Automate code fixes using Claude Code or OpenAI Codex. Engineers benefit by reducing manual debugging. Works by scanning codebase for comments like '// @ai fix this code' and running the AI agent in the background until the code passes lint/build checks.
git clone https://github.com/joseferben/hands-please.gitThe hands-please skill enables users to run Claude Code or OpenAI Codex in the background, streamlining the coding process and enhancing productivity. By automating background tasks, this skill allows developers to focus on more complex issues without being bogged down by repetitive coding tasks. This intermediate-level skill can be implemented in approximately 30 minutes, making it a practical addition to any developer's toolkit. One of the key benefits of the hands-please skill is its potential to save time, although specific time savings are not quantified. By automating code execution in the background, developers can significantly reduce the time spent on mundane tasks, allowing them to allocate more resources to innovation and problem-solving. This skill is particularly valuable for developers and product managers who are looking to optimize their workflow automation processes and enhance their productivity. The hands-please skill is ideal for developers and AI practitioners who are comfortable with intermediate-level coding. It fits seamlessly into AI-first workflows, where the integration of automation can lead to more efficient project management and execution. For instance, a developer working on a large-scale application can utilize this skill to run tests or compile code while simultaneously focusing on new feature development. Implementing hands-please requires a basic understanding of Claude Code and OpenAI Codex, as well as familiarity with coding environments. While the skill has not yet achieved verified status and has a modest number of GitHub stars, its medium GTM relevance suggests it holds promise for those looking to enhance their AI agent skills. Overall, hands-please is a valuable addition to any developer's arsenal, promoting efficiency and allowing for a more streamlined approach to coding.
["1. **Set Up Triggers**: Add `// @ai fix this code` comments to problematic code sections in your repository. Include these in files you want the AI to analyze (e.g., `src/**/*.js`).","2. **Configure Environment**: Ensure your environment has access to the AI tool (Claude Code or OpenAI Codex) and required dependencies (e.g., Node.js, linters). Set up environment variables for API keys if needed.","3. **Run Automation**: Execute the automation script with your custom paths and commands. Example for a Node.js project: `npx ai-code-fixer --codebase ./src --test \"npm test\" --lint \"npm run lint\" --changelog ./CHANGELOG.md`.","4. **Verify Output**: Review the generated fixes in the console or output file. Check the CI/CD pipeline to ensure no new errors were introduced.","5. **Commit Changes**: After validation, commit the fixes to your repository. Include the changelog entry in your commit message for traceability."]
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/joseferben/hands-pleaseCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Scan the [CODEBASE_PATH] repository for all instances of '// @ai fix this code' comments. For each instance, use Claude Code or OpenAI Codex to automatically generate and apply code fixes that resolve lint/build errors. Verify fixes by running [TEST_COMMAND] until all checks pass. Document each change in [CHANGELOG_FILE] with the original issue, applied fix, and verification results.
## Code Fix Automation Report
Generated on: 2023-11-15
Repository: acme-web-app (main branch)
AI Tool: Claude Code v1.2.3
### Issues Detected & Fixed
**1. File: src/api/handlers/userController.js (Line 42)**
- **Issue:** `// @ai fix this code` comment found. Lint error: 'no-unused-vars' for variable 'tempUser'.
- **Fix Applied:** Removed unused variable declaration.
```diff
- const tempUser = await User.findById(userId);
+ const user = await User.findById(userId);
```
- **Verification:** ESLint passed. Build successful. All tests green (12/12).
**2. File: tests/integration/auth.test.js (Line 89)**
- **Issue:** `// @ai fix this code` comment found. Build error: 'Cannot find module @/utils/auth'.
- **Fix Applied:** Updated import path to resolve module alias.
```diff
- import { verifyToken } from '@/utils/auth';
+ import { verifyToken } from '../../src/utils/auth';
```
- **Verification:** Build successful. Jest tests passed (23/23). Coverage: 92%.
**3. File: config/database.js (Line 112)**
- **Issue:** `// @ai fix this code` comment found. Lint error: 'no-console' for debug log.
- **Fix Applied:** Removed console.log statement.
```diff
- console.log('Connecting to DB...');
```
- **Verification:** ESLint passed. MongoDB connection established successfully.
### Summary
- **Total Issues Fixed:** 3
- **Automation Success Rate:** 100%
- **Manual Review Required:** 0
- **Time Saved:** ~45 minutes (estimated manual fix time)
### Change Log Entry
```
[2023-11-15] Automated Code Fixes
- Fixed lint/build errors in userController.js, auth.test.js, and database.js
- Applied changes via AI agent (Claude Code)
- Verified all fixes with tests and linting
```
**Next Steps:**
1. Review the automated changes in the PR: #421
2. Merge changes after team approval
3. Monitor CI pipeline for any regressionsPioneering accessible, high-performance AI models
AI assistant built for thoughtful, nuanced conversation
Metagenomic analysis for microbiome research
AI sales agent for lead generation and follow-up
AI-assisted web application security testing
Connected workspace for docs, wikis, and projects
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan