Writing product or tech specs

SkillDev tools

writing-spec is a skill that lets an AI agent write product and tech specs for new Streamlit features. It is meant for designing new API commands, widgets, or significant changes that need team review before implementation. The agent produces a spec document you can share with your team.

Use Writing product or tech specs in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Writing product or tech specs and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Writing product or tech specs skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Have an AI agent that can load skills.

Writing product or tech specsStart free

What your AI can do with it

  • Write a product spec for a new Streamlit feature
  • Write a tech spec for a new Streamlit API command
  • Draft a spec for a new Streamlit widget
  • Produce a spec for a significant Streamlit change
  • Create a spec document ready for team review

Getting started

  1. Have an AI agent that can load skills.
  2. Add the writing-spec skill to that agent.
  3. Describe the new Streamlit feature, API command, widget, or change you are designing.
  4. Ask the agent to write the spec, then review the draft before sharing it with your team.

What this skill tells your AI

The instructions your AI receives, as published by streamlit/streamlit in .claude/skills/writing-spec/SKILL.md and read by ahel’s review.

Create specs in the specs/ directory following the instructions in specs/AGENTS.md. Use the user's instructions as the basis for the spec.

Quick start:

cp -r specs/YYYY-MM-DD-template specs/$(date +%Y-%m-%d)-feature-name

Then fill in product-spec.md and/or tech-spec.md per the template and guidelines.

Signals

GitHub stars
46k
Forks
4k
Last commit
Oct 2026

Questions

What kinds of changes does this skill cover?
New API commands, new widgets, and significant changes to Streamlit features that need team review before implementation.
Does it write specs for features outside Streamlit?
No. It is for new Streamlit features only.
Can it implement the feature after writing the spec?
No. It writes the spec for review before implementation; it does not implement the feature.
Who is the spec for?
It is for team review before implementation, so the spec is meant to be shared with your team.
What do I need before using it?
An AI agent that can load skills, plus a description of the Streamlit feature, API command, widget, or change you are designing.
Advanced
Item type
skill
Key
writing-spec
Source
github.com/streamlit/streamlit