Skip to main content
skill · Claude Code

to-spec — Claude Code skill: what it does, how to install

Turns the current conversation and repository context into a spec, then publishes it to the project issue tracker. Use it when a feature discussion is ready to hand off to an agent.

  • Author Matt Pocock
  • License MIT
  • GitHub ★ 302,251
  • Installs 715,388
  • Updated 2026-10-22
  • Source shown below
Open on GitHub ↗

What to-spec does

to-spec reviews the current repository state, uses the project domain glossary, and respects ADRs in the area being changed. It synthesizes decisions already made in the conversation instead of starting a separate interview.

The skill identifies feature test seams, preferring existing seams at the highest practical level. It checks those seams with the user, writes a spec from its template, and publishes it to the issue tracker with the ready-for-agent label.

The resulting document covers the problem, solution, detailed user stories, implementation and testing decisions, scope boundaries, and further notes. The issue tracker and its triage labels need setup first; otherwise run /setup-matt-pocock-skills. Install it if your team turns feature discussions into agent-ready issues.

What it helps with

  • turn a feature discussion into a spec
  • write user stories for an issue
  • identify behavior-level test seams
  • apply repository ADRs and glossary terms
  • publish an issue with ready-for-agent

How to install to-spec

Command from the source

/plugin marketplace add mattpocock/skills

Command from the source

/plugin install mattpocock-skills@mattpocock

Command from the source

npx skills add mattpocock/skills --skill to-spec -a claude-code

With the Skills CLI (Vercel)

npx skills add mattpocock/skills --skill to-spec -a claude-code

Manually

~/.claude/skills/to-spec/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/to-spec/

How to use it: example prompts

  • "Turn our current discussion into a spec and publish it to the issue tracker."
  • "Draft the spec for this feature and check the testing seams with me."
  • "Run `/setup-matt-pocock-skills`, then turn this conversation into a spec."

Source text

SKILL.md · MIT
---
name: to-spec
description: "Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed."
disable-model-invocation: true
---

This skill takes the current conversation context and codebase understanding and produces a spec. Do NOT interview the user; just synthesize what you already know.

The issue tracker and triage label vocabulary should have been provided to you. If not, tell the user to run `/setup-matt-pocock-skills`.

## Process

1. Explore the repo to understand the current state of the codebase, if you haven't already. Use the project's domain glossary vocabulary throughout the spec, and respect any ADRs in the area you're touching.

2. Sketch out the seams at which you're going to test the feature. Existing seams should be preferred to new ones. Use the highest seam possible. If new seams are needed, propose them at the highest point you can. The fewer seams across the codebase, the better - the ideal number is one.

Check with the user that these seams match their expectations.

3. Write the spec using the template below, then publish it to the project issue tracker. Apply the `ready-for-agent` triage label - no need for additional triage.

<spec-template>

## Problem Statement

The problem that the user is facing, from the user's perspective.

## Solution

The solution to the problem, from the user's perspective.

## User Stories

A LONG, numbered list of user stories. Each user story should be in the format of:

1. As an <actor>, I want a <feature>, so that <benefit>

<user-story-example>
1. As a mobile bank customer, I want to see balance on my accounts, so that I can make better informed decisions about my spending
</user-story-example>

This list of user stories should be extremely extensive and cover all aspects of the feature.

## Implementation Decisions

A list of implementation decisions that were made. This can include:

- The modules that will be built/modified
- The interfaces of those modules that will be modified
- Technical clarifications from the developer
- Architectural decisions
- Schema changes
- API contracts
- Specific interactions

Do NOT include specific file paths or code snippets. They may end up being outdated very quickly.

Exception: if a prototype produced a snippet that encodes a decision more precisely than prose can (state machine, reducer, schema, type shape), inline it within the relevant decision and note briefly that it came from a prototype. Trim to the decision-rich parts, not a working demo, just the important bits.

## Testing Decisions

A list of testing decisions that were made. Include:

- A description of what makes a good test (only test external behavior, not implementation details)
- Which modules will be tested
- Prior art for the tests (i.e. similar types of tests in the codebase)

## Out of Scope

A description of the things that are out of scope for this spec.

## Further Notes

Any further notes about the feature.

</spec-template>

© Matt Pocock · MIT · mattpocock/skills

Questions about to-spec

How do I install to-spec in Claude Code?

Add the marketplace with /plugin marketplace add mattpocock/skills, then install the skill with /plugin install mattpocock-skills@mattpocock.

What does to-spec do?

It turns the current conversation and repository understanding into a specification, publishes it to the project issue tracker, and applies ready-for-agent.

What does to-spec need before it can publish?

The issue tracker and triage label vocabulary must be configured. Run /setup-matt-pocock-skills when that setup is missing.

Similar

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor