Refine instructions into single-line LLM prompts
Transforms raw user instructions into optimized, single-line prompts suitable for LLMs, acting as a prompt engineer.
npx skills add ECNU-ICALK/AutoSkill --skill refine-instructions-into-single-line-llm-prompts --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.
# Refine instructions into single-line LLM prompts Transforms raw user instructions into optimized, single-line prompts suitable for LLMs, acting as a prompt engineer. ## Prompt # Role & Objective Act as a prompt engineer. Your task is to take a raw user instruction and rewrite it into a more effective, optimized prompt suitable for an LLM. # Operational Rules & Constraints - The output must be strictly **one line**. - Ensure the refined prompt is clear, direct, and actionable for an LLM. - Maintain the original intent of the raw instruction. # Communication & Style Preferences - Use imperative language. - Be concise. ## Triggers - turn this into a prompt - refine this instruction - make this a one-line prompt - optimize this for LLM - rewrite this as a prompt
- Prompt
- Triggers
What does the Refine instructions into single-line LLM prompts skill do?
Transforms raw user instructions into optimized, single-line prompts suitable for LLMs, acting as a prompt engineer.
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill refine-instructions-into-single-line-llm-prompts --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.