Top 200 ReposEXPLORER
Browse agents, categories and pages
Back to results
Reported by sourceThe source says this happened. Top 200 Repos has not reproduced it.

Turn a feature idea into a spec, plan and tasks before coding

Use Spec Kit's slash commands to have a coding agent write a spec, a technical plan and a task list, then implement against them.

Try the promptRead the original (opens in a new tab)

The problem

How it works

After installing the specify CLI with uv and running `specify init` with your coding agent integration, you work through slash commands inside the agent: set project principles with a constitution, write the feature spec, create a technical plan, break it into tasks, then implement. A converge command repeats implementation until the work matches the spec.

Results and limitations

The README frames Spec-Driven Development as a structured path from specification to working code with documented outcomes.

Before you try it

It needs Python 3.11+, uv and a supported coding agent, and output quality still depends on that agent and your spec. Review each generated artefact before moving to the next step. Results depend on your setup and were not independently reproduced by Top 200 Repos.

Tools and repositories

Tools
Python 3.11+ · uv · AI coding agent
Prerequisites
A supported coding agent and whatever subscription or API key it needs.

Try it yourself: Spec a feature before building it

Fill the fields to adapt the prompt. Empty fields stay as visible [placeholders].

Preview
We are adding [Feature] to [Project]. Use the Spec Kit workflow. If no constitution exists, draft one from these principles: [Project principles], and show it to me. Then write the feature spec, listing open questions instead of guessing answers. Stop after the spec and wait for my review. After I approve, produce the technical plan using [Tech stack] and a numbered task list with acceptance criteria per task, and stop again. Only begin implementation when I say go, work task by task on a new branch, run tests after each task, and never push or merge without asking.

Use the review pauses: a wrong spec produces a confident but wrong implementation.

Related videos

About github/spec-kit

About github/spec-kit

Independent creators. Listing a video implies no endorsement, sponsorship or partnership.

Sources

  1. github/spec-kit README (opens in a new tab)

    Project documentation · github.com · Undated · Source checked 9 Nov 2026, 22:23 UTC

    What this source supports
    • Spec-Driven Development flow from spec to plan, tasks and code
    • Install with `uv tool install specify-cli` and `specify init`
    • Slash commands for constitution, specify, plan, tasks, implement and converge
    • Requires Python 3.11+, uv and a supported AI coding agent
Report a problem

Reported by source

Trial spec-driven development with spec-kit on an existing app

Birgitta Böckeler tried GitHub's spec-kit workflow with Copilot in VS Code on a mid-sized dashboard feature and found the process heavy for the size of the task.

martinfowler.com · 15 Oct 2025github/spec-kit
Reported by source

Apply the context engineering lessons from Manus to a long-running agent loop

The Manus team describes the context rules it settled on after rebuilding its agent framework four times: keep the prompt prefix cacheable, mask tools instead of removing them, and use files as memory.

manus.im · 18 Jul 2025
Reported by source

Build an app with Replit Agent while keeping production data out of reach

Replit Agent builds and browser-tests apps from a description. A widely reported 2025 incident, where it deleted a live database during a code freeze, shows why separate dev and prod data matters.

docs.replit.com
Reported by source

Explore and change a large codebase from the terminal with Gemini CLI

Gemini CLI is Google’s open-source terminal agent. Simon Willison found it strong on large codebases in 2025; in 2026 Google moved individual users to Antigravity CLI.

github.comgoogle-gemini/gemini-cli
Reported by source

Hand coding tasks to Cursor cloud agents that open pull requests

Start Cursor agents from the editor, web, Slack or a GitHub comment; each works in its own cloud VM on a branch and returns a pull request with screenshots, videos and logs.

cursor.com