to-spec

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

9|Updated Jul 17, 2026
One-click install
npx skills add https://github.com/Yassimba/loom --skill to-spec-yassimba
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: to-spec
Source: https://github.com/Yassimba/loom/tree/main/skills/to-spec
Command: npx skills add https://github.com/Yassimba/loom --skill to-spec-yassimba

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a design discussion into a written spec usually means re-interviewing stakeholders and re-deriving decisions. This Skill synthesizes the current conversation and codebase understanding directly into a structured spec, without asking the user to repeat themselves. ## Core Features & Use Cases - Conversation-to-Spec Synthesis: Converts the existing discussion context into a spec with problem statement, solution, user stories, implementation decisions, testing decisions, and scope boundaries. - Test Seam Planning: Identifies the highest-level testing seams in the codebase before writing the spec, preferring existing seams and confirming them with the user. - Issue Tracker Publishing: Publishes the finished spec to the configured project issue tracker, falling back to Beads or local Markdown when no tracker is configured. - Use Case: After a brainstorming session about a CSV export feature, invoke this Skill to produce a complete spec with user stories and architectural decisions, then file it as a ticket for implementation. ## Quick Start Use the to-spec skill to turn our current discussion into a spec and publish it to the 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 design discussion into a written spec?

Invoke the to-spec skill after your design conversation. It synthesizes the existing context into a spec covering problem statement, solution, user stories, implementation decisions, and testing decisions, then publishes it to your issue tracker.

How do I write user stories for a feature spec?

The skill generates an extensive numbered list of user stories in the format 'As an <actor>, I want a <feature>, so that <benefit>'. It derives them from the conversation context rather than asking you to enumerate them manually.

What happens if no issue tracker is configured?

The skill falls back to Beads when the br command is installed, otherwise it writes the spec to local Markdown files. Running /loom initializes the project and configures the tracker.

Should a spec include file paths and code snippets?

No, the spec template explicitly excludes file paths and code snippets because they become outdated quickly. The exception is prototype snippets that encode a decision more precisely than prose, such as state machines or type shapes.

What are test seams in spec planning?

Test 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 confirms the choice with the user before writing the spec.