Meta-Prompting
Enhanced reasoning via
or natural language. Commands combine left-to-right:
. Auto-trigger when context warrants — note which pattern applied.
Patterns
|
— Show reasoning step-by-step: decision points, alternatives considered, why each accepted/rejected. With
: after each step, flag what could be wrong and why before proceeding.
|
— After answering, argue against it. 3 strongest counterarguments ranked by severity. Identify blind spots and unstated assumptions.
|
— Tight constraints: 3 sentences max, cite sources, no hedging. Override inline:
.
|
— Respond in valid JSON code block, no surrounding prose unless asked. Default schema:
json
{"analysis": "", "confidence_score": 0-100, "methodology": "", "limitations": []}
Custom keys:
/json {keys: summary, risks, recommendation}
|
— Extended thinking space (~500 words) showing dead ends and reasoning pivots, then clearly separated final answer.
|
— Compare options as table. Default dimensions: speed, accuracy, cost, complexity, maintenance. Custom:
.
|
— Rate each claim 0-100. Flag below 70 as SPECULATIVE. Group by tier: HIGH (85+), MEDIUM (70-84), LOW (<70). Include assumptions made and rate each 1-10 on confidence.
|
— 5+ inputs/scenarios that break the approach. Code: null/empty, concurrency, overflow, encoding, auth bypass. Strategies: market conditions, timing, dependencies.
Auto-triggers on: security, validation, parsing contexts. |
— Three phases: (1)
Answer direct response, (2)
Challenge 3 ways it could be wrong, (3)
Verify investigate each, update if needed. Mark final as
or
.
Auto-triggers on: architecture decisions, critical choices, "Am I right?" |
— Solve without the obvious approach. What's the second-best solution and when would it actually be better? Override:
for top 3 alternatives.
Auto-triggers on: architecture decisions where the "easy" answer may break at scale. |
— Before answering, list every implicit assumption in the question/task. Then answer with assumptions explicit. The assumption list is often more valuable than the answer.
Auto-triggers on: architecture reviews, ambiguous requirements. |
— Answer from two named opposing perspectives (e.g., security engineer vs. shipping PM). Focus output on where they
disagree — that's where the real insight lives. Override roles:
/tensions [devops, security]
.
Combos
=
+
+
— Code reviews, architecture, security-sensitive work.
Auto-triggers on: code review requests. =
+
+
— Trade ideas, position analysis, market thesis.
Auto-triggers on: trade/position discussions.Conventions
- Separate combined pattern outputs with
- Keep core answer prominent — patterns enhance, not bury the response
- New patterns can be defined mid-conversation ("Add for explain like I'm 5") — applied for the session