feat(skills): Add write_to_csv skill for data export workflows#25
feat(skills): Add write_to_csv skill for data export workflows#25
Conversation
- Add write_to_csv skill definition to agent.yaml with comprehensive schema - Implement CSV writing functionality with support for: - Custom headers and file paths - Append mode for existing files - Data validation and error handling - Directory auto-creation - Register skill in main.go for A2A server integration - Add comprehensive test suite with 15+ test cases - Include integration demo documentation - Enables end-to-end workflows: navigate → extract_data → write_to_csv Resolves #24 🤖 Generated with [Claude Code](https://claude.ai/code) Co-authored-by: Eden Reich <edenreich@users.noreply.github.com>
|
@claude Prepare this pull request for a review - remove all inline comments (above variables declarations, for loops - whatever that is inside of a function or method body) and ensure new lines at the end of the files you've changed. I already see that file_path should be removed from the skill and should be configurable via environment variables defaulting to /tmp/playwright (please also adjust screenshots to the same default path for consistency). |
|
Claude finished @edenreich's task —— View job Preparing PR for Review ✅Working on preparing this PR for review as requested:
✅ Changes Completed SuccessfullyRefactored file path configuration:
Code cleanup:
Commit: da25618 The PR is now ready for review with the requested changes implemented. |
- Remove file_path parameter from write_to_csv skill schema - Add BROWSER_DATA_FILES_DIR environment variable (default: /tmp/playwright) - Update screenshot directory to use consistent /tmp/playwright default - Change skill to accept filename parameter instead of full file path - Files are automatically saved to configured data directory - Remove inline comments from function bodies - Update tests to work with new signature - All tests passing, lint clean Co-authored-by: Eden Reich <edenreich@users.noreply.github.com>
- Replace separate data_files_dir and screenshots_dir with single data_dir - Update agent.yaml to use single data_dir: "/tmp/playwright" - Update config.go to use DataDir field instead of separate fields - Update write_to_csv and take_screenshot skills to use combined directory - Update all test files to use new configuration structure - All tests passing and linting clean Co-authored-by: Eden Reich <edenreich@users.noreply.github.com>
Signed-off-by: Eden Reich <eden.reich@gmail.com>
…gent URL configuration Signed-off-by: Eden Reich <eden.reich@gmail.com>
…ions Signed-off-by: Eden Reich <eden.reich@gmail.com>
… configuration Signed-off-by: Eden Reich <eden.reich@gmail.com>
## [0.2.0](v0.1.3...v0.2.0) (2025-09-26) ### ✨ Features * **skills:** Add write_to_csv skill for data export workflows ([#25](#25)) ([5b7509f](5b7509f)), closes [#24](#24) ### ♻️ Improvements * Update agent metadata to use agent-card.json and increment ADL CLI version to 0.21.6 ([#33](#33)) ([7d91dde](7d91dde))
|
🎉 This PR is included in version 0.2.0 🎉 The release is available on:
Your semantic-release bot 📦🚀 |
Add new
write_to_csvskill that enables the agent to export extracted data to CSV files, completing data collection workflows.Features
extract_dataskill for end-to-end workflowsExample Workflow
navigate_to_url→ Navigate to target websiteextract_data→ Collect pricing/product datawrite_to_csv→ Export data to structured fileResolves #24
Generated with Claude Code