Agent skill
stitch-mcp-delete-project
Permanently deletes a Stitch project and all its screens. Destructive — requires explicit user confirmation before calling.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/stitch-mcp-delete-project
SKILL.md
Stitch MCP — Delete Project
Permanently deletes a Stitch project and all its screens, designs, and history. This action is irreversible.
Critical prerequisite
Only use this skill when the user explicitly mentions "Stitch".
This is a destructive action. You MUST ask the user to confirm before calling delete_project. Never auto-delete.
When to use
- User explicitly asks to delete a Stitch project
- Cleaning up test/scratch projects after confirming with the user
- The orchestrator offers project cleanup and the user accepts
Step 1: Confirm the project
Show the user what they're about to delete:
- Call
stitch-mcp-get-projectwithprojects/[ID]to get the project title and screen count - Present: "You're about to permanently delete [title] ([N] screens). This cannot be undone. Proceed?"
- Only continue if the user explicitly confirms
Step 2: Call the MCP tool
{
"name": "delete_project",
"arguments": {
"name": "projects/3780309359108792857"
}
}
name — full path with projects/ prefix
✅ "projects/3780309359108792857"
❌ "3780309359108792857"
This follows the same format as get_project — both use projects/ID.
After deleting
- Confirm: "Project [title] has been deleted."
- Offer: "Want to see your remaining projects?" →
stitch-mcp-list-projects - Do NOT attempt to access the deleted project's screens or data
Anti-patterns
- Never delete without explicit user confirmation — even if the orchestrator suggests cleanup
- Never delete multiple projects in a batch without confirming each one
- Never use numeric ID —
delete_projectrequires the fullprojects/IDpath
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?