skills/changelog-generator/SKILL.md
Analyzes commit history, PR descriptions, and spec changes to automatically generate developer-friendly API changelogs.
npx skillsauth add fatih-developer/fth-skills changelog-generatorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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.
Parse the provided text (Git commits, PR bodies, or OpenAPI diffs) and filter out internal noise.
Organize the update into established categories:
breaking-change-detector).Required Outputs (Must write BOTH to docs/api-report/):
docs/api-report/api-changelog.md)# 🌍 API Changelog
## [v1.4.0] - 2024-03-24
### 🚀 Features
- **[Orders]** Added new `POST /v1/orders/{id}/cancel` endpoint. You can now cancel orders within 30 minutes of creation.
- **[Users]** The `GET /v1/users/me` endpoint now includes a `last_login_at` timestamp.
### 🛠️ Fixes
- **[Payments]** Fixed an issue where `GET /v1/payments` would return a 500 error if the user had no payment methods. It now correctly returns an empty array `[]`.
### ⚠️ Deprecations
- **[Products]** The `category_id` field in the `/products` response is deprecated. Please use the new `categories` array instead. `category_id` will be removed in v2.0.0.
docs/api-report/api-changelog-output.json){
"skill": "changelog-generator",
"version": "1.4.0",
"date": "2024-03-24",
"changes": {
"features": ["POST /v1/orders/{id}/cancel added", "last_login_at added to GET /v1/users/me"],
"fixes": ["GET /v1/payments empty state fix"],
"deprecations": ["category_id in /products response"]
},
"breaking_changes": []
}
tools
Create, optimize, critique, and programmatically structure prompts for AI systems. Use this skill whenever the user is designing or improving a static prompt, system prompt, coding prompt, agent prompt, workflow prompt, MCP-oriented prompt package, or an algorithmic prompt optimization pipeline. Also use it when the user asks to turn vague AI behavior into a precise instruction set, tool policy, agent spec, evaluation metric, or prompt architecture.
testing
Assumption-first architecture review skill to stress-test project plans and expose hidden risks.
testing
Enforce and manage DESIGN.md specifications, extract design systems from URLs, and combine design reasoning with token roles to prevent drift.
testing
Forces the agent to act with a Claude-like product mindset, prioritizing user journey, UX states, and visual quality before coding.