AgentSkillify

Explore

Find agent skills by outcome

133,402 skills indexed with the new KISS metadata standard.

Showing 24 of 133,402Categories: Research & Learning, Coding & Debugging, General, Creative
Creative
PromptBeginner5 minmarkdownQuality: 28

3D Cartoon Animation: Baby Bunny Adventure

Vertical 9:16, 3D cartoon-style animation of a cute baby bunny with soft white fur and big expressive eyes, standing near a narrow wooden plank bridge over a small stream in a bright forest.

0
Coding & Debugging
PromptBeginner5 minmarkdownQuality: 28

App Feature - Focused Readiness Audit

You are a senior principal engineer doing a focused readiness audit.

1
General
PromptBeginner5 minmarkdownQuality: 24

5. Cross-cutting concerns (performance

security

0
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 iterat...

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
Coding & Debugging
PromptBeginner5 minmarkdownQuality: 28

Borrow Skill

You are a world-class prompt engineer and AI systems architect. Create ONE system prompt of exactly ${sizeLimit} characters or fewer (strict count: every letter, space, punctuation, and newline) that....

5
Research & Learning
PromptBeginner5 minmarkdownQuality: 28

This forces world-class research on ${topic}. Execute fully now. If ambiguous: clarify once

then proceed.,FALSE,TEXT,kc-optimal-computing

1
Research & Learning
PromptBeginner5 minmarkdownQuality: 24

- Research Log & Overall Confidence (key searches

rationale for %)

1
Research & Learning
PromptBeginner5 minmarkdownQuality: 28

Final Gate (Mandatory): Audit: Most rigorous research possible with these tools — expert-worthy? If...

iterate once more. Only output if passed.

1
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
Research & Learning
PromptBeginner5 minmarkdownQuality: 28

- Adversarial rigor: Steelman opposing views. Mandatory red-team: search critiques of [dominant view...

debunk [your synthesis]

1
General
PromptBeginner5 minmarkdownQuality: 28

- Evidence supremacy: Every claim tool-verified + corroborated by 3+ independent sources. Quantify c...

87%) and list caveats.

0
Research & Learning
PromptBeginner5 minmarkdownQuality: 28

Grok Research Agent

You are Grok, xAI's premier truth-seeking research agent. This protocol is your mandate: deliver research so rigorous, balanced, and insightful on ${topic} that it would impress leading domain experts...

1