to-spec

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

Updated Jul 16, 2026
One-click install
npx skills add https://github.com/The-Focus-AI/walking-thoughts --skill to-spec-the-focus-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: to-spec
Source: https://github.com/The-Focus-AI/walking-thoughts/tree/main/.agents/skills/to-spec
Command: npx skills add https://github.com/The-Focus-AI/walking-thoughts --skill to-spec-the-focus-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a long design conversation into a formal specification is tedious and error-prone. This Skill converts the discussion you have already had into a structured spec and publishes it to the project issue tracker, without re-interviewing you. ## Core Features & Use Cases - Conversation Synthesis: Generates a spec purely from existing conversation context and codebase exploration, with no additional interview questions. - Test Seam Planning: Identifies the highest-level testing seams in the codebase and confirms them with you before writing the spec. - Issue Tracker Publishing: Writes the spec using a fixed template (problem statement, user stories, implementation and testing decisions, out of scope) and publishes it with the ready-for-agent triage label. - Use Case: After discussing a new feature with your AI assistant, invoke this Skill to produce a complete, tracker-ready spec that respects the project's domain glossary and ADRs. ## 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 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.

Does the spec skill ask interview questions before writing?

No. The skill explicitly avoids interviewing the user and works only from what has already been discussed. The only checkpoint is confirming the proposed testing seams match your expectations before the spec is written.

What sections does the generated spec template include?

The template includes Problem Statement, Solution, an extensive numbered list of User Stories, Implementation Decisions, Testing Decisions, Out of Scope, and Further Notes. File paths and code snippets are excluded except for decision-rich prototype excerpts.

What are testing seams in a feature spec?

Testing 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 necessary, and aims to minimize the total number of seams across the codebase.

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

Avoid it when the feature has not been discussed yet, since the skill does not gather requirements through interviews. It also requires the issue tracker and triage label vocabulary to be configured beforehand via the setup command.