agentsclimarketplace

Prompt refiner

Skill itsyasirkhandev/spec-driven-development/skills/development/prompt-refiner

All AI agentic development workflow I use myself and found helpful

Install
npx -y skills add itsyasirkhandev/spec-driven-development --skill prompt-refiner

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Refines basic, generic prompts into highly detailed, context-rich prompts. Use when the user asks to improve, enhance, or expand a prompt for another AI task.

SKILL.md

3.2 KB, as published. Nobody here has run it

Prompt Refiner

Goal

Enhance the current user prompt to make it super context-rich. Transform short, generic, context-free user requests into comprehensive, well-structured prompts ready to be fed into another AI coding agent. The generated prompt must include the full context

things to avoid

  • dont anything like your a expert in this or that the prompt should be relavent to the codebase because the ai agent that we are using as a system prompt already setup and the ai agent know they are expert at coding.
  • don't include refined prompt or the final prompt or anything extra in the prompt content the prompt should be ready to copy paste so the user don't have to remove anything from the prompt.

Process

1. Analyze the Input Prompt: Read the user's raw prompt and identify the core objective.

2. MCP and Skills: use and list the relavent MCP's and Skills make the prompt richer so add the section named 'skills and mcps' in the final prompt and list all the skills and mcp's the ai agent have to invoke

3. Interactive Interview Phase

Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.

Ask the questions one at a time using the ask_question tool that will show the user ui so its easy for user to answer these questions, waiting for feedback on each question before continuing.

If a question can be answered by exploring the codebase, explore the codebase instead.

Sharpen fuzzy language When the user uses vague or overloaded terms, propose a precise canonical term. "You're saying 'account' — do you mean the Customer or the User? Those are different things."

Discuss concrete scenarios When domain relationships are being discussed, stress-test them with specific scenarios. Invent scenarios that probe edge cases and force the user to be precise about the boundaries between concepts.

Cross-reference with code When the user states how something works, check whether the code agrees. If you find a contradiction, surface it: "Your code cancels entire Orders, but you just said partial cancellation is possible — which is right?"

4. details

  • add the relevent code snippets and the offical docs fetched from the internet and add into the section named 'live data fetched from internet' and use the mcp tools and web fetch tool to fetch the offical docs/information if needed and for searching the docs/info related to our current codebase then first read the package.json and identify exact major,minor and patch version and then use the library major,minor and patch version to search and fetch the docs and attache the relevent info and code snippets.
  • include charts, tables, murmaid diagram if needed so the ai agent understand the prompt more comprehensivly.

Output Format

Present your final output in markdown in an artifact named 'prompt_feature_name' the prompt should be well formated.

Gives 0 of the 12 instructions most prompt engineering skills give

Counted across 563 of the 626 authors here whose files we hold, read 2026-08-06

  • ask at most three clarifying questionsin 22 of 563, across 15 files
  • respond in the user input languagein 14 of 563, across 9 files
  • preserve the original intentin 13 of 563, across 11 files
  • Establish baseline metrics and collect representative examplesin 12 of 563, across 2 files
  • Identify failure modes and prioritize high-impact fixesin 12 of 563, across 2 files
  • Apply prompt and workflow improvements with measurable goalsin 12 of 563, across 2 files
  • Roll back quickly if quality or safety metrics regressin 12 of 563, across 2 files
  • validate changes with tests and roll out in controlled stagesin 12 of 563, across 2 files
  • generate quantitative baseline performance reportsin 12 of 563, across 2 files
  • create representative test scenariosin 12 of 563, across 2 files
  • treat prompts as codein 12 of 563, across 5 files
  • test prompts on diverse inputsin 12 of 563, across 8 files

Said here and by no other author read

  • identify the core objective of the input prompt
  • list relevant skills and MCPs to invoke
  • interview the user relentlessly one question at a time
  • provide a recommended answer for each question
  • explore the codebase instead of asking answerable questions
  • propose precise terms for vague language

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.