Longwave

To spec skill

To spec is part of Matt Pocock's engineering skills. Its job is to turn the current conversation into a spec on your issue tracker, without another interview. It runs only when you call it by name; the agent never loads it on its own.

Add to Longwave

Source

When it runs

Only when you ask for it. The skill turns off automatic loading, so the agent never starts it on its own. This is the description it carries:

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.

What the instructions cover

The sections of its SKILL.md, in order.

Process
Problem Statement
Solution
User Stories
Implementation Decisions
Testing Decisions
Out of Scope
Further Notes

What ships with it

Besides SKILL.md, the folder carries these. The agent opens them only when a step in the instructions calls for one.

agents/ 1 file · 135 B

Install the to spec skill

In Claude Code, run this in a session. It comes from the publisher's own instructions.

Claude Code

/plugin install mattpocock-skills

License: MIT.

In Longwave, add Engineering Skills from the marketplace. It installs all 37 of its skills, and your Claude Code, Codex and OpenCode threads can use them.

Questions people ask

How do I install the to spec skill?

In Claude Code, run /plugin install mattpocock-skills. In Longwave, add Engineering Skills from the marketplace, and its skills reach your Claude Code, Codex and OpenCode threads.

Does the agent use the to spec skill automatically?

No. It sets disable-model-invocation in its frontmatter, so the agent never loads it on its own. Ask for it by name when you want it.

Use your skills in every harness.

Longwave installs a skill collection once, and your Claude Code, Codex and OpenCode threads can all use it.

Download Longwave