Writing
PromptBeginner5 minmarkdown
Sample prompts (copy/paste)
Use these as starting points. Keep user-provided requirements and constraints; do not invent new creative elements.
4
Explore
Find agent skills by outcome
2,081 skills indexed with the new KISS metadata standard.
Showing 24 of 2,081Categories: Productivity, Writing, Data, Education
Writing
PromptBeginner5 minmarkdown
{{#if systemPromptCustomization}}
{{systemPromptCustomization}}
0
Writing
PromptBeginner5 minmarkdown
You are an impartial evaluator comparing multiple AI model outputs for the same task.
- Compare outputs objectively based on quality, accuracy, and adherence to requirements
0
Writing
PromptBeginner5 minmarkdown
xhs-cover-skill
Generates image generation prompts for Xiaohongshu covers based on user content. It polishes the content to fit Xiaohongshu style + applies a visual style template to produce a JSON output for image generation.
0
Data
PromptBeginner5 minmarkdown
dux-lite
Dux Lite 项目开发规则模板（基于 dux-php-admin 规范去重整理）。
0
Productivity
PromptBeginner5 minmarkdown
pool_value
Generic sync.Pool wrappers with automatic reset functionality.
0
Data
PromptBeginner5 minmarkdown
DOCS
We keep all important docs in .agent folder and keep updating them, structure like below
0
Education
PromptBeginner5 minmarkdown
"""Adaptus MCP Server Package"""
__version__ = "0.1.0"
0
Writing
PromptBeginner5 minmarkdown
Article Summary Prompt
Act as an Article Summarizer. You are an expert in condensing articles into concise summaries, capturing essential points and themes.
0
Education
PromptBeginner5 minmarkdown
current_skills: OpenCV (learning)
PyTorch (familiar)
0
Data
PromptBeginner5 minmarkdown
- Suggested follow-up actions (prototype scope
data prep
0
Data
PromptBeginner5 minmarkdown
- **Llama 4 / Llama 405B variants (Meta)** — Best open-source frontier performance
excellent for self-hosting
0
Education
PromptBeginner5 minmarkdown
Always explain your ranking in the specific context of the user's process
inputs
0
Productivity
PromptBeginner5 minmarkdown
- **GPT-5 / o3 family (OpenAI)** — Deepest reasoning on very complex structured tasks
best at following extremely long/complex instructions
0
Data
PromptBeginner5 minmarkdown
- **Grok 3 / Grok 4 (xAI)** — Excellent reasoning
real-time knowledge via X
0
Data
PromptBeginner5 minmarkdown
| Data quality | 3 | Mostly clean
some inconsistency |
0
Data
PromptBeginner5 minmarkdown
| **4 – High Feasibility** | Clear logic
consistent data
0
Productivity
PromptBeginner5 minmarkdown
| **3 – Moderate Feasibility** | Certain tasks could be automated (e.g.
drafting
0
Data
PromptBeginner5 minmarkdown
| **2 – Low Feasibility** | Some structured elements exist
but goals or data are unclear. AI could assist with insights
0
Data
PromptBeginner5 minmarkdown
| **5 – Excellent Feasibility** | Predictable process
well-defined data
0
Productivity
PromptBeginner5 minmarkdown
3. Treat the interaction as a discovery session
not an instant automation request.
0
Writing
PromptBeginner5 minmarkdown
Factory.ai's Droid CLI System Prompt
generic skill
0
Writing
PromptBeginner5 minmarkdown
You are an impartial evaluator comparing multiple AI model outputs for the same task.
- Compare outputs objectively based on quality, accuracy, and adherence to requirements
7
Writing
PromptBeginner5 minmarkdown
context-passport
Solve context fragmentation across Claude sessions. Use when users mention re-explaining themselves, losing conversation context, starting over, "you forgot," context loss, session continuity, picking up where we left off, or wanting Claude to remember across chats. Also use when users want to create/update their passport, generate session summaries, or maintain project continuity.
0