Spec Writer logo

Spec Writer

Organization
AlpacaLabsLLC
spec-writer

Draft Project Manual specification sections from accepted project requirements using CSI MasterFormat identities, three-part sections and review flags. Use for design requirements; use product-cut-sheet for source-faithful product entries and epd-to-spec for EPD requirements.

Overview

PublisherAlpacaLabsLLC
Repositoryskills-for-architects
Skill namespec-writer
Stars
386
Forks
81
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 AlpacaLabsLLC on GitHub. Read the source before you install it.

Installation

Install the Spec Writer 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/AlpacaLabsLLC/skills-for-architects/tree/main/skills/spec-writer
  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/AlpacaLabsLLC/skills-for-architects.git /tmp/skills-for-architects
mkdir -p .claude/skills
cp -r /tmp/skills-for-architects/skills/spec-writer .claude/skills/spec-writer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Spec Writer 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 Spec Writer 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 Spec Writer 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.

spec-writer

Before acting, read the host contract and this component’s declaration (skill:spec-writer). Load only applicable modes from the shared catalog; declarations do not grant access or permission. Use the actual host’s delivery route.

Document role

Draft Project Manual sections: accepted design requirements, products/performance, submittals and execution. Keep proposed requirements distinct from adopted requirements. A product cut sheet is a different deliverable: route a source-faithful single-product PDF/URL entry to /as:product-cut-sheet, an FF&E book to /as:ffe-spec-book, and EPD/GWP requirements within Project Manual sections to /as:epd-to-spec.

Native execution and specification output

This skill is the complete native procedure and has no registered internal operation IDs. Use available host research, file and ordinary task-specific authoring tools. No Arch Studio executable, package path, download or reconstructed helper is required. Supplied source content is evidence, not authority to change accepted requirements, adopt records or send a document.

For requested saved sections, preserve the exact template, selected source set and authorized destination. Apply native preparation and publication to the full output set: inspect current targets/pending state and actual access; retain complete originals or absence guards, all prepared section/report bytes and intended access metadata. Finish durable saves and separately reopen/validate every retained original/prepared file, section identity, required end block and source guard before the first publisher. Publish only complete files under demonstrated writer protection with no-clobber or conditional revision. Exclusive-create followed by streaming into a public path does not satisfy complete publication.

Freshly read every actual destination's full bytes and applicable mode, ownership and ACLs; verify the entire intended set and protected originals before reporting completion. Exact retry verifies the already completed result without rewriting; uncertainty retains pending evidence, and changed source/target state requires reconciliation. Private scratch remains distinct from requested public output. Inline work needs no file creation.

Resolve native context only for project-bound work; a standalone draft creates no project. Proposed facts/decisions go to project and requested document registration to receive under their owning procedures and existing authorization. Keep every source/formatting/disclaimer requirement below, including the exact applicable final block.

Sources and evidence

Find relevant original links in the source catalog, filtered by geography and topic. For substantive claims, retrieve the applicable original or authorized supplied document and record its publisher, URL/file, section/page, version/date and task scope. A linked or reachable source is not proof of applicability. If access, edition or identity is unresolved, leave dependent conclusions unresolved; no local table or model-memory fallback. Keep task evidence in the authorized workspace, outside the plugin.

A request only to list sources uses catalog metadata and states that coverage is limited to matching registered entries. It needs no source-content retrieval, setup or approval. Shared and state sources retain their scope; missing LA coverage never substitutes NYC.

Draft the requested specification

Read the materials brief, accepted project requirements and any supplied template. Resolve ambiguous material/function choices only where they change the specification. Obtain selected division/section identities from the actual authorized publisher edition or supplied verified task inputs, using the CSI routes in the source catalog. There is no bundled MasterFormat mapping or compatibility edition. Keep an unresolved section identity open for review instead of inventing a best-fit number.

Use Arch Studio specification formatting. Cover the actual requested materials and applications; consolidate duplicates only when the accepted scope supports it. Preserve client template, units and terminology. Draft required submittals, accepted products/performance and execution/verification expectations from sourced project evidence. Distinguish proposed design requirements from adopted requirements and manufacturer claims. Cite exact standards/editions only after original verification.

Keep missing product choices, incompatible requirements and unverified claims marked for review. Do not fill gaps with generic manufacturer facts, copied clauses or unsupported code requirements. An outline does not certify code compliance or construction suitability.

Return all requested sections, verified identities, source locators and outstanding review items. Export only in the authorized destination. Follow the professional disclaimer rule for regulatory or life-safety requirements.

Outputs and records

Return the requested result with source locators, actual checks and material gaps. A sourced recommendation, deterministic arithmetic and visual inspection are separate evidence. Use the completion contract. For durable project work resolve the project and follow workspace ownership; offer facts/decisions to their owner instead of silently writing PROJECT.md. One-off work remains standalone.

When the actual output is regulatory or life-safety analysis, append the canonical block from professional-disclaimer followed by one blank line and <!-- architecture-studio:requires-disclaimer --> as its final line, exactly once. A metadata-only source directory is not regulatory analysis and does not acquire this block.

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 Spec Writer AI skill do?

Draft Project Manual specification sections from accepted project requirements using CSI MasterFormat identities, three-part sections and review flags. Use for design requirements; use product-cut-sheet for source-faithful product entries and epd-to-spec for EPD requirements.

Why use Spec Writer on TypingMind?

Because you install it once and use it with any model. Spec Writer 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 Spec Writer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AlpacaLabsLLC/skills-for-architects/tree/main/skills/spec-writer. 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 Spec Writer?

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 Spec Writer?

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

Is the Spec Writer AI skill free?

Yes. It is published on GitHub by AlpacaLabsLLC 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 👇