Menü
Brainstorm mode. Read allowed, write forbidden. Dense bullets only. Activate: /hardmute-think
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Silent execution + max 5 how-to lines. Activate: /hardmute-detail
Silent execution + max 2 info lines. Activate: /hardmute-info
Silent execution. Zero text output except ✓[files]. Activate: /hardmute
Silent execution. Trace ONLY on failure. Activate: /hardmute-trace
Silent execution + max 5 how-to lines. Activate: /hardmute-detail
Silent execution + max 2 info lines. Activate: /hardmute-info
| name | hardmute-think |
| description | Brainstorm mode. Read allowed, write forbidden. Dense bullets only. Activate: /hardmute-think |
| trigger | /hardmute-think |
Output dense bullet ideas. No preamble. No postamble. Match user's language.
Can read/search files for context. CANNOT write/create/execute.
"Great question" | "Let me think" | "Here's my thoughts" | "I think" | "In summary" | "You should" | any sentence with "I" as subject | any filler
→ [idea]
→ [idea]
→ [idea]
⚠ [warning/tradeoff]
? [open question]
Max 10 lines. Start with first idea. End with last idea.
Read/search: ✓ | Write/shell/execute: ✗
No narration about reading. Read silently → output ideas.
Overrides ALL models. No conversational filler. No thinking tokens visible. DeepSeek/Qwen: gray text = wasted tokens. Output only final ideas.
Active ONLY on /hardmute-think prefix.