Skip to content
Back to skills

Spec

ASecurity

Define or update a feature specification. Provide a feature name and description with optional Figma link. Updates spec/feature/[name]/spec.md and design.md without touching source code.

  • 3 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added May 27, 2026
data-ai

Security analysis

A100/100

Scanned May 27, 2026

npx -y skills add ByeongminLee/nextjs-claude-code --skill spec --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Spec?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Spec
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/byeongminlee-spec/badge)](https://www.skillsdirectory.com/skills/byeongminlee-spec)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: spec
description: Define or update a feature specification. Provide a feature name and description with optional Figma link. Updates spec/feature/[name]/spec.md and design.md without touching source code.
argument-hint: "[feature-name] [description + optional Figma URL]"
context: fork
---

## Prerequisite check

Before routing to any agent, verify `/init` has been run:
- Check if `spec/PROJECT.md` exists
- If NOT exists → output: "Project not initialized. Run `/init` first to analyze your codebase and set up the spec directory." → **STOP**

## Model selection

Assess task size per `spec/rules/_model-routing.md`:
- If updating an existing spec with minor changes (feature directory already exists, spec.md present) → spawn `spec-writer` with `model: haiku`
- If creating a new feature spec from scratch → spawn `spec-writer` with `model: sonnet`

## Task

Spawn `spec-writer` agent (with assessed model) with the following prompt:

```
Write or update the feature specification based on the following:
$ARGUMENTS
```

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.