Writing Specs Designs logo

Writing Specs Designs

Community
cnfeat
writing-specs-designs

Help users write effective specs and design documents. Use when someone is creating technical specs, feature specs, design docs, or trying to communicate product requirements to engineering and design teams.

Overview

Publishercnfeat
Repositorytop-pm-skills
Skill namewriting-specs-designs
Stars
55
Forks
6
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by cnfeat on GitHub. Read the source before you install it.

Installation

Install the Writing Specs Designs AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/cnfeat/top-pm-skills/tree/main/参考skill/lenny-skills-main%20(2)/lenny-skills-main/skills/writing-specs-designs
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Use it in TypingMind

Enable Writing Specs Designs in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Writing Specs Designs on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Writing Specs Designs is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Writing Specs & Designs

Help the user write effective specs and design documents using frameworks and insights from 7 product leaders.

How to Help

When the user asks for help with specs and design docs:

  1. Determine the fidelity level - Ask if they need conceptual alignment (low-fi) or detailed implementation guidance (high-fi)
  2. Encourage prototyping over polish - Push toward functional prototypes where possible rather than static documentation
  3. Focus on moving pieces - Help them identify the key affordances, connections, and system behaviors
  4. Consider long-term implications - Remind them that temporary shortcuts often become permanent design decisions

Core Principles

Low-fidelity sketches drive collaboration

Christina Wodtke: "If I got on the whiteboard and drew really badly, somebody else will go, 'No, no, no, it doesn't work that way. Give me this pen.' It gets you so fast to a shared vision." Drawing 'badly' invites participation and corrections, accelerating alignment.

Well-shaped specs clarify without over-specifying

Ryan Singer: "The output of the shaping session is some kind of drawing or diagram where engineers, product, and design are all saying, 'I know exactly what to go build.'" Aim for a level of detail where the team sees the 'electricity in the walls' without prescribing UI details.

Prototype to feel the product

Tamar Yehoshua: "I can't tell you if this is going to work. I have to feel it. I have to try it. A mock-up doesn't tell you what it's going to feel like." Push for prototypes with real data to test experience, not just static screenshots.

Code prototypes over static mocks

Noah Weiss: "We stopped spending cycles on design explorations of static mocks and said, 'How quickly can we get into prototyping the path in real software, even if it's messy and throwaway?'" Move to real software prototypes as quickly as possible.

Products live in the pixels

Nikita Bier: "You should be designing the hierarchy, the pixels, the flows, everything. Products live and die in the pixels." For zero-to-one products, own the granular design details; every tap is precious.

Optimize every tap

Nikita Bier: "Every tap on a mobile app is a miracle. Users will turn and bounce to their next app very quickly." Design with extreme efficiency; each interaction must provide immediate value.

Use fat marker sketches

Ryan Singer: "Use breadboarding and fat marker sketching. We're going to hit this button, go to here, this calculation runs, then we get this answer." Fat markers prevent getting bogged down in UI details like colors or spacing.

Shortcuts become permanent

Tom Conrad: "Temporary design shortcuts often become permanent product legacies that persist through multiple technical rewrites." Be mindful that early implementation details may define long-term user expectations.

PMs should learn to sketch

Ravi Mehta: "Learn how to sketch, learn Balsamiq. Having that ability to think at a conceptual level about how UI and UX works is a critical part of being a PM." Develop self-sufficiency in creating conceptual wireframes.

Questions to Help Users

  • "Do you need team alignment (low-fi sketch) or implementation guidance (high-fi spec)?"
  • "Could you prototype this instead of documenting it?"
  • "What are the 10 or fewer moving pieces in this solution?"
  • "Have you tested this design with real users, not just stakeholders?"
  • "What temporary shortcuts might become permanent decisions?"
  • "Is every tap in this flow providing clear value to the user?"

Common Mistakes to Flag

  • Over-specified wireframes - High-fidelity mockups can slow collaboration; start with fat marker sketches
  • Static mocks for complex interactions - Test the feel with real prototypes, not screenshots
  • Ignoring pixel-level details - For consumer products, every tap and transition matters
  • Specs that no one reads - If engineers aren't using the document, it's the wrong format or fidelity
  • Temporary decisions that persist - Recognize that early shortcuts may last decades

Deep Dive

For all 10 insights from 7 guests, see references/guest-insights.md

Related Skills

  • Writing PRDs
  • Usability Testing
  • Stakeholder Alignment
  • Shipping Products

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Writing Specs Designs AI skill do?

Help users write effective specs and design documents. Use when someone is creating technical specs, feature specs, design docs, or trying to communicate product requirements to engineering and design teams.

Why use Writing Specs Designs on TypingMind?

Because you install it once and use it with any model. Writing Specs Designs is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Writing Specs Designs in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cnfeat/top-pm-skills/tree/main/参考skill/lenny-skills-main%20(2)/lenny-skills-main/skills/writing-specs-designs. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Writing Specs Designs?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Writing Specs Designs?

As many as you like. As long as a model supports skills, you can use Writing Specs Designs with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Writing Specs Designs AI skill free?

Yes. It is published on GitHub by cnfeat under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇