Stats
Actions
Available In
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
By sharathsphd
TRIZ 40 Inventive Principles engine for systematic contradiction resolution, ARIZ-85C analysis, and benchmark arena
Identifies and classifies engineering contradictions from problem statements
Scores solution sketches on a strict 4x25-point TRIZ quality rubric
Generates principle-based solution sketches from a contradiction card
Admin access level
Server config contains admin-level keywords
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Systematic contradiction resolution using the 40 Inventive Principles — a Claude Code plugin
TRIZ (Theory of Inventive Problem Solving) is a structured innovation methodology developed by Genrich Altshuller from the study of hundreds of thousands of patents. Instead of brainstorming, TRIZ treats difficult design situations as contradictions and uses repeatable patterns of resolution.
The 40 Inventive Principles are abstract strategies (segmentation, dynamics, feedback, etc.) that recur across domains. The Contradiction Matrix (39x39 engineering parameters) suggests which principles historically resolved specific improving-vs-worsening trade-offs.
TRIZ Engine is a Claude Code plugin. Install it via the marketplace flow so all slash commands, agents, MCP tools, and hooks activate automatically in every Claude Code session.
git clone https://github.com/SharathSPhD/triz-engine.git
cd triz-engine # repo root with .claude-plugin/marketplace.json
claude plugin marketplace add ./ # register the local marketplace
claude plugin install triz-engine@triz-arena
claude plugin list # verify: triz-engine shown "enabled"
claude plugin marketplace add SharathSPhD/triz-engine
claude plugin install triz-engine@triz-arena
claude -p "/triz-engine:analyze How do we reduce weight without losing strength?" \
--model haiku --dangerously-skip-permissions --output-format json
You should see a structured TRIZ analysis with contradiction, principles, and a concrete solution. The run invokes the contradiction-agent → solution-agent → evaluator-agent pipeline and the triz-knowledge MCP server automatically.
See docs/QUICKSTART.md for the full getting-started guide, docs/USER_GUIDE.md for detailed usage, and the live dashboard at TRIZ Arena for benchmark results.
Once installed, the plugin exposes the following slash commands (all namespaced /triz-engine:...):
| Command | What it does |
|---|---|
/triz-engine:analyze | Full contradiction analysis: classify, map parameters, look up matrix, generate solutions, score against IFR |
/triz-engine:principles | Browse or search the 40 Inventive Principles with domain-specific examples |
/triz-engine:matrix | Navigate the Contradiction Matrix for an improving/worsening parameter pair |
/triz-engine:ifr | Formulate the Ideal Final Result — maximum benefit, zero cost/harm/complexity |
/triz-engine:ariz | Full ARIZ-85C step-by-step analysis for deeply intractable contradictions |
/triz-engine:benchmark | Run TRIZBENCH evaluation on the current session |
The triz-knowledge server exposes 8 tools:
| Tool | Description |
|---|---|
get_principle | Fetch one inventive principle by ID (1-40) |
search_principles | Keyword search over principles with optional domain filter |
lookup_matrix | Matrix lookup for an improving/worsening parameter pair (1-39) |
list_parameters | List all 39 engineering parameters |
get_separation_principles | Separation strategies (time, space, condition, system level) for physical contradictions |
suggest_parameters | Map a natural-language description to candidate TRIZ parameters |
score_solution | IFR-oriented score (0-4) for a proposed solution |
log_session_entry | Append a structured entry to the session innovation ledger |
contradiction-agent → solution-agent → evaluator-agent
npx claudepluginhub sharathsphd/triz-engine --plugin triz-engineMonitor and steer multi-agent Claude Code trajectories using dynamical systems theory. Computes finite-time Lyapunov exponents (FTLE) over semantic embedding sequences to classify regime (CONVERGING / CYCLING / EXPLORING / DIVERGING / STUCK / OSCILLATING / PLATEAU) and prescribe interventions before a task derails.
SharathSPhDLong-context discipline for Claude Code: Avacchedaka-typed retrieval, sublation, witness-consciousness invariants, event-boundary compaction, and Khyātivāda hallucination classification. 15 MCP tools, 3 skills, 3 agents, 4 commands, 3 hooks.
SharathSPhDPratyabhijna x Active Inference creative-cognition engine v0.4 (mechanism study). Builds on v0.3's clean Haiku CLI substrate (no API key) and event-gated, always-shadow-revision cascade. v0.4 makes cit_temperature causal via best-of-K candidate width, makes the free-energy budget a hard gate inside run_cascade (HaikuRateLimitError on 429), adds a pluggable commit-policy stack (always_draft / always_revise / event_gated / learned_gate / oracle) so Experiments A/B/C from the v0.3 adversarial review run on a single cascade pass, and re-enables a stratified Sonnet LLM-judge bridge for construct validity (32-item subset, $5 cap, frozen prompt sha). Ships 19 MCP tools (18 v0.3 + judge_pair), 5 skills, 5 agents, 5 slash commands, and 3 lifecycle hooks.
Closed-loop autonomous AEO/LLM-SEO citation engineering. Audits your site, drafts the fix as a PR, measures the lift after merge. Powered by the Claude Code subscription CLI — no API keys.
Structured thinking methods that counteract LLM reasoning biases during problem exploration — first principles, inversion, constraint manipulation, perspective forcing, analogy search, and more, with user-gated parallel subagent exploration for deep dives
oborchersStructured thinking methods as multi-agent sessions — Six Thinking Hats, Adversarial Debate, Disney Method, Pre-Mortem, Polarity Management, TRIZ, W³, Troika Consulting, Wise Crowds, First Principles Decomposition, Analogical Transfer, Morphological Box, Futures Cone — plus meta-cognitive modules (Bias Check, Frame Check, Method Check) that reflect on the thinking itself
worksystems-designClaude Code skills for systems thinking: stock-flow / causal-loop diagram critique with archetype identification (W2), stock-flow simulation commissioning (W3 — emit a brief that your AI agent uses to build an interactive HTML simulation app), Meadows leverage-point mapping for a stated goal (W4), and the W6 'redraw the box' pair — Goldratt Theory-of-Constraints constraint-finding and Altshuller TRIZ contradiction-dissolving. Plus why-tree: a heavyweight multi-agent Goldratt Current-Reality-Tree instrument that builds an evidence-graded causal tree and converges on the one binding constraint. From the AI + Systems Thinking course (Empatika).
BayramAnnakovInnovation & Intrapreneurship domain agent. 10 skills covering the full DLA Stack: Design Thinking (customer discovery, ideation), Lean Startup (hypothesis testing, MVP design, validated learning), Business Model Canvas, financial modelling, competitive intelligence, go-to-market strategy, investor pitch, and innovation sprints. 4 persistent agents for continuous innovation intelligence. Policy-configurable via innov.local.md.
panaversityUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
upstashComprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
anthropics