Set up a new OpenSpec change for a feature, fix, or modification. Create its working directory, show the document sequence and current status, and present the first template so drafting can begin.
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.
Review the instructions the agent will receive before you install.
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:
--schema <name>openspec schemas --json and let them chooseOtherwise: 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:
Guardrails
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Adapts existing designs for phones, tablets, desktops, print, and email. Adjusts layouts, navigation, content priorities, and touch controls to suit each context, with guidance for responsive sizing and verification across devices and input methods.
Audit a website for Google AdSense application readiness or ongoing ad-serving issues. Check content, navigation, crawler access, and disclosures against official requirements, then receive evidence-based findings, specific fixes, and a complete checklist with unresolved questions clearly marked.
Routes AI development questions to focused references on agents, language model security, retrieval-augmented generation, which uses retrieved information in answers, and prompt design and evaluation. It also outlines principles for validation, safety boundaries, version control, and ongoing assessment.
Review an interface and add purposeful motion to buttons, forms, navigation, and state changes. Plan and implement animations that clarify actions and provide feedback, while checking performance and supporting users who prefer reduced motion.
Find the relevant architectural guidance for API design, security, cloud infrastructure, message queues, and caching. This skill acts as an index to specialized references and lists principles for structuring software, distributed systems, and access controls.
Improve interface layouts by reviewing spacing, alignment, content density, and visual hierarchy, the cues that show what matters most. Refine repetitive card grids and crowded sections into compositions with consistent spacing and responsive structure.