to-spec

Converts conversation context into a structured spec published to the project issue tracker.

2|Updated Jul 6, 2026
One-click install
npx skills add https://github.com/NAMEWTA/learning-open-code --skill to-spec-namewta
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: to-spec
Source: https://github.com/NAMEWTA/learning-open-code/tree/main/translator/open-ai-skills/matt-pocock-skills/skills/engineering/to-spec
Command: npx skills add https://github.com/NAMEWTA/learning-open-code --skill to-spec-namewta

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a long design discussion into an actionable specification usually requires tedious re-interviewing and manual write-up. This Skill synthesizes the current conversation and codebase understanding directly into a complete spec, then publishes it to the project's issue tracker without asking redundant questions. ## Core Features & Use Cases - Context Synthesis: Reads the existing conversation and explores the repository to ground the spec in the project's domain vocabulary and ADRs. - Seam Planning: Drafts test seams for the feature, preferring existing high-level seams, and confirms them with the user before writing. - Structured Spec Template: Produces problem statement, solution, exhaustive user stories, implementation decisions, testing decisions, out-of-scope items, and additional notes. - Issue Tracker Publishing: Posts the finished spec to the project issue tracker with the ready-for-agent triage label. - Use Case: After discussing a new billing feature with the AI, invoke this Skill to generate a full spec with user stories and test decisions, then file it as an issue ready for an implementation agent. ## Quick Start Ask the AI to turn the current conversation into a spec and publish it to the project issue tracker with the ready-for-agent label.

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 synthesizes the conversation and codebase context into a spec with problem statement, user stories, implementation decisions, and test decisions, then publishes it to the issue tracker.

Does to-spec interview the user for requirements?▼

No. The skill explicitly avoids interviewing and only synthesizes what has already been discussed in the conversation. The single exception is confirming the proposed test seams with the user before writing the spec.

What is a test seam in a feature spec?▼

A test seam is the boundary where tests interact with the feature. The skill prefers existing high-level seams over creating new ones, aiming for ideally one seam per codebase, and confirms the choice with the user.

What happens if the issue tracker setup is missing?▼

The skill expects the issue tracker and triage label glossary to be provided beforehand. If they are missing, it instructs running /setup-matt-pocock-skills to configure them before generating the spec.

Should a spec include file paths and code snippets?▼

Generally no, because they become outdated quickly. The exception is when a prototype produced a snippet, such as a state machine or schema, that encodes a decision more precisely than prose; it is inlined with a note.