DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to plan a feature with an AI before any code is written with Open Spec

Explore, propose, apply, and archive one change so the agent builds only what you agreed to.

Who it is forA developer working in an existing project who wants an AI coding assistant to add a feature but has unclear requirements and wants to review the plan first.

The problemWhen requirements live only in chat history, AI coding output is vague and hard to predict.

The outcomeA change folder under openspec/changes/ with a proposal, specs, design, and tasks that you reviewed, plus code that matches those tasks and an archived record.

What you need first

  • Node.js 20.19.0 or higher, or Homebrew on macOS or Linux
  • A project directory you want to use OpenSpec in
  • An AI coding assistant that OpenSpec supports (30+ tools listed in the docs)

Steps

  1. Run npm install -g @fission-ai/openspec@latest
  2. Run cd your-project and then openspec init
  3. In your AI assistant, run /opsx:explore to shape the idea, then /opsx:propose add-dark-mode to create the change folder
  4. Review proposal.md, the specs folder, design.md, and tasks.md before any code is written
  5. Run /opsx:apply to implement the tasks, then /opsx:archive to move the change into the archive and update the specs

Prompt for your agent

Using the OpenSpec repo at Fission-AI/OpenSpec, set up OpenSpec in <project-path> by running the install and `openspec init` steps, then use /opsx:explore and /opsx:propose <change-name> to create a change folder. Expected output: openspec/changes/<change-name>/ containing proposal.md, specs/, design.md, and tasks.md. Verify that the tasks file exists and summarize it for human review before running /opsx:apply.

Caveat. The README says Open Spec works best with high-reasoning models and a clean context window, so results depend on the model and session you use.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page