OpenSkillIndex← back to search
claude-code

AutoSkill Refine instructions into single-line LLM prompts

Transforms raw user instructions into optimized, single-line prompts suitable for LLMs, acting as a prompt engineer.

install
source · Clone the upstream repo
git clone https://github.com/ECNU-ICALK/AutoSkill
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/ECNU-ICALK/AutoSkill "$T" && mkdir -p ~/.claude/skills && cp -r "$T/SkillBank/ConvSkill/english_gpt4_8_GLM4.7/refine-instructions-into-single-line-llm-prompts" ~/.claude/skills/ecnu-icalk-autoskill-refine-instructions-into-single-line-llm-prompts && rm -rf "$T"
manifest: SkillBank/ConvSkill/english_gpt4_8_GLM4.7/refine-instructions-into-single-line-llm-prompts/SKILL.md
source content

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