Use when delegating async coding tasks to Jules AI. Helps create Jules sessions, monitor progress, and integrate results. Use for bug fixes, documentation, tests, or refactoring that can run in the background.
/plugin marketplace add ANcpLua/ancplua-claude-plugins/plugin install jules-integration@ancplua-claude-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Jules is Google's asynchronous AI coding agent. It runs tasks in the background on a cloud VM, clones your repo, and creates PRs with changes.
When to use Jules:
When NOT to use Jules:
export JULES_API_KEY="your-key-here"
curl 'https://jules.googleapis.com/v1alpha/sessions' \
-X POST \
-H "Content-Type: application/json" \
-H "X-Goog-Api-Key: $JULES_API_KEY" \
-d '{
"prompt": "YOUR TASK DESCRIPTION HERE",
"sourceContext": {
"source": "sources/github/OWNER/REPO",
"githubRepoContext": { "startingBranch": "main" }
},
"automationMode": "AUTO_CREATE_PR",
"requirePlanApproval": true
}'
npm install -g @google/jules
jules login
jules remote new --repo . --session "YOUR TASK"
Trigger the jules-review.yml workflow manually with your prompt.
Do:
parseQueryString in utils.js"src/auth/ directory"Don't:
Always use:
requirePlanApproval: true - Review before Jules actsautomationMode: "AUTO_CREATE_PR" - Creates PR, doesn't merge# List your sessions
curl 'https://jules.googleapis.com/v1alpha/sessions' \
-H "X-Goog-Api-Key: $JULES_API_KEY"
# Get session details
curl 'https://jules.googleapis.com/v1alpha/sessions/SESSION_ID' \
-H "X-Goog-Api-Key: $JULES_API_KEY"
# List activities (progress updates)
curl 'https://jules.googleapis.com/v1alpha/sessions/SESSION_ID/activities' \
-H "X-Goog-Api-Key: $JULES_API_KEY"
| Issue | Solution |
|---|---|
| "Source not found" | Connect repo at jules.google first |
| "401 Unauthorized" | Check API key is valid |
| Session stuck | Check jules.google for status; may need feedback |
| Bad PR | Reject plan, provide clearer instructions |
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.