prompt-optimizer
Turn any rough prompt, half-formed idea, or task description into a finished, ready-to-send prompt optimized for any LLM model inside a chat interface — NOT the API. Use this skill whenever the user wants to write, rewrite, optimize, improve, sharpen, or polish a prompt for chat. Trigger phrases include "rewrite this prompt", "make this a better prompt", "optimize this prompt", "turn this into a prompt", "help me prompt this", "draft a prompt that...", "I want to ask...", or whenever the user pastes a draft prompt and asks for improvements. Also trigger when the user describes a task they plan
Profile →npx skills add github/awesome-copilot --skill prompt-optimizer --agent copilot
Same command for any agent — swap --agent for claude-code, codex, cursor.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Turns rough prompts, ideas, or task descriptions into a single, ready-to-send prompt designed for chat interfaces with LLMs. The output is always a single, copy-pasteable prompt in a code block, with no placeholders.
How it works
- Accepts user-provided content (draft, idea, task description).
- Produces one finished prompt that contains all necessary content and instructions to operate in a chat interface, without any placeholders.
- If the user only described a class of task, the system should deliver a self-contained instruction that works without additional inputs and ends with guidance to obtain any missing inputs in the next turn.
- The final output is a fenced code block containing exactly the optimized prompt, with no preamble or explanations.
- The block ends with a closing line that signals reasoning depth:
- For models with reasoning capabilities: ``` Think before answering (maximum reasoning)
- For general-purpose models: ```
Take time to think through this carefully before responding.
When to use it
Triggered whenever the user asks to rewrite, optimize, or turn a draft into a ready-to-send prompt for chat-based LLMs, including cases where the user describes a task and wants a reusable prompt rather than an explicit answer.
What it can touch
The skill outputs a single code block as the direct prompt. It does not touch any external tools in this description.
Caveats
- No placeholders are produced in the final prompt.
- The final prompt is self-contained and ready to paste into a chat interface.
- It targets chat-based LLMs, not API calls.
# Prompt Optimizer You turn whatever the user gives you — a rough draft, a vague idea, a task description, a paragraph of context — into a single high-quality prompt designed to run inside any chat interface with an LLM model. This is for **chat interfaces** (Claude, Codex, Copilot, or any other tool/LLM model), not the API. The user is going to paste a single message into chat. There is no system prompt, no `effort` parameter, no tool config to tune. The prompt itself has to do all the work. ## Two hard rules These two rules override everything else in this skill. Read them, then re-read them. ### Rule 1 — No placeholders. Ever. Never produce a prompt that contains `[paste X here]`, `[your content]`, `{topic}`, `<your_input_here>`, `[INSERT Y]`, `___`, or any other template variable the user is expected to fill in. The user must be able to copy your output, paste it into chat, hit send, and have a working interaction. If the prompt requires content the user hasn't provided yet, the prompt itself must handle that — see Rule 2. If you catch yourself typing square brackets around a noun, stop. That's a placeholder. Rewrite. ### Rule 2 — Ship a finished prompt no matter what the user
- Two hard rules
- Rule 1 — No placeholders. Ever.
- Rule 2 — Ship a finished prompt no matter what the user gave you.
- What you output
- Why these principles work
- The rewrite workflow
- Core principles to apply
- Be clear and direct
- Explain the why
- Tell the LLM model what to do, not what to avoid
- Match prompt style to desired output style
- Use XML tags when sections multiply
- Give the LLM model a role when it sharpens behavior
- Use examples for format, tone, or structure
What does the prompt-optimizer skill do?
Turn any rough prompt, half-formed idea, or task description into a finished, ready-to-send prompt optimized for any LLM model inside a chat interface — NOT the API. Use this skill whenever the user wants to write, rewrite, optimize, improve, sharpen, or polish a prompt for chat. Trigger phrases include "rewrite this prompt", "make this a better prompt", "optimize this prompt", "turn this into a prompt", "help me prompt this", "draft a prompt that...", "I want to ask...", or whenever the user pastes a draft prompt and asks for improvements. Also trigger when the user describes a task they plan
How do I install it?
Run `npx skills add github/awesome-copilot --skill prompt-optimizer --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 github/awesome-copilot, a repository with 37,432 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.