prompt-builder
Skill0 starsChanged 37 days agoNo licenceView on GitHub
Baut im Dialog einen einzelnen, fokussierten Prompt nach dem schlanken 5-Pillar-Raster (Kontext & Zweck, Auftrag, Constraints mit Begründung, Format, Rolle optional) für Claude, Gemini oder andere Modelle. Standard-Skill, wenn jemand einen Prompt erstellen, verbessern oder strukturieren will. Auslöser: 'Bau mir einen Prompt', 'erstell mir einen Prompt', 'Prompt Builder', 'ich brauche einen guten Prompt', 'strukturierter Prompt', 'mein Prompt ist nicht gut genug', 'Prompt für Claude erstellen', 'Prompt für Gemini bauen', 'build me a prompt', 'help me write a prompt'. Abgrenzung: Soll ein Thema stufenweise aus mehreren Perspektiven mit Gegenprüfung und Synthese durchgearbeitet werden (Entscheidung, Strategie) → advanced-prompt-builder. Soll ein Agent eine mehrstufige Aufgabe autonom ausführen (Claude Code /goal, Workflows, Codex) → agentic-prompt-architect. Führt die beschriebene Aufgabe nicht selbst aus, sondern liefert den Prompt dafür.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- syncwin/ai-extendertheir own version, first seen Nov 8, 2026
- jboczek/skillstheir own version, first seen Nov 1, 2026
- MarieLynneBlock/arcanum-artifextheir own version, first seen Nov 1, 2026
- Murphiyii/murphiyii-skillstheir own version, first seen Oct 20, 2026
- timwright12/claude-skillstheir own version, first seen Oct 17, 2026
- Nankov-ai/anthropics-skillstheir own version, first seen Sep 11, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- MarieLynneBlock/arcanum-artifex★ 4same name
- fabioc-aloha/alex-cognitive-architecture★ 0same name
- jboczek/skills★ 0same name
- Murphiyii/murphiyii-skills★ 0same name
- Nankov-ai/anthropics-skills★ 0same name
- ReaperOAK/ForgeOS★ 0same name
- syncwin/ai-extender★ 0same name
- timwright12/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- advanced-prompt-builderSkill
- mittelstands-usecase-analyserSkill
- scroll-deckSkill
- spec2opsxSkill
- spec-creatorSkill
- telepro-scriptSkill
- topic-explainerSkill
- youtube-strategySkill
- youtube-thumbnailSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.