to-spec

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

Updated May 31, 2026
One-click install
npx skills add https://github.com/AlexanderNarbaev/agi --skill to-spec-alexandernarbaev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: to-spec
Source: https://github.com/AlexanderNarbaev/agi/tree/main/.opencode/skills/matt-pocock/to-spec
Command: npx skills add https://github.com/AlexanderNarbaev/agi --skill to-spec-alexandernarbaev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a long design conversation into a formal specification usually requires tedious re-interviewing and manual write-up. This Skill synthesizes the existing conversation and codebase understanding directly into a structured spec and publishes it to the project issue tracker, eliminating redundant questioning. ## Core Features & Use Cases - Conversation-to-Spec Synthesis: Generates a complete spec (problem statement, solution, user stories, implementation and testing decisions) from the current conversation without interviewing the user again. - Test Seam Planning: Identifies existing architectural seams for testing, preferring the highest-level seam and minimizing new ones, with user confirmation. - Issue Tracker Publishing: Publishes the finished spec to the project issue tracker and applies the ready-for-agent triage label automatically. - Use Case: After discussing a new feature with the AI and exploring the codebase, invoke this Skill to produce a ready-for-implementation spec issue without writing any of it manually. ## Quick Start Ask the AI to turn the current conversation into a spec and publish it to the 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 existing conversation and codebase context into a structured spec covering problem statement, user stories, implementation decisions, and testing decisions, then publishes it to the issue tracker.

How to write user stories for a software specification?

The skill generates an extensive numbered list of user stories in the format 'As an <actor>, I want a <feature>, so that <benefit>'. The stories are derived from the conversation and cover all aspects of the feature being specified.

Does the spec skill require an issue tracker setup?

Yes, the issue tracker and triage label vocabulary must be provided beforehand. If they are missing, the skill instructs the user to run /setup-matt-pocock-skills before it can publish specs.

What are test seams in specification writing?

Test seams are the architectural boundaries where a feature will be tested. The skill prefers existing seams at the highest possible level, proposes new ones only when necessary, and confirms the choices with the user before writing the spec.

When should I not use conversation-based spec generation?

Avoid it when requirements have not been discussed yet, since the skill explicitly does not interview the user. It only synthesizes what has already been explored in the conversation and codebase.