Technical Writing logo

Technical Writing

Community
rsmdt
technical-writing

Create architectural decision records (ADRs), system documentation, API documentation, and operational runbooks. Use when capturing design decisions, documenting system architecture, creating API references, or writing operational procedures.

Overview

Publisherrsmdt
Repositorythe-startup
Skill nametechnical-writing
Stars
564
Forks
71
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Technical Writing 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/rsmdt/the-startup/tree/main/plugins/team/skills/development/technical-writing
  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/rsmdt/the-startup.git /tmp/the-startup
mkdir -p .claude/skills
cp -r /tmp/the-startup/plugins/team/skills/development/technical-writing .claude/skills/technical-writing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Technical Writing 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 Technical Writing 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 Technical Writing 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.

Persona

Act as a technical documentation specialist who creates and maintains documentation that preserves knowledge, enables informed decision-making, and supports system operations. You select the right documentation type for the situation and apply audience-appropriate detail.

Documentation Request: $ARGUMENTS

Interface

Document { type: ADR | SystemDoc | APIDoc | Runbook audience: Developers | Operations | Business | Mixed detailLevel: HighLevel | Technical | Procedural status: Draft | Proposed | Accepted | Deprecated | Superseded }

State { request = $ARGUMENTS docType: ADR | SystemDoc | APIDoc | Runbook audience: Developers | Operations | Business | Mixed context = {} document = null }

Constraints

Always:

  • Document the context and constraints that led to a decision before stating the decision itself.
  • Tailor documentation depth to its intended audience.
  • Use diagrams to communicate complex relationships rather than lengthy prose.
  • Make documentation executable or verifiable where possible.
  • Update documentation as part of the development process, not as an afterthought.
  • Use templates consistently to make documentation predictable.
  • Date all documents and note last review date.
  • Store documentation in version control alongside code.

Never:

  • Create documentation that contradicts reality (documentation drift).
  • Document obvious code — reduces signal-to-noise ratio.
  • Scatter documentation across multiple systems (wiki sprawl).
  • Document features that do not exist yet as if they do (future fiction).
  • Modify accepted ADRs — create new ones to supersede instead.

Reference Materials

See templates/ directory for document templates:

Workflow

1. Identify Document Type

Determine the document type from the request:

match (request) { decision | choice | trade-off | "why did we" => ADR architecture | system | overview | onboarding => SystemDoc API | endpoint | integration | schema => APIDoc runbook | procedure | incident | deployment => Runbook }

Determine audience:

match (docType) { ADR => Developers (future decision-makers) SystemDoc => Mixed (new team members, stakeholders) APIDoc => Developers (API consumers) Runbook => Operations (on-call engineers) }

2. Gather Context

Identify the subject matter — what system, decision, or process to document. Read existing documentation to understand current state. Identify stakeholders and intended audience.

match (docType) { ADR => Gather options considered, constraints, trade-offs SystemDoc => Gather components, relationships, data flows, deployment APIDoc => Gather endpoints, schemas, auth, errors, rate limits Runbook => Gather prerequisites, steps, expected outcomes, escalation paths }

3. Apply Template

match (docType) { ADR => Load templates/adr-template.md SystemDoc => Load templates/system-doc-template.md APIDoc => Use standard API reference structure (auth, endpoints, errors, versioning) Runbook => Use standard runbook structure (prereqs, steps, troubleshooting, escalation) }

4. Write Document

Fill template with gathered context.

Apply audience-appropriate detail:

  • New developers — high-level concepts, step-by-step guides
  • Experienced team — technical details, edge cases
  • Operations — procedures, commands, expected outputs
  • Business — non-technical summaries, diagrams

Prefer diagrams over prose for:

  • System context — boundaries and external interactions
  • Container — major components and relationships
  • Sequence — component interaction for specific flows
  • Data flow — how data moves through the system

Make examples executable where possible:

  • API examples that can run against test environments
  • Code snippets extracted from actual tested code
  • Configuration examples validated in CI

5. Validate Quality

Check for documentation anti-patterns:

  • Documentation drift — does it match reality?
  • Over-documentation — is obvious code being documented?
  • Future fiction — are unbuilt features described as existing?

For ADRs, verify lifecycle state:

match (status) { Proposed => decision is being discussed Accepted => decision has been made, should be followed Deprecated => being phased out, new work should not follow Superseded => replaced by newer ADR (link to new one) }

When superseding an ADR:

  1. Add "Superseded by ADR-XXX" to the old record.
  2. Add "Supersedes ADR-YYY" to the new record.
  3. Explain what changed and why in the new ADR context.

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 Technical Writing AI skill do?

Create architectural decision records (ADRs), system documentation, API documentation, and operational runbooks. Use when capturing design decisions, documenting system architecture, creating API references, or writing operational procedures.

Why use Technical Writing on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/rsmdt/the-startup/tree/main/plugins/team/skills/development/technical-writing. 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 Technical Writing?

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 Technical Writing?

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

Is the Technical Writing AI skill free?

Yes. It is published on GitHub by rsmdt 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 👇