dimitritholen/1337-claude/spec

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.

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.

1. 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.

1. Derive the Expectations block from the user stories and the touched surfaces, following references/expectations.md. Show it to the user for approval: the approved block is the definition of done. This is the one exception to "do not interview", like confirming the seams: confirm the block, do not open a Q&A.

1. Write the spec using the template below, then record it (below).

<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.

Expectations

Mandatory. A table ID | Expectation | Check | Seam, built with references/expectations.md: Acceptance, Claims, Context map, Transitions, Parity, Conventions, Inputs and controls, Styling and Edge-case rows, plus the house rules the feature is subject to. Check is e2e, unit, metric, visual or judgement; judgement rows are the only ones left to 1337:qa. Internal-only features (no UI, no user-visible output) need only Acceptance and Edge-case rows.

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>

Where the spec lives

Check once, in this order, and never record in both:

1. tasqx — tasqx_add_memory is in this session's tool list. Save the

spec with tasqx_add_memory, title Spec: <feature>, project set, the one-sentence goal as the first line. A tasqx server without its write tools counts as absent; say so in one line.

1. Plan file — otherwise plans/<slug>-spec.md in the repo root: slug

from the feature, kebab-case, at most five words.

Pipeline

Before this: /1337:grill sharpens the idea into settled decisions this skill can synthesize. After this: /1337:plan slices the spec into builder-sized tasks, then /1337:implement works them.