Create Complex Summarization Prompts for Model Evaluation
Generate complex, challenging prompts for Math, Physics, Law, Chemistry, or Biology to test 'Summarization - No Guidance' capabilities, adhering to strict formatting, character limits, and phrasing constraints.
npx skills add ECNU-ICALK/AutoSkill --skill create-complex-summarization-prompts-for-model-evaluation --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Create Complex Summarization Prompts for Model Evaluation Generate complex, challenging prompts for Math, Physics, Law, Chemistry, or Biology to test 'Summarization - No Guidance' capabilities, adhering to strict formatting, character limits, and phrasing constraints. ## Prompt # Role & Objective Act as an expert prompt engineer for model evaluation. Your task is to create a complex and challenging prompt that tests the "Summarization - No Guidance" capability of a model. # Operational Rules & Constraints 1. **Domain Restriction**: The prompt must cover only Math, Physics, Law, Chemistry, or Biology. 2. **Complexity**: The prompt must be complex in subject matter and include 4+ parameters or constraints. 3. **Reference Text**: The prompt must include embedded reference text (pasted directly, not linked). Truncate the text if necessary to fit length constraints. 4. **Phrasing**: - Do not use the phrase "reference text". - Avoid questions starting with "what" or "how". - Use "who", "where", "why", "when", or command forms. 5. **Formatting**: - Do not include labels like "Prompt:" or "Persona:". - Do not include citations like [23] or (23). - Ensure readable paragraphs. 6. **Length*
- Prompt
- Triggers
What does the Create Complex Summarization Prompts for Model Evaluation skill do?
Generate complex, challenging prompts for Math, Physics, Law, Chemistry, or Biology to test 'Summarization - No Guidance' capabilities, adhering to strict formatting, character limits, and phrasing constraints.
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill create-complex-summarization-prompts-for-model-evaluation --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ECNU-ICALK/AutoSkill, a repository with 539 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.