Proc changelog

Skill barcelosvinicius/basic-engineering/plugins/be/skills/proc-changelog

Claude Code plugin + npm base for AI-assisted engineering: 25 skills, 12 agents, slash commands, session-continuity hook. Also works with Copilot, Cursor, and others.

Install

npx -y skills add barcelosvinicius/basic-engineering --skill proc-changelog

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when preparing a release, creating release notes, generating user-facing updates, or closing a sprint with deliverables. Maintains CHANGELOG.md from Conventional Commits following Keep a Changelog + SemVer.

SKILL.md

4.3 KB, as published. Nobody here has run it

Skill: Changelog Generation

What this skill is

Defines the process for maintaining CHANGELOG.md following the Keep a Changelog standard with Conventional Commits. Use when preparing releases, creating release notes, or documenting changes for users.

CHANGELOG.md format

# Changelog

All notable changes to this project are documented here.
Format: [Keep a Changelog](https://keepachangelog.com/en/1.1.0/)
Versioning: [Semantic Versioning](https://semver.org/)

## [Unreleased]

### Added
- New features not yet in production

---

## [1.2.0] — 2026-04-15

### Added
- RF-25: Nubank CSV import with duplicate detection
- RF-26: File type validation using magic bytes

### Changed
- Dashboard now highlights the emergency reserve
- /api/v1/transactions endpoint performance improved (index added)

### Fixed
- Bug #47: commitment showed NaN when income was zero
- Timeout on CSV imports with more than 500 lines

### Security
- JJWT update 0.12.3 → 0.12.6 (CVE-2024-XXXX)

---

## [1.1.0] — 2026-03-01
...

Conventional Commits → sections mapping

Commit type	Changelog section	Include?
`feat:`	Added	✅ Always
`fix:`	Fixed	✅ Always
`perf:`	Changed	✅ Always
`refactor:`	Changed	⚠️ If it affects observable behavior
`security:` or `fix(security):`	Security	✅ Always
`docs:`	—	❌ Do not include
`test:`	—	❌ Do not include
`chore:`	—	❌ Do not include (except deps)
`chore(deps):` or Dependabot	Security	✅ If a CVE was fixed
`ci:`	—	❌ Do not include

How to generate changelog from git commits

# View commits since the last tag
git log v1.1.0..HEAD --oneline --no-merges

# More detailed format
git log v1.1.0..HEAD \
  --pretty=format:"- %s (%h)" \
  --no-merges \
  | grep -E "^- (feat|fix|perf|refactor|security)"

# View all existing tags
git tag --sort=-version:refname | head -10

Release process — step by step

1. Create section [x.y.z] above [Unreleased]
   └── Move items from [Unreleased] to the new section

2. Filter: include only feat, fix, perf, security
   └── Translate into user-facing language (not technical)

3. Sort within each section: impact → stability → security
   └── Most impactful to the user comes first

4. Review: each line must answer "what can the user do now?"
   └── ❌ "refactors TransactionService to use Strategy pattern"
   └── ✅ "Transaction categorization is now 30% faster"

5. Commit together with the release code
   └── git commit -m "chore(release): v1.2.0 — changelog and version bump"

Semantic versioning (SemVer)

MAJOR.MINOR.PATCH

MAJOR: breaks compatibility (e.g.: endpoint change, API field removal)
MINOR: new feature without breaking changes (e.g.: new endpoint, new report)
PATCH: bug or vulnerability fix without a new feature

For projects in active development (before stable production):

Use 0.x.y — MINOR for features, PATCH for fixes
Promote to 1.0.0 on the first stable production deploy

User-oriented writing

❌ Technical (do not include in the public changelog):
"Adds composite index (date, user_id) to the transactions table"
"Refactors GlobalExceptionHandler to use ProblemDetail"

✅ User-oriented:
"Transaction history now loads up to 3x faster"
"Error messages now indicate the specific field with a problem"

Common mistakes

Mistake	Cause	Solution
Outdated changelog	Not updated at merge time	Update `[Unreleased]` in every feat/fix PR
Too technical items	Copying commits without filtering	Filter to feat, fix, perf, security and translate
Versions without date	Release date not recorded	Always include the date in YYYY-MM-DD format
Duplicate version	Numbering error	Check git tags before creating a new section

Reference: Keep a Changelog · SemVer

Gives 0 of the 12 instructions most readme changelog skills give

Counted across 471 of the 478 authors here whose files we hold, read 2026-08-06

follow the Keep a Changelog formatin 31 of 471, across 26 files
omit empty sectionsin 21 of 471
Run from the git repository rootin 20 of 471, across 7 files
save output directly to CHANGELOG.mdin 20 of 471, across 7 files
Group commits into logical categoriesin 19 of 471, across 6 files
Review the generated changelog before publishingin 19 of 471, across 6 files
Apply changelog guidelines and brand voicein 18 of 471, across 5 files
Exclude internal commits like refactoring and testsin 18 of 471, across 5 files
Specify date ranges for focused changelogsin 17 of 471, across 4 files
Convert technical commits into customer languagein 17 of 471, across 4 files
group commits by conventional commit typein 14 of 471
insert new entry below unreleased sectionin 14 of 471

Said here and by no other author read

move unreleased items to a new version section
include only feat, fix, perf, or security commits
translate changes into user-facing language
sort items by impact, stability, then security
verify each line answers what the user can do
bump major versions for breaking changes

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.