what would make the system unnecessary while the function still happens.
- Formulate the technical contradiction: improving X
worsens Y. Every record carries
matched:keywordwhen a catalogue row named the topic,fallbackwhen none did. Treat a fallback as unformulated: itsnear_resolutionslist the rows within one or two edits of the topic's words. Restate the topic in a row's terms or keep the fallback with a reason. For a physical contradiction (one parameter pulled toward two opposite values,physical: true), apply separation in time, space, condition, or system/scale instead of compromise.separationlists the axis the system description points at first, with the words that put it there inwhy. - Probe the statement before searching:
probesholds five fixed probes, each with its principle and a dated source. Swap the sides (#13), relax the equality into a range (#16), name the parameter and direction that would surface a near-solution (#35), promote a constant to a variable (#15), and ask whether any value satisfies both demands. The swap probe carries both principle sets andprinciple_set_differs. Show the inverted form only when it is true. Answer each in a line or dismiss it with a reason. When nothing satisfies both, stop searching harder: separate the demands or state the ideal final result. - Map to adjacent fields using the field taxonomy.
- Search for solved analogues in those fields.
- Build bridge mappings with rationale and a confidence score.
Field Mapping Strategy
- Software architecture: civil engineering, biology
- Data structures: logistics, materials science
- Algorithms: operations research, genetics
- Security: military strategy, immunology
- Financial: game theory, ecology
Related
TRIZ is the analogical method in the broader ideation catalog.
For diverse, category-spanning ideation with rotation, see
Skill(tome:ideate).
Limitations
- The built-in contradiction catalog maps common software trade-offs to principles. It is a convenience mapping rather than part of the classical TRIZ Body of Knowledge, which is scoped to technological systems.
- The strongest, most portable parts of TRIZ are the 40 principles as a divergence checklist and Ideality as a framing question. ARIZ, Substance-Field analysis, the 76 standard solutions, the Laws of Technical Systems Evolution (S-curves), and Function-Oriented Search (FOS) are out of scope here.
Sources
- TRIZ Body of Knowledge (MATRIZ) and the classical contradiction matrix (matriz.org).
- AutoTRIZ (arXiv 2403.13002, 2024): LLM-driven TRIZ ideation.
- TRIZ Agents (arXiv 2506.18783, 2025): multi-agent LLM orchestration across TRIZ steps, a companion to AutoTRIZ.
- Madrigal, "The Shadows Lurking in the Equations" (gods.art, 2025) and the literature the reformulation probes cite: Chinneck, Feasibility and Infeasibility in Optimization (2008); Allgower and Georg, Numerical Continuation Methods (1990); Liberti, Reformulations in Mathematical Programming (2009); Duncker, On Problem-Solving (1945); Hipple, TRIZ Separation Principles (2012). ADR-0026.
Exit Criteria
- An Ideal Final Result statement is produced before the search begins.
- A technical contradiction is stated as "improving X worsens Y" (or a physical contradiction is named with a separation axis).
- A
fallbackrecord is either restated in a catalogue row's terms vianear_resolutionsor kept with a stated reason. It is never reported as a keyword match. - Each of the five reformulation probes is answered in a line or dismissed with a reason. An infeasible verdict routes to separation or the ideal final result and no analogy search follows it.
- At least one cross-domain bridge with a confidence score is returned per active adjacent field, or the field is explicitly reported as yielding nothing.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/athola/claude-night-market/triz">View triz on skillZs</a>