to-spec

Generate a structured feature spec from conversation context and publish it to the project issue tracker.

Updated Mar 27, 2026
One-click install
npx skills add https://github.com/gmackie/agent-skills --skill to-spec-gmackie
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: to-spec
Source: https://github.com/gmackie/agent-skills/tree/main/skills/to-spec
Command: npx skills add https://github.com/gmackie/agent-skills --skill to-spec-gmackie

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a long planning conversation into a formal, actionable specification is tedious and error-prone. This Skill synthesizes the existing conversation and codebase understanding into a complete spec document and publishes it directly to the project's issue tracker, without re-interviewing the user. ## Core Features & Use Cases - Conversation-to-Spec Synthesis: Converts already-discussed context into a structured spec with problem statement, solution, user stories, implementation decisions, testing decisions, and scope boundaries. - Test Seam Planning: Identifies existing or proposed testing seams in the codebase and confirms them with the user before writing the spec. - Issue Tracker Publishing: Publishes the finished spec to the project issue tracker and applies the ready-for-agent triage label. - Use Case: After discussing a new feature with your AI assistant, invoke this Skill to produce a numbered user-story spec and file it as a triaged issue ready for an implementation agent. ## Quick Start Ask the assistant to turn the current conversation into a spec and publish it to the project issue tracker.

Frequently Asked Questions about to-spec

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn a conversation into a feature spec?▼

Invoke the to-spec skill after discussing the feature. It explores the repository, confirms testing seams with you, then writes a spec using a fixed template covering problem statement, user stories, implementation and testing decisions, and scope.

How to publish a spec to a project issue tracker?▼

The skill publishes the finished spec directly to the configured project issue tracker and applies the ready-for-agent triage label. The tracker and label vocabulary must be provided beforehand via the setup-matt-pocock-skills command.

Does the spec include file paths or code snippets?▼

No, implementation decisions exclude specific file paths and code snippets because they become outdated quickly. The only exception is a trimmed prototype snippet that encodes a decision more precisely than prose, such as a state machine or schema.

What are testing seams in spec writing?▼

Testing seams are the boundaries at which a feature will be tested. The skill prefers existing seams at the highest possible level, proposes new ones only when needed, and asks you to confirm the seams before writing the spec.

When should I not use conversation-to-spec generation?▼

Avoid it when requirements have not been discussed yet, since the skill explicitly does not interview the user. It synthesizes only what is already known from the conversation and codebase exploration.