Jules
Skill ActiveDelegate coding tasks to Google Jules AI agent for asynchronous execution. Use when user says: 'have Jules fix', 'delegate to Jules', 'send to Jules', 'ask Jules to', 'check Jules sessions', 'pull Jules results', 'jules add tests', 'jules add docs', 'jules review pr'. Handles: bug fixes, documentation, features, tests, refactoring, code reviews. Works with GitHub repos, creates PRs.
To seamlessly delegate coding tasks to an AI agent, automating bug fixes, code reviews, and other development tasks asynchronously on GitHub.
Features
- Delegate coding tasks to Google Jules AI agent
- Asynchronous execution of tasks
- Supports bug fixes, documentation, features, tests, refactoring, and code reviews
- Integrates with GitHub repositories
- Creates pull requests automatically or locally
Use Cases
- Use when user says: 'have Jules fix', 'delegate to Jules', 'send to Jules'
- Use for tasks like 'jules add tests', 'jules add docs', 'jules review pr'
- Delegate complex coding tasks that require AI assistance for asynchronous execution
- Automate the creation and application of code changes via pull requests
Non-Goals
- Directly executing code on the user's machine without Jules
- Interacting with non-GitHub repositories
- Replacing the entire development workflow with AI
- Handling tasks outside of coding and repository management
Workflow
- Set up authentication (CLI login or API key export)
- Configure environment variables and repository context
- Create a task using CLI or API, specifying the prompt and repository
- Monitor task status via CLI or API
- Retrieve and apply results, optionally creating a pull request
Prerequisites
- JULES_API_KEY environment variable
- Access to jules.google.com settings for API key
- GitHub repository connected to Jules or specified via --repo flag
Maintenance
- info:Dependency ManagementThe skill relies on external tools like npm and curl, and Python packages, but lacks explicit version pinning or vulnerability scanning for these dependencies.
Execution
- info:ValidationWhile inputs are generally structured, explicit validation against schemas for CLI arguments and API parameters is not detailed in the source.
- warning:Pinned dependenciesWhile dependencies like npm packages are used, explicit version pinning or lockfiles are not present, and shebangs in scripts are not consistently provided with side-effect headers.
Code Execution
- info:Error HandlingError handling is present, particularly in the API polling loop, but the structure of error reporting (code, message, retryable, hint) is not fully detailed for all potential failure modes.
Errors
- info:Actionable error messagesError messages are provided, but remediation steps are often brief or refer to the web UI, lacking specific guidance for all failure paths.
Protocol
- info:Idempotent retry & timeoutsThe API polling loop includes a timeout and retry logic, but the idempotency of the underlying Jules API operations is not explicitly detailed.
Practical Utility
- info:Edge casesThe skill documentation mentions session states like 'Awaiting User Input' and 'Failed', but lacks detailed descriptions of other potential failure modes and their recovery steps.
Safety
- info:Halt on unexpected stateWhile the skill provides guidance on session states, explicit instructions to halt and report on unexpected pre-states (e.g., dirty Git tree before applying changes) are not machine-readable preconditions.
Installation
First, add the marketplace
/plugin marketplace add sanjay3290/ai-skills/plugin install ai-skills@ai-skillsQuality Score
Trust Signals
Similar Extensions
Github
100Use gh for GitHub issues, PR status, CI/logs, comments, reviews, releases, and API queries.
Lean Ctx
100Context Runtime for AI Agents — 59 MCP tools, 10 read modes, 95+ shell patterns, tree-sitter AST for 18 languages. Compresses LLM context by up to 99%. Use when reading files, running shell commands, searching code, or exploring directories. Auto-installs if not present.
Manus
100Delegate complex, long-running tasks to Manus AI agent for autonomous execution. Use when user says 'use manus', 'delegate to manus', 'send to manus', 'have manus do', 'ask manus', 'check manus sessions', or when tasks require deep web research, market analysis, product comparisons, stock analysis, competitive research, document generation, data analysis, or multi-step workflows that benefit from autonomous agent execution with parallel processing.
Use My Browser
100Use when work depends on the user's live browser session or visible rendered state rather than static fetches, especially for browser debugging contexts or DevTools-selected elements or requests, logged-in dashboards or CMS flows, localhost apps, forms, uploads, downloads, media inspection, DOM or iframe inspection, Shadow DOM, or browser failures that look like soft 404s, auth walls, anti-bot checks, or rate limits.
Openclaw Testing
100Choose, run, rerun, or debug OpenClaw tests, CI checks, Docker E2E lanes, release validation, and the cheapest safe verification path.
ClawSweeper Skill
100Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, commit-review reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions monitoring, permissions, gates, and manual backfills.