to-spec

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

2|Updated May 12, 2026
One-click install
npx skills add https://github.com/tajo9128/BioDockify-Pharma-AI --skill to-spec-tajo9128
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: to-spec
Source: https://github.com/tajo9128/BioDockify-Pharma-AI/tree/main/.agents/skills/to-spec
Command: npx skills add https://github.com/tajo9128/BioDockify-Pharma-AI --skill to-spec-tajo9128

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a long design discussion into an actionable specification usually requires tedious manual writing and re-interviewing stakeholders. This Skill converts the current conversation and codebase understanding directly into a structured spec and publishes it to the project issue tracker without asking redundant questions. ## Core Features & Use Cases - Conversation-to-Spec Synthesis: Generates a complete spec (problem statement, solution, user stories, implementation and testing decisions, scope) from existing discussion context. - Test Seam Planning: Identifies the highest-level existing seams in the codebase for testing and confirms them with the user before writing. - 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 and exploring the repo, invoke this Skill to produce a ready-for-implementation spec issue without re-explaining anything. ## Quick Start Ask the AI 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 software spec?

Invoke the to-spec skill after discussing the feature with the AI. 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 feature specification?

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 these stories automatically from the conversation rather than asking you to enumerate them.

Does to-spec require an issue tracker setup?

Yes, the issue tracker and triage label vocabulary must be provided beforehand, typically by running /setup-matt-pocock-skills. Without that configuration the skill cannot publish the spec or apply the ready-for-agent label.

Can I review the spec before it is published?

The skill checks proposed test seams with you before writing the spec, but the spec itself is written and published in one pass. It is designed for synthesis of agreed context, not iterative drafting.

What are the limitations of conversation-based spec generation?

The skill deliberately avoids interviewing the user, so any requirement never discussed will not appear in the spec. It also excludes specific file paths and code snippets from implementation decisions, except for prototype-derived decision-rich snippets.