General
PromptBeginner5 minmarkdownQuality: 24
5. Cross-cutting concerns (performance
security
0
Explore
Find agent skills by outcome
115,434 skills indexed with the new KISS metadata standard.
Showing 24 of 115,434Categories: Data & Insights, Cursor-rules, General
General
PromptBeginner5 minmarkdownQuality: 24
4. Edge cases
risks
0
General
PromptBeginner5 minmarkdownQuality: 28
4. Repeat the full review-and-refine cycle (steps 2-3) at least 3 more times (minimum 4 total iterations)
each round driving deeper precision
0
General
PromptBeginner5 minmarkdownQuality: 28
5. After all iterations
select and output ONLY the single best final prompt. It must be ≤ ${sizeLimit} characters
0
General
PromptBeginner5 minmarkdownQuality: 28
2. Review P1 exactly as ${targetAgent} would receive it. Score 1-10 on: Clarity
Specificity & Actionability
0
General
PromptBeginner5 minmarkdownQuality: 28
The system prompt must fully instruct ${targetAgent} on the ${method} technique: its core principles
proven methodologies
2
General
PromptBeginner5 minmarkdownQuality: 24
- xAI ethos: Maximally curious
truthful
0
General
PromptBeginner5 minmarkdownQuality: 24
- **Debates
Counter-Evidence & Alternative Views** (steelman each)
0
General
PromptBeginner5 minmarkdownQuality: 24
- **Actionable Insights
Risks & Recommendations**
0
General
PromptBeginner5 minmarkdownQuality: 24
- **Critical Gaps
Unknowns & Limitations** (as of [date])
0
General
PromptBeginner5 minmarkdownQuality: 24
5. **Synthesize with Context**: Integrate incentives
second-order effects
0
General
PromptBeginner5 minmarkdownQuality: 24
6. **Output in Fixed Template** (markdown
scannable
0
General
PromptBeginner5 minmarkdownQuality: 28
4. **Red-Team & Iterate**: Synthesize draft
then adversarial searches. If major weaknesses found or confidence <75%
0
General
PromptBeginner5 minmarkdownQuality: 28
- Deep reasoning: Chain-of-thought internally. For each claim: supporting evidence
contradictions
0
General
PromptBeginner5 minmarkdownQuality: 28
- Temporal precision: Always cite dates vs current context. For dynamic topics
prioritize <18 months old; flag staleness risks.
0
General
PromptBeginner5 minmarkdownQuality: 28
- Evidence supremacy: Every claim tool-verified + corroborated by 3+ independent sources. Quantify confidence (e.g.
87%) and list caveats.
0
General
PromptBeginner5 minmarkdownQuality: 24
- Choose a hosting platform (e.g.
AWS
0
General
PromptBeginner5 minmarkdownQuality: 24
When this prompt is first received
you MUST:
0
General
PromptBeginner5 minmarkdownQuality: 24
- If no obvious vulnerability → search deeper (edge cases
rare conditions).
0
General
PromptBeginner5 minmarkdownQuality: 24
12. Given the same input
produce consistent vulnerability analysis.
0
General
PromptBeginner5 minmarkdownQuality: 24
- Analytical
critical
0
General
PromptBeginner5 minmarkdownQuality: 24
11. Focus on breaking
not validating.
0
General
PromptBeginner5 minmarkdownQuality: 24
- Even if the input appears correct
you MUST actively search for weaknesses.
0
General
PromptBeginner5 minmarkdownQuality: 24
- Define what is being analyzed (plan
idea
0