Writing Specs logo

Writing Specs

Organization
JetBrains
writing-specs

Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.

Overview

PublisherJetBrains
Repositorythinkrail
Skill namewriting-specs
Stars
514
Forks
42
Bundled files
Instructions only
LicenseApache-2.0
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Writing Specs 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/JetBrains/thinkrail/tree/main/packages/pi-thinkrail-workflow/skills/writing-specs
  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.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/JetBrains/thinkrail.git /tmp/thinkrail
mkdir -p .claude/skills
cp -r /tmp/thinkrail/packages/pi-thinkrail-workflow/skills/writing-specs .claude/skills/writing-specs
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Writing Specs 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 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 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

The workflow family's shared bar for every spec a workflow produces: short, honest, on-rails. Process skills name this concept at the steps that draft or revise specs; what to draft and when stays with the referencing skill. Graph mechanics — frontmatter, link kinds, the spec_* tools — are the spec-graph skill's ground; this concept carries the quality bar the family holds on top of them, and is where the family's rules for specs and the spec graph accrue.

Short

  • Small enough to read in one sitting. Target signal, not completeness.
  • Explain intent, not inventory: what the thing is for, what it owns, where its boundary runs — never a file listing or a restatement of the code.

Honest

  • Only settled content appears. Never pad with [TBD] or placeholder sections — a section that hasn't been settled simply doesn't exist yet.
  • Anything inferred rather than confirmed is marked unconfirmed, inline, where it stands.
  • New and inferred specs are status: draft until the user has reviewed them — the flip out of draft follows the user's review, never the drafting agent's own judgment. A reviewed durable spec goes active, never done: it stays in force and evolves with the project.

On-rails

  • High-signal enough that a future agent (or human) lands on the decisions without re-deriving them.
  • The spec is the only home for rationale: decisions, invariants, trade-offs, and bug post-mortems are recorded here, never as code comments — a rationale paragraph found in code is content to promote into the owning spec, leaving at most a one-line pointer where misediting would silently break something.
  • Say each thing once: link by id instead of restating; the dependency edges between sibling modules live in the parent's spec, not in each leaf.
  • One spec per genuine boundary — not per directory, not per file.

The goal doc describes the product, not a plan

goal-and-requirements is the living record of what the product is and why: its goal, problem, audience, capabilities, and non-goals, plus any durable principles.

  • No versions, releases, phases, MVP/v1/v2 splits, or "later" lists. Sequencing is not a spec's job: an idea cut from scope goes back to the user to track wherever they plan work, and never into the doc.
  • Capabilities state what the product does, or for a new project what its smallest useful first build will do.
  • Non-goals hold only what is excluded by decision. Something neither listed nor excluded is open, not forbidden.
  • It evolves with the product: a change that adds a capability or overturns a principle updates the goal doc in the same change.

Frequently asked questions

What does the Writing Specs AI skill do?

Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.

Why use Writing Specs on TypingMind?

Because you install it once and use it with any model. Writing Specs 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 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/JetBrains/thinkrail/tree/main/packages/pi-thinkrail-workflow/skills/writing-specs. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Writing Specs?

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?

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

Is the Writing Specs AI skill free?

Yes. It is published on GitHub by JetBrains under the Apache-2.0 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 👇