To Spec logo

To Spec

Community
devton
to-spec

Specification synthesis protocol to transform wayfinder orientation, grilling logs, domain models, research spikes, and prototypes into actionable, executable technical plans.

Overview

Publisherdevton
Repositoryagentic-workflow-blueprint
Skill nameto-spec
Stars
73
Forks
4
Bundled files
Instructions only
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 devton on GitHub. Read the source before you install it.

Installation

Install the To Spec 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/devton/agentic-workflow-blueprint/tree/main/workflows/mattpocock/to-spec
  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/devton/agentic-workflow-blueprint.git /tmp/agentic-workflow-blueprint
mkdir -p .claude/skills
cp -r /tmp/agentic-workflow-blueprint/workflows/mattpocock/to-spec .claude/skills/to-spec
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable To Spec 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 To Spec 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 To Spec 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.

agentic-workflows-blueprint.workflow.mattpocock.to-spec

Goal

Goal

Synthesize orientation briefs, grilling decision logs, domain models, technical research spikes, and prototype learnings into a rigorous, unambiguous executable technical specification saved at docs/tasks/task.<reference>.md.


Scope

  • Applies to: Transforming conceptual discovery and research artifacts into executable implementation specifications and task breakdowns.
  • Does not cover: Direct code execution or preliminary discovery (use upstream Matt Pocock skills or execution phase).

Triggers

  • "/to-spec"
  • "Convert findings to executable spec"
  • "Generate specification from prototype and domain model"
  • "To-spec conversion"

Inputs

  • wayfinderBrief: Orientation brief (wayfinder.md).
  • decisionLog: Grilling decision log (decision-log.md).
  • domainModel: Domain entity & state machine specification (domain-model.md).
  • researchReport (optional): Technical research spike report (research-spike.md).
  • prototypeReport (optional): Prototype retrospective (prototype-report.md).
  • projectSlug: Short identifier for the repository.

Invariants (Guardrails)

  1. Unambiguous Task Mapping: Every task in docs/tasks/task.<reference>.md must specify exact target file paths, explicit dependencies, step-by-step code changes, and verification commands.
  2. Enforce UUIDv7 Identity Standards: Ensure all data models, schemas, and resource IDs in the spec mandate UUIDv7 for time-ordered sorting.
  3. Strict Phase Gating: The generated specification (docs/tasks/task.<reference>.md) must obtain explicit user approval before execution (Phase 9 of embed-aihero-radioactive).
  4. Isolated Task File Path: Save specifications under docs/tasks/task.<reference>.md to avoid cluttering root and prevent overwriting tasks from other sessions.

Procedure

1) Consolidate Upstream Evidence
  1. Gather all upstream artifacts: wayfinder.md, decision-log.md, domain-model.md, research-spike.md, and prototype-report.md.
  2. Verify that all critical unknowns have been resolved and domain entities have UUIDv7 primary keys.
2) Structure Technical Specification (docs/tasks/task.<reference>.md)

Produce a structured task specification file at docs/tasks/task.<reference>.md formatted as follows:

markdown
# Technical Specification & Execution Plan: <Feature Title>

## 1. Executive Context & Objectives
- **Goal**: Clear 1-2 sentence objective.
- **Scope**: Explicit In-Scope vs. Out-of-Scope boundaries.
- **Key Invariants**: UUIDv7 primary keys, security rules, performance SLA.

## 2. Architecture & Domain Model
- Summary of entities, UUIDv7 schemas, state machines, and API endpoints.
- Embedded Mermaid ER / State diagrams from Phase 3.

## 3. Sequential Task Breakdown
- [ ] Task 1: <Task Title>
  - **Target Files**: `path/to/file.ext`
  - **Dependencies**: None / Task X
  - **Changes Required**: Detailed description of code/schema edits.
  - **Verification Command**: `npm run test` or `bun test path/to/spec`

- [ ] Task 2: <Task Title>
  - **Target Files**: `path/to/file.ext`
  - **Dependencies**: Task 1
  - **Changes Required**: Detailed description of edits.
  - **Verification Command**: `npm run test`

## 4. Quality Assurance & Test Strategy
- Unit test requirements, integration tests, and performance/security verification steps.

## 5. Rollback & Operational Safety Playbook
- Pre-change snapshot commands, change window constraints, and step-by-step rollback procedures.
3) Review & Sanity-Check Specification
  1. Verify that all target file paths exist or have parent directories defined.
  2. Ensure task dependencies form a directed acyclic graph (DAG) without circular loops.
  3. Confirm that verification commands are non-interactive and testable.
4) Present Specification & Gate on User Approval
  1. Present docs/tasks/task.<reference>.md to the user.
  2. Gate on explicit user approval before proceeding to Phase 8 (Blueprint Contract) and Phase 9 (Execute).

Outputs

  • docs/tasks/task.<reference>.md: Comprehensive technical specification and execution breakdown ready for implementation.

Review gate

  • All upstream artifacts (wayfinder, decision log, domain model, research, prototype) integrated.
  • Tasks contain exact file paths, explicit edits, and verification commands.
  • UUIDv7 primary key standard enforced for all data models.
  • Specification presented to user and explicit approval obtained.

References

  • ../../../SKILL.md
  • ../domain-modeling/SKILL.md
  • ../prototype/SKILL.md
  • ../../plan-to-blueprint/SKILL.md
  • ../../embed-aihero-radioactive/SKILL.md

Frequently asked questions

What does the To Spec AI skill do?

Specification synthesis protocol to transform wayfinder orientation, grilling logs, domain models, research spikes, and prototypes into actionable, executable technical plans.

Why use To Spec on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/devton/agentic-workflow-blueprint/tree/main/workflows/mattpocock/to-spec. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use To Spec?

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 To Spec?

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

Is the To Spec AI skill free?

It is published on GitHub by devton. Check the repository for licensing terms. 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 👇