skills.rest
sanjanb
sanjanbCOMMUNITY
Explore all skills by this author →
GitHub

to-spec

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

1|Updated Jul 23, 2026
Search Tags:#documentation#requirements#issue tracker#feature planning#user stories#spec#prd
One-click install
npx skills add https://github.com/sanjanb/my-agent-harness --skill to-spec-sanjanb
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: to-spec
Source: https://github.com/sanjanb/my-agent-harness/tree/main/skills/mp-to-spec
Command: npx skills add https://github.com/sanjanb/my-agent-harness --skill to-spec-sanjanb

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a long planning conversation into a formal spec (PRD) is tedious and error-prone. This Skill converts the current conversation and codebase understanding directly into a structured spec and publishes it to the project issue tracker, without re-interviewing the user. ## Core Features & Use Cases - Conversation-to-Spec Synthesis: Generates a complete spec from existing discussion context, with no additional user interview required. - Test Seam Planning: Identifies and validates testing seams in the codebase before writing the spec, preferring existing high-level seams. - 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 your AI assistant, invoke this Skill to produce a spec with problem statement, user stories, implementation decisions, and testing decisions, then file it as a ready-for-agent issue. ## 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 product spec?▼

Invoke this Skill after discussing a feature with your AI assistant. 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 your issue tracker.

How to write a PRD without interviewing stakeholders again?▼

This Skill explicitly avoids re-interviewing the user. It synthesizes what has already been discussed in the conversation, explores the repository for context, and produces the spec using a fixed template.

Does the spec include testing and implementation decisions?▼

Yes. The spec template includes Implementation Decisions (modules, interfaces, architectural choices) and Testing Decisions (what to test, which modules, prior art). It deliberately excludes specific file paths and code snippets that could become outdated.

What setup is required before using this spec skill?▼

The issue tracker and triage label vocabulary must be configured first by running /setup-matt-pocock-skills. Without this setup, the Skill cannot publish specs or apply the ready-for-agent triage label.

When should I not use conversation-to-spec automation?▼

Avoid it when requirements are still ambiguous or undiscussed, since the Skill only synthesizes existing context and will not interview you. It also requires user confirmation of proposed testing seams before writing the spec.

Related Skills

Explore More Product & Management Skills→
jwh3timesjwh3times
1

to-spec

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

Community
Intermediate
Obsidian-OwlObsidian-Owl
9

sw-build

Implement software work units through a TDD cycle with Git commits.

Official
Advanced
jwh3timesjwh3times
1

improve-codebase-architecture

Scan a codebase for module deepening opportunities and present them as a visual HTML report.

Community
Advanced
dhruvbaldawadhruvbaldawa
31

interviewing

Clarify ambiguous requirements through structured questioning and documentation.

Community
Basic