artifacts/bundle/skills/engineering/changelog-generator/SKILL.md
# Changelog Generator **Tier:** POWERFUL **Category:** Engineering **Domain:** Release Management / Documentation ## Overview Use this skill to produce consistent, auditable release notes from Conventional Commits. It separates commit parsing, semantic bump logic, and changelog rendering so teams can automate releases without losing editorial control. ## Core Capabilities - Parse commit messages using Conventional Commit rules - Detect semantic bump (`major`, `minor`, `patch`) from comm
npx skillsauth add neekware/ehayeskills artifacts/bundle/skills/engineering/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.
Tier: POWERFUL
Category: Engineering
Domain: Release Management / Documentation
Use this skill to produce consistent, auditable release notes from Conventional Commits. It separates commit parsing, semantic bump logic, and changelog rendering so teams can automate releases without losing editorial control.
major, minor, patch) from commit streamAdded, Changed, Fixed, etc.)python3 scripts/generate_changelog.py \
--from-tag v1.3.0 \
--to-tag v1.4.0 \
--next-version v1.4.0 \
--format markdown
git log v1.3.0..v1.4.0 --pretty=format:'%s' | \
python3 scripts/generate_changelog.py --next-version v1.4.0 --format markdown
python3 scripts/generate_changelog.py --input commits.txt --next-version v1.4.0 --format json
CHANGELOG.mdpython3 scripts/generate_changelog.py \
--from-tag v1.3.0 \
--to-tag HEAD \
--next-version v1.4.0 \
--write CHANGELOG.md
python3 scripts/commit_linter.py --from-ref origin/main --to-ref HEAD --strict --format text
Or file/stdin:
python3 scripts/commit_linter.py --input commits.txt --strict
cat commits.txt | python3 scripts/commit_linter.py --format json
Supported types:
feat, fix, perf, refactor, docs, test, build, ci, choresecurity, deprecated, removeBreaking changes:
type(scope)!: summaryBREAKING CHANGE:SemVer mapping:
majorfeat -> minorpatchpython3 scripts/generate_changelog.py --help
--inputpython3 scripts/commit_linter.py --help
--strict mode on violationsfeat(api): ...) in multi-package repos.[Unreleased] section for manual curation when needed.Use this release flow for predictability:
Security section.commit_linter.py --strict on all PRs.CHANGELOG.md on main branch.Creator: Engineering License: MIT Source Repo:
neekware/ehaye-skillsSource Bucket:engineeringOriginal Path:engineering/changelog-generator
tools
# ehAye Multimedia Use this skill for **video, audio, images, media conversion, previews, transcription, thumbnails, frame extraction, Spotter visual search, or FFmpeg-backed processing**. Core rule: use ehAye native media tools first. Do not reach first for shell `ffmpeg`, `ffprobe`, Python, or `mediainfo` when a native media tool can do the job. Native tools use bundled engines, show proper tool UI, respect cancellation/timeouts, integrate with Preview/Spotter, and avoid cross-platform shell
development
Test-driven development skill for writing unit tests, generating test fixtures and mocks, analyzing coverage gaps, and guiding red-green-refactor workflows across Jest, Pytest, JUnit, Vitest, and Mocha. Use when the user asks to write tests, improve test coverage, practice TDD, generate mocks or stubs, or mentions testing frameworks like Jest, pytest, or JUnit. Handles test generation from source code, coverage report parsing (LCOV/JSON/XML), quality scoring, and framework conversion for TypeScript, JavaScript, Python, and Java projects.
tools
Help a user set up Telegram for ehAye Dojo. Default to Personal private bots (recommended). Group setup is advanced for teams/observers/demos.
development
# Writing Skills ## Overview **Writing skills IS Test-Driven Development applied to process documentation.** **Personal skills live in agent-specific directories (`~/.claude/skills` for Claude Code, `~/.agents/skills/` for Codex)** You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes). **Core principle:** If you didn't watch an agent fail without the ski