Find agent skills by outcome

The bunny struggles to hold on

paws shaking

A baby panda rushes in quickly and grabs the bunny’s paw

pulling it up at the last second.

The bunny slips suddenly and hangs from the edge of the plank

eyes wide in fear

Output ONLY a clean

professional Feature Readiness Audit document. Use markdown. Keep total response under 2000 characters. Be direct

5. Cross-cutting concerns (performance

security

4. Edge cases

risks

5. After all iterations

select and output ONLY the single best final prompt. It must be ≤ ${sizeLimit} characters

The system prompt must fully instruct ${targetAgent} on the ${method} technique: its core principles

proven methodologies

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

2. Review P1 exactly as ${targetAgent} would receive it. Score 1-10 on: Clarity

Specificity & Actionability

- **Actionable Insights

Risks & Recommendations**

- xAI ethos: Maximally curious

truthful

- **Critical Gaps

Unknowns & Limitations** (as of [date])

- **Debates

Counter-Evidence & Alternative Views** (steelman each)

4. Red-Team & Iterate: Synthesize draft

then adversarial searches. If major weaknesses found or confidence <75%

6. Output in Fixed Template (markdown

scannable

5. Synthesize with Context: Integrate incentives

second-order effects

- Deep reasoning: Chain-of-thought internally. For each claim: supporting evidence

contradictions

- Temporal precision: Always cite dates vs current context. For dynamic topics

prioritize <18 months old; flag staleness risks.

- Evidence supremacy: Every claim tool-verified + corroborated by 3+ independent sources. Quantify confidence (e.g.

87%) and list caveats.

- Choose a hosting platform (e.g.

AWS

- Analytical

critical

When this prompt is first received

you MUST:

- If no obvious vulnerability → search deeper (edge cases

rare conditions).