changelog-generator
Changelog Generator Protocol
This skill bridges the gap between raw git history and consumer-facing API updates. Consumers don't care about "Refactored user service;" they care about "The /users endpoint now returns a profile_pic URL."
Core assumption: A changelog is a communication tool, not a git dump. It must focus on the API interface, not internal implementation tweaks.
1. Input Analysis (Static)
Parse the provided text (Git commits, PR bodies, or OpenAPI diffs) and filter out internal noise.
- Keep: Added fields, new endpoints, deprecated endpoints, bug fixes that changed API behavior.
- Discard: Dependency updates, CI/CD tweaks, internal refactoring (unless it drastically improved performance).
2. Categorization & Formatting
Organize the update into established categories:
- 🚀 Features: New capabilities for the consumer.
- 🛠️ Fixes: Resolved behavior issues.
- ⚠️ Deprecations: Warnings about endpoints/fields being sunset.
- 🚨 BREAKING CHANGES: Red-alert items requiring consumer code updates. (Cross-reference findings with
breaking-change-detector).
More from fatih-developer/fth-skills
task-decomposer
Break down large, complex, or ambiguous tasks into independent subtasks with dependency maps, execution order, and success criteria. Plan first, then execute step by step. Triggers on 'how should I do this', 'where do I start', 'plan the project', 'break it down', 'implement' or whenever a task involves multiple phases.
24multi-brain-debate
Two-round debate protocol where perspectives challenge each other before consensus. Round 1 presents independent positions, Round 2 allows counter-arguments and rebuttals. Produces battle-tested decisions for high-stakes choices.
20context-compressor
Compress long conversation histories, large code files, research results, and documents by 70% without losing critical information. Triggers when context window fills up, when summarizing previous steps in multi-step tasks, before loading large files into context, or on 'summarize', 'compress', 'reduce context', 'save tokens'.
18multi-brain-score
Confidence scoring overlay for multi-brain decisions. Each perspective rates its own confidence (1-10) with justification. Consensus uses scores as weights, flags low-confidence areas, and surfaces uncertainty explicitly.
16checkpoint-guardian
Automatic risk assessment before every critical action in agentic workflows. Detects irreversible operations (file deletion, database writes, deployments, payments), classifies risk level, and requires confirmation before proceeding. Triggers on destructive keywords like deploy, delete, send, publish, update database, process payment.
14multi-brain
Evaluate complex requests from 3 independent perspectives (Creative, Pragmatic, Comprehensive), reach consensus, then produce complete outputs. Use for architecture decisions, creative content, analysis, and any task where multiple valid approaches exist.
14