Skip to main content

creative-seeds

Inject creative absurdity to break AI pattern-thinking before creative tasks. Randomly samples surreal micro-stories to spark unconventional thinking. Use before brainstorming, naming, writing, or any task needing fresh perspective.

Aller à l'installation

Informations de source

Dépôt
aviz85/claude-skills-library
Dernière activité de la source
10 juin 2026 à 07:40
Langue détectée de SKILL.md
anglais
Étoiles
49
Forks
14

Options d'installation

Le prompt qui vérifie d'abord la source est sélectionné par défaut. Vous pouvez passer à une commande directe ou télécharger une copie locale.

Vérifiez les fichiers source

Lisez SKILL.md et les fichiers associés affichés par SkillsMP avant de décider de l'installer.

Explorateur de fichiers
2 fichiers

Affichage de SKILL.md

SKILL.md
Instructions source · Aperçu en lecture seule
name
creative-seeds
description
Inject creative absurdity to break AI pattern-thinking before creative tasks. Randomly samples surreal micro-stories to spark unconventional thinking. Use before brainstorming, naming, writing, or any task needing fresh perspective.
allowed-tools
Bash
# Creative Seeds Before any creative task, run the script below — it selects 3 random seeds and returns them directly. ## How to Use Run this to pull 3 random seeds: ```bash python3 -c " import random, re, os with open(os.path.expanduser('~/.claude/skills/creative-seeds/seeds.md')) as f: content = f.read() seeds = [s.strip() for s in re.split(r'\n---\n', content) if re.search(r'##\s*\d+\.', s)] random.shuffle(seeds) print('\n\n---\n\n'.join(seeds[:3])) " ``` ## Instructions 1. Run the bash command above — it returns 3 randomly selected seed paragraphs 2. Read the output — let the absurdist logic seep in 3. Then proceed with the actual creative task with that mental residue active 4. Do NOT explain the seeds to the user unless asked — just use them internally to shift your thinking frame The seeds are not prompts. They are cognitive disruptors. They work by contaminating your pattern-matching with nonsense, forcing novel connections.
Voir sur GitHub