The Scarlet Pimp
Supreme Member
- Apr 2, 2008
- 1,416
- 4,457
Here's a complete list of ChatGPT operators:
/ACT AS makes ChatGPT speak in a specific role.
/AUDIENCE adapts the response to a chosen audience.
/BEGIN WITH / END WITH forces starting or ending with something.
/BRIEFLY forces a very short answer.
/CHAIN OF THOUGHT shows intermediate reasoning.
/CHECKLIST turns a response into a checklist.
/COMPARE puts two or more things side by side.
/CONTEXT STACK keeps multiple layers of context in memory.
/DELIBERATE THINKING forces slower, more thoughtful reasoning.
/DEV MODE simulates a raw, technical developer style.
/ELI5 is used to explain as if to a 5-year-old.
/EVAL-SELF asks for a critical self-evaluation of the response.
/EXEC SUMMARY gives a quick executive-style summary.
/FIRST PRINCIPLES rebuilds from fundamental basics.
/FORMAT AS enforces a specific format (table, JSON, etc.).
/GUARDRAIL sets strict boundaries not to cross.
/JARGON asks to use technical vocabulary.
/METRICS MODE expresses answers with measures and indicators.
/MULTI-PERSPECTIVE shows several points of view.
/NO AUTOPILOT forbids superficial, autopilot responses.
/PARALLEL LENSES examines from several angles in parallel.
/PITFALLS identifies possible traps and errors.
/PM MODE gives a project-management perspective.
/REFLECTIVE MODE prompts the AI to reflect on its own answer.
/REWRITE AS: rephrases in a requested style.
/ROLE: TASK: FORMAT: explicitly defines the role, the task, and the expected format.
/SCHEMA generates a structured outline or a data model.
/STEP-BY-STEP lays out reasoning step by step.
/SWOT produces a strengths/weaknesses/opportunities/threats analysis.
/SYSTEMATIC BIAS CHECK asks to identify biases.
/TLDL summarizes a very long text in a few lines.
/TONE changes the tone (formal, funny, dramatic, etc.).
/ACT AS makes ChatGPT speak in a specific role.
/AUDIENCE adapts the response to a chosen audience.
/BEGIN WITH / END WITH forces starting or ending with something.
/BRIEFLY forces a very short answer.
/CHAIN OF THOUGHT shows intermediate reasoning.
/CHECKLIST turns a response into a checklist.
/COMPARE puts two or more things side by side.
/CONTEXT STACK keeps multiple layers of context in memory.
/DELIBERATE THINKING forces slower, more thoughtful reasoning.
/DEV MODE simulates a raw, technical developer style.
/ELI5 is used to explain as if to a 5-year-old.
/EVAL-SELF asks for a critical self-evaluation of the response.
/EXEC SUMMARY gives a quick executive-style summary.
/FIRST PRINCIPLES rebuilds from fundamental basics.
/FORMAT AS enforces a specific format (table, JSON, etc.).
/GUARDRAIL sets strict boundaries not to cross.
/JARGON asks to use technical vocabulary.
/METRICS MODE expresses answers with measures and indicators.
/MULTI-PERSPECTIVE shows several points of view.
/NO AUTOPILOT forbids superficial, autopilot responses.
/PARALLEL LENSES examines from several angles in parallel.
/PITFALLS identifies possible traps and errors.
/PM MODE gives a project-management perspective.
/REFLECTIVE MODE prompts the AI to reflect on its own answer.
/REWRITE AS: rephrases in a requested style.
/ROLE: TASK: FORMAT: explicitly defines the role, the task, and the expected format.
/SCHEMA generates a structured outline or a data model.
/STEP-BY-STEP lays out reasoning step by step.
/SWOT produces a strengths/weaknesses/opportunities/threats analysis.
/SYSTEMATIC BIAS CHECK asks to identify biases.
/TLDL summarizes a very long text in a few lines.
/TONE changes the tone (formal, funny, dramatic, etc.).
