to-spec

Synthesizes the current conversation into a structured spec and publishes it to the project issue tracker.

1|Updated Jul 2, 2026
One-click install
npx skills add https://github.com/filippolmt/skills --skill to-spec-filippolmt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: to-spec
Source: https://github.com/filippolmt/skills/tree/main/skills/to-spec
Command: npx skills add https://github.com/filippolmt/skills --skill to-spec-filippolmt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? After a long design discussion, turning scattered conversation context into a formal, actionable specification is tedious and error-prone. This Skill converts what has already been discussed into a complete spec document and publishes it to the project issue tracker, without re-interviewing the user. ## Core Features & Use Cases - Conversation-to-Spec Synthesis: Generates a spec from existing conversation context and codebase understanding, with no additional user interview. - Test Seam Planning: Identifies the highest-level testing seams in the codebase and confirms them with the user before writing the spec. - Structured Spec Template: Produces a spec with problem statement, solution, extensive user stories, implementation decisions, testing decisions, and out-of-scope notes. - 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 the AI, invoke the skill to produce a ready-for-implementation spec posted directly to the issue tracker, respecting the project's domain glossary and ADRs. ## Quick Start Ask the AI to turn the current conversation into a spec and publish it to the project issue tracker using the to-spec skill.

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 with problem statement, user stories, and implementation decisions, then publishes it to the project issue tracker.

How to write a spec without re-explaining requirements?

This skill explicitly avoids interviewing the user. It synthesizes what has already been discussed in the conversation, so you only need to confirm the proposed test seams before the spec is written and published.

Does the spec get published to an issue tracker automatically?

Yes. After writing the spec from the built-in template, the skill publishes it to the project issue tracker and applies the ready-for-agent triage label, with no additional triage step required.

What setup is required before using to-spec?

The issue tracker and triage label vocabulary must be configured first by running /setup-matt-pocock-skills. Without that setup, the skill cannot publish the spec or apply the correct labels.

What are test seams in a feature spec?

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

When should I not use conversation-to-spec synthesis?

Avoid it when requirements have not yet been discussed, since the skill only synthesizes existing context and will not interview you. It also excludes specific file paths and code snippets from the spec, except decision-rich prototype fragments.