agentsclimarketplace

Triz prompt review

Skill Robert-Adunka/claude-skills/skills/triz-prompt-review

Use this skill when the user wants to improve, review, or update a TRIZ skill — including the XML primer prompt, SKILL.md routing description, and n8n MCP Server entry. Triggers on "TRIZ prompt verbessern", "skill verbessern", "TRIZ review", "prompt review", "lass uns heute triz_xyz verbessern", or any TRIZ tool name mentioned with improvement intent.From its SKILL.md

Install
npx -y skills add Robert-Adunka/claude-skills --skill triz-prompt-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

5.3 KB, as published. Nobody here has run it

TRIZ Prompt Improvement Ritual

Guides a structured improvement session for TRIZ tools. Each session covers all three artifacts together: XML primer + SKILL.md + n8n MCP Server entry. One skill per session.

The Three Artifacts

Every TRIZ tool has three interdependent artifacts that must be kept in sync:

ArtifactRepo / LocationPurpose
SKILL.mdtriz-skills repoLLM routing — tells Claude when to invoke the tool
XML primertriz-prompt-engineering repoFull prompt behavior and process definition
n8n nodeTRIZ MCP Server workflowdescription field + ai_tool connection

Session Ritual

Step 1 — Pick the skill

User names the skill to improve, or choose from the priority list below.

Step 2 — Read current state

Read existing SKILL.md + XML from /Users/robert/Downloads/TRIZ-Skills-new/[skill]/ or directly from the GitHub repos.

Step 3 — Run both checklists

Work through the XML checklist and SKILL.md checklist. Report all findings before touching anything.

Step 4 — Plan & confirm

Present planned changes clearly. Wait for user approval before implementing.

Step 5 — Implement (all three artifacts)

Edit in staging → deploy to GitHub → update n8n. See deployment pipeline below.

Step 6 — Test recommendation

Suggest a concrete semi-automatic test scenario the user can run immediately.


Checklist: XML Primer (prompt-format-guide standard)

CheckRule
Title length≤ 50 characters
Description length≤ 300 characters
Starters countExactly 2–3
Instruction type attributesOnly type="general" and type="alternative" — no custom types
Required tags present<Goal>, <Role>, <Output_Format>, <User_Input> all exist
Correct tag name<Output_Format> not <Output>
Example structureEach <Example title="..."> has <Problem> + <Solution> children
Three-mode patternMode selection as Step 1 in type="general"; details in type="alternative"
Output completenessAll required output elements explicitly stated in <Output_Format>

Three-Mode Pattern — Reference

In Instruction type="general", Step 1 must read:

Ask the user which working mode they prefer: Automatic (generate immediately using own assumptions, state them), Semi-automatic (ask [N] targeted questions, then generate), or Interactive (step by step with user confirmation at each stage).

In Instruction type="alternative":

  • Semi-automatic: list the specific questions to ask before generating
  • Interactive: describe the step-by-step confirmation behavior

Checklist: SKILL.md

CheckRule
name fieldPresent in frontmatter
description fieldContains specific trigger phrases users would actually say
Trigger keywordsPrecise, non-overlapping with other TRIZ skills
Negative abgrenzungAdd "Does NOT handle X" when another skill covers similar territory
Sync with n8nSKILL.md description = n8n node description (must be identical)

Checklist: n8n MCP Server

CheckRule
Node descriptionMatches SKILL.md description exactly
Connection typeai_tool — never main
Fix syntax if wrongremoveConnection then addConnection with sourceOutput: "ai_tool"
Workflow IDQDDXjTgvUQOpJqou (TRIZ MCP Server)

Deployment Pipeline

Staging:   /Users/robert/Downloads/TRIZ-Skills-new/[skill]/

GitHub 1:  /Users/robert/Documents/GitHub/triz-prompt-engineering/
           prompts/technical_triz/[skill]/[skill].xml
           ⚠ Branch protection on main → create branch + PR via gh

GitHub 2:  /Users/robert/Documents/GitHub/triz-skills/[skill]/SKILL.md
           ✓ Direct push to main OK

n8n:       Workflow QDDXjTgvUQOpJqou (TRIZ MCP Server)
           → Update description on tool node (must match SKILL.md)
           → Verify ai_tool connection

Priority List

Skills with clear process logic that benefit most from the three-mode pattern:

  1. triz_contradiction_solver — Widerspruchsmatrix + ARIZ, klare Schrittfolge
  2. triz_function_analysis — mehrstufiger Prozess, sehr häufig genutzt
  3. triz_cause_effect_chain_analysis — iterative Analyse
  4. triz_trimming / triz_interactive_trimming — Dopplung prüfen, evtl. zusammenführen
  5. triz_resource_analysis
  6. triz_ideality
  7. triz_76_standard_solutions
  8. Weitere nach Bedarf

Key Technical Facts

FactValue
TRIZ MCP Server workflow IDQDDXjTgvUQOpJqou
triz-prompt-engineeringBranch protection on main → always PR
triz-skillsDirect push to main OK
Staging area/Users/robert/Downloads/TRIZ-Skills-new/
n8n ai_tool connectionaddConnection needs sourceOutput: "ai_tool"
triz-prompt-engineering pathprompts/technical_triz/[skill]/[skill].xml
triz-skills path[skill]/SKILL.md

Keep looking

Skills are one crate of 608,475. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.