Skip to content

fix: add slash command hints in workflow completion messages #603

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
CS-Tao wants to merge 2 commits into
base: main
Choose a base branch
from
+2 −2
Open

fix: add slash command hints in workflow completion messages #603

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1109b4f
fix: add slash command hints in workflow completion messages
CS-Tao Jan 27, 2026
a9d72fb
Merge branch 'main' into main
CS-Tao Jan 28, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions src/core/templates/skill-templates.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1762,7 +1762,7 @@ export function getOpsxContinueCommandTemplate(): CommandTemplate {
**If all artifacts are complete (\`isComplete: true\`)**:
- Congratulate the user
- Show final status including the schema used
- Suggest: "All artifacts created! You can now implement this change or archive it."
- Suggest: "All artifacts created! You can now implement this change with \`/opsx:apply\` or archive it with \`/opsx:archive\`."
Copy link
Contributor

@TabishB TabishB Jan 27, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think this possibly might be claude code specific commands? I've tried to make the instructions not specific to claude code since people use this with different coding agents.

Copy link
Author

@CS-Tao CS-Tao Jan 29, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi, I'd like to clarify - the change I made is in the Command template (getOpsxContinueCommandTemplate), not the Skill template.

The Command templates (returning CommandTemplate) already contain many /opsx:* references throughout. For example:

  • "Run /opsx:continue to create the next artifact"
  • "Run /opsx:apply to start implementing"

So adding the slash command hints here is consistent with the existing pattern in Command templates.

The real problem I'm trying to solve: when new team members first use OpenSpec, they don't know they need to run /opsx:apply after /opsx:continue completes all artifacts. They keep running /opsx:continue repeatedly, getting stuck in a loop. Adding explicit command hints helps them understand the next step.

The Skill templates (openspec-xxx, returning SkillTemplate) remain agent-agnostic with no command references - I didn't touch those.

- STOP
---
Expand Down Expand Up @@ -1951,7 +1951,7 @@ Working on task 4/7: <task description>
- [x] Task 2
...
All tasks complete! Ready to archive this change.
All tasks complete! You can archive this change with \`/opsx:archive\`.
\`\`\`
**Output On Pause (Issue Encountered)**
Expand Down