AI-powered changelog automation system with security #1
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Claude Sonnet 4.5 integration for natural language generation - Multi-language support (English, Chinese, Korean) - Semantic versioning with AI analysis (Major/Minor/Patch) - Context-aware changelog formatting - Weekly automated changelog generation (Every Wednesday) - PR creation to mintlify-docs repository - Configurable schedule and triggers - Complete CI/CD integration - 34 pre-generated versions for 2025 (v3.3.0 β v4.3.0) - Week-by-week PR data collection - Cumulative changelog architecture - Version mapping and tracking - Pre-execution skill validation - Tool restriction (SAFE/MODERATE/HIGH-RISK/BLOCKED) - Sensitive data protection (API keys, tokens) - Command injection prevention - Network access control with domain whitelist - Automated security scanning - Malicious skill detection and quarantine - 12 core Codatta repositories monitored - Flexible configuration (core-only, default, all) - Multi-repo PR aggregation - Configurable lookback period - `scripts/` - 5 core Python scripts for generation - `config/` - Repository and version configuration - `data/` - Historical PR data and changelog cache - `.github/` - GitHub Actions workflows and setup guides - `skills/` - Agent skills with security validation - `docs/` - Comprehensive English documentation - Multi-layer skill validation system - API key theft prevention - Command injection detection - Data exfiltration blocking - Automated security scanning tools - Incident response procedures - 5 active Python scripts (1,554 lines) - 2 GitHub Actions workflows - 6 core documentation files - 34 historical versions (2025) - 12 monitored repositories - 3 languages supported - `validate_skill.py` - Single skill security validator - `scan_skills_security.py` - Batch security scanner - `generate_weekly_changelog.py` - Main automation script - `fetch_github_prs.py` - PR data collector - `preview_2025_aligned.py` - Version preview tool All documentation in English: - README.md - Project overview - AUTOMATION_COMPLETE.md - Setup completion guide - scripts/README.md - Script usage documentation - config/README.md - Configuration guide - skills/SECURITY.md - Security guidelines - skills/SECURITY_QUICKSTART.md - 5-min security setup - Code structure optimized (67% reduction in scripts) - All documentation in English - Security validated on existing skills - Tested with real Codatta repositories - Production-ready automation Integrates with: - Codatta GitHub organization (12 repos) - mintlify-docs (changelog.mdx updates) - Anthropic Claude API (changelog generation) - GitHub API (PR data fetching) Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
- Changed repository count from 12 to 22 (accurate) - Modified generate_weekly_changelog.py to generate 3 languages: EN, ZH, KO - Each language gets its own cumulative file (changelog_EN/ZH/KO.mdx) - Updated README.md and PR_TEMPLATE.md to reflect changes - All three changelogs grow cumulatively with each weekly run
- Workflow now automatically creates PR after generating changelogs - PR includes all 3 language files (EN, ZH, KO) - Detailed PR description with version info and next steps - Uploads artifacts with 90-day retention - Updated SETUP.md with PR creation documentation
- Visual flowchart of entire weekly automation process - Step-by-step breakdown from trigger to PR creation - Key features, configuration, and metrics - Error handling and human touch points
- Detailed breakdown of Claude API costs - Monthly cost: $0.32 (yearly: $4.20) - Scenario analysis for different PR volumes - Cost optimization strategies - ROI analysis: 1,250x return (99.92% savings vs manual) - Infrastructure costs (GitHub Actions, storage)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
π― Overview
This PR introduces a complete AI-powered multi-language changelog generation system with automated weekly runs and comprehensive security validation for AIOK skills.
β¨ Key Features
1. AI-Powered Changelog Generation
2. Automated Weekly Runs
--forceoverride3. Security System (5 Layers)
validate_skill.py+scan_skills_security.pyπ File Structure
Core Scripts (5 Active)
scripts/fetch_github_prs.py- Fetches merged PRs from 22 repositoriesscripts/generate_weekly_changelog.py- Main weekly automation (cumulative)scripts/generate_mintlify_changelog_v2.py- AI generation enginescripts/validate_skill.py- Single skill security validatorscripts/scan_skills_security.py- Batch security scannerConfiguration
config/repos.json- 22 monitored repositoriesconfig/2025_version_mapping.json- Historical version data (33 versions)skills/security/config.json- Security rules and patternsDocumentation
scripts/README.md- Complete script usage guideskills/SECURITY.md- Comprehensive security system documentationskills/SECURITY_QUICKSTART.md- 5-minute security setupGitHub Actions
.github/workflows/weekly-changelog.yml- Weekly automation workflow.github/SETUP.md- GitHub Actions configuration guideπ Usage
Quick Start
GitHub Actions Setup
ANTHROPIC_API_KEY,GITHUB_TOKENπ Security Highlights
Detected Patterns:
$ANTHROPIC_API_KEY,$TOKEN,os.environ&&,||,;,$(...), backtickseval(),exec(),__import__()Tool Categories:
π Impact
Code Optimization
scripts/archived/Changelog Data
π§ͺ Testing
All scripts tested:
π Related Documentation
βοΈ Configuration Required
After merging, configure these GitHub secrets:
ANTHROPIC_API_KEY- For Claude Sonnet 4.5 API accessGITHUB_TOKEN- For PR fetching and automation (auto-provided or custom)π― Next Steps
Co-Authored-By: Claude Sonnet 4.5 noreply@anthropic.com