openspec-continue
Create the next artifact in the dependency chain with `/opsx:continue`, building up a change incrementally. Use when the user says "continue the change", "create next artifact", "/opsx:continue", or wants step-by-step artifact creation.
Best use case
openspec-continue is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. Create the next artifact in the dependency chain with `/opsx:continue`, building up a change incrementally. Use when the user says "continue the change", "create next artifact", "/opsx:continue", or wants step-by-step artifact creation.
Create the next artifact in the dependency chain with `/opsx:continue`, building up a change incrementally. Use when the user says "continue the change", "create next artifact", "/opsx:continue", or wants step-by-step artifact creation.
Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.
Practical example
Example input
Use the "openspec-continue" skill to help with this workflow task. Context: Create the next artifact in the dependency chain with `/opsx:continue`, building up a change incrementally. Use when the user says "continue the change", "create next artifact", "/opsx:continue", or wants step-by-step artifact creation.
Example output
A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.
When to use this skill
- Use this skill when you want a reusable workflow rather than writing the same prompt again and again.
When not to use this skill
- Do not use this when you only need a one-off answer and do not need a reusable workflow.
- Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/openspec-continue/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How openspec-continue Compares
| Feature / Agent | openspec-continue | 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?
Create the next artifact in the dependency chain with `/opsx:continue`, building up a change incrementally. Use when the user says "continue the change", "create next artifact", "/opsx:continue", or wants step-by-step artifact creation.
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
# OpenSpec Continue Skill
Use **`/opsx:continue`** to create the next artifact in the dependency chain. This builds a change incrementally — one artifact at a time — giving the user control to review and edit before proceeding.
## When to Use
- The user wants incremental, step-by-step artifact creation.
- After creating a change with **openspec-new** and wanting to build artifacts one at a time.
- The user says "continue", "next artifact", "create specs", "create design".
## Prerequisites
- **An active change** exists (created via **openspec-new** or `/opsx:new`).
## Workflow
1. **Query the dependency graph**
- Run `openspec status --change <name> --json` to see which artifacts are done, ready, or blocked.
2. **Identify ready artifacts**
- In the default `spec-driven` schema: `proposal` -> `specs` / `design` -> `tasks`.
- Dependencies are enablers: once a dependency is done, its dependents become "ready".
3. **Create one artifact**
- Read dependency files for context.
- Run `openspec instructions <artifact> --change <name> --json` to get enriched instructions and templates.
- Create the first ready artifact (e.g. proposal, then specs, then design, then tasks).
4. **Show what's unlocked**
- After creating an artifact, report what becomes available next.
5. **Repeat**
- User reviews, optionally edits, then runs `/opsx:continue` again for the next artifact.
## Artifact Dependency Graph (spec-driven schema)
```
proposal (root, no dependencies)
|
+---> specs (requires: proposal)
|
+---> design (requires: proposal)
|
+---> tasks (requires: specs + design)
```
## Outputs
- One artifact file created per invocation (e.g. `proposal.md`, `specs/**/*.md`, `design.md`, `tasks.md`).
## Next Steps
- Run `/opsx:continue` again for the next artifact.
- When all planning artifacts are done: use **openspec-apply** to implement tasks.
- Or use **openspec-ff** to fast-forward remaining artifacts.
## Troubleshooting
- **"No artifacts ready"**: All artifacts are either complete or blocked. Check `openspec status --change <name>`.
- **"Change not found"**: Specify the change name explicitly: `/opsx:continue add-dark-mode`.
## References
- [OpenSpec Commands: /opsx:continue](https://github.com/Fission-AI/OpenSpec/blob/main/docs/commands.md)
- [OpenSpec Concepts: Artifacts](https://github.com/Fission-AI/OpenSpec/blob/main/docs/concepts.md)Related Skills
openspec-verify
Validate that implementation matches change artifacts using `/opsx:verify`, checking completeness, correctness, and coherence. Use when the user says "verify implementation", "check my work", "/opsx:verify", or wants quality validation before archiving.
openspec-update
Run `openspec update` to regenerate AI tool instruction files after upgrading the OpenSpec CLI. Use when the user says "update OpenSpec", "openspec update", or "refresh OpenSpec skills/commands".
openspec-sync
Sync delta specs from a change into main specs using `/opsx:sync`, without archiving the change. Use when the user says "sync specs", "merge specs to main", "/opsx:sync", or needs to update main specs mid-change.
openspec-schema
Create and manage custom workflow schemas using `openspec schema init/fork/validate/which`. Use when the user says "create a custom workflow", "custom schema", "fork a schema", or wants to define their own artifact types and dependencies.
openspec-onboard
Guided onboarding through the complete OpenSpec workflow using `/opsx:onboard`, walking the user through a real change in their codebase. Use when the user says "onboard me", "tutorial", "/opsx:onboard", "how does OpenSpec work", or is new to OpenSpec.
openspec-new
Start a new OpenSpec change with `/opsx:new`, creating a change folder with metadata and scaffolding. Use when the user says "start a new change", "new feature", "/opsx:new", or "create an OpenSpec change".
openspec-install
Install the OpenSpec CLI globally via npm, pnpm, yarn, bun, or nix. Use when the user says "install OpenSpec", "set up OpenSpec", or "openspec command not found".
openspec-initial
Run `openspec init` to initialize OpenSpec in a project directory, creating the openspec/ folder structure and configuring AI tool integrations. Use when the user says "initialize OpenSpec", "openspec init", or "set up OpenSpec in this project".
openspec-ff
Fast-forward through artifact creation with `/opsx:ff`, generating all planning artifacts (proposal, specs, design, tasks) at once. Use when the user says "fast forward", "create all artifacts", "/opsx:ff", or has a clear picture of what to build.
openspec-explore
Think through ideas, investigate problems, and clarify requirements before committing to a change using `/opsx:explore`. Use when the user says "explore an idea", "think through this", "investigate options", or wants to brainstorm before creating a formal change.
openspec-config
Configure OpenSpec project settings and global CLI configuration using `openspec/config.yaml` and `openspec config` commands. Use when the user says "configure OpenSpec", "project config", "add project context", or wants to set per-artifact rules.
openspec-bulk-archive
Archive multiple completed changes at once with `/opsx:bulk-archive`, handling spec conflicts between changes. Use when the user says "archive all changes", "bulk archive", "/opsx:bulk-archive", or has multiple completed changes.