What is the experimental artifact-driven approach?

It scaffolds changes as a sequence of artifacts with statuses, letting you preview the first template before creating any artifacts.

What if the change name is not kebab-case or already exists?

If the name is invalid (not kebab-case), provide a valid name. If a change with that name already exists, consider continuing that change instead of starting a new one.

How do I use a non-default schema or see available workflows?

Use --schema to specify a schema. If you want to explore, run openspec schemas --json to see options, or say 'show workflows' to choose.

openspec-new-change

Scanned

npx machina-cli add skill azzgo/agent-skills/openspec-new-change --openclaw

Files (1)

SKILL.md

2.8 KB

Start a new change using the experimental artifact-driven approach.

Input: The user's request should include a change name (kebab-case) OR a description of what they want to build.

Steps

If no clear input provided, ask what they want to build

Use the AskUserQuestion tool (open-ended, no preset options) to ask:

"What change do you want to work on? Describe what you want to build or fix."

From their description, derive a kebab-case name (e.g., "add user authentication" → add-user-auth).

IMPORTANT: Do NOT proceed without understanding what the user wants to build.
Determine the workflow schema

Use the default schema (omit --schema) unless the user explicitly requests a different workflow.

Use a different schema only if the user mentions:
- A specific schema name → use --schema <name>
- "show workflows" or "what workflows" → run openspec schemas --json and let them choose
Otherwise: Omit --schema to use the default.
Create the change directory
```
openspec new change "<name>"
```
Add --schema <name> only if the user requested a specific workflow. This creates a scaffolded change at openspec/changes/<name>/ with the selected schema.
Show the artifact status
```
openspec status --change "<name>"
```
This shows which artifacts need to be created and which are ready (dependencies satisfied).
Get instructions for the first artifact The first artifact depends on the schema (e.g., proposal for spec-driven). Check the status output to find the first artifact with status "ready".
```
openspec instructions <first-artifact-id> --change "<name>"
```
This outputs the template and context for creating the first artifact.
STOP and wait for user direction

Output

After completing the steps, summarize:

Change name and location
Schema/workflow being used and its artifact sequence
Current status (0/N artifacts complete)
The template for the first artifact
Prompt: "Ready to create the first artifact? Just describe what this change is about and I'll draft it, or ask me to continue."

Guardrails

Do NOT create any artifacts yet - just show the instructions
Do NOT advance beyond showing the first artifact template
If the name is invalid (not kebab-case), ask for a valid name
If a change with that name already exists, suggest continuing that change instead
Pass --schema if using a non-default workflow

Source

git clone https://github.com/azzgo/agent-skills/blob/main/.opencode/skills/openspec-new-change/SKILL.mdView on GitHub

Overview

This skill guides you through starting a new OpenSpec change using the experimental artifact-driven workflow. It provides a structured, step-by-step approach to create a change with a kebab-case name, select a workflow schema, and preview the first artifact template—without actually creating artifacts yet.

How This Skill Works

You provide a change name or description, and the system derives a kebab-case name. It then selects the default workflow schema (unless you request a specific one), creates the change scaffold with openspec new change "<name>", shows the current artifact status, and retrieves the first artifact template via openspec instructions <first-artifact-id> --change "<name>". The process stops there, awaiting your direction before generating any artifacts.

When to Use It

Starting a new feature or fix in an OpenSpec project using a structured, artifact-driven workflow
Planning changes when you want a clear kebab-case name and explicit schema choice
Pre-checking artifact readiness and first-template content before implementation
Sharing a concrete plan with teammates by displaying the change location and artifact sequence
Ensuring no artifacts are created prematurely while you validate the approach

Quick Start

Step 1: Provide a kebab-case change name or a description of what you want to build
Step 2: Run openspec new change "<name>" (Add --schema <name> only if a non-default workflow is requested)
Step 3: Run openspec status --change "<name>" to see artifacts; then runs openspec instructions <first-artifact-id> --change "<name>" to view the first artifact template

Best Practices

Validate that the change name is kebab-case before proceeding
Decide on a schema early; omit --schema for default unless a specific workflow is requested
Rely on the status output to understand which artifacts are ready or pending
Carefully review the first artifact template before drafting any content
Stop after showing the first artifact template and confirm next steps with the user

Example Use Cases

add-user-auth: Start a new feature to implement user authentication with the artifact workflow
fix-404-handling: Create a change to address API route 404 behavior using the experimental schema
update-api-docs: Begin a change to revise API documentation workflow and artifact templates
improve-caching: Initiate a change to enhance caching strategy across services
refactor-product-endpoints: Start a change to restructure product catalog endpoints using the default schema

Frequently Asked Questions

Add this skill to your agents