Spec

## Command

170 stars

byMiosa-osa

View on GitHub Installation ↓

Best use case

Spec is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

## Command

Teams using Spec should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/spec/SKILL.md --create-dirs "https://raw.githubusercontent.com/Miosa-osa/canopy/main/operations/dev-shop/skills/spec/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/spec/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How Spec Compares

Feature / Agent	Spec	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

## Command

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Spec

## Command
/spec <feature_name> [--depth brief|full]

## Purpose
Generate a technical specification for a feature or system change.

## Arguments
| Arg | Type | Required | Description |
|-----|------|----------|-------------|
| feature_name | string | Yes | Feature to spec |
| --depth | string | No | Spec depth: brief (1-page) or full (complete). Default: full |

## Output
Genre: spec
Format: Markdown technical specification

Produces:
1. **Goal** -- what and why
2. **Requirements** -- numbered with acceptance criteria
3. **Constraints** -- what's off the table
4. **Architecture** -- system design, affected services, API contracts
5. **Test Plan** -- what to test, edge cases
6. **Rollback Plan** -- how to undo if needed

## Agent Activation
1. **tech-lead** (wave 1): Requirements, constraints, acceptance criteria
2. **architect** (wave 1): System design, API contracts, data model

## Process
```
1. Tech-lead defines requirements and constraints
2. Architect designs system integration and API contracts
3. Combined into single spec document per tech-lead's template
4. Tech-lead reviews and approves final spec
```

## Examples
```
/spec "user-search-feature"
/spec "api-rate-limiting" --depth brief
```

Related Skills

Prospect

170

from Miosa-osa/canopy

## Command

create-spec

170

from Miosa-osa/canopy

Guided spec creation through 9 phases from discovery to testing strategy. Supports spec types: library, feature, change. Produces a complete specification document with requirements, architecture, constraints, and YAML test data. Interactive or autonomous modes. Triggers on: "create spec", "write spec", "spec out", "specification", "design document"