changelog-md-workmanship

Rebuild CHANGELOG.md files from git history, tags, releases, and issue trackers.

3|1|Updated Apr 15, 2026
One-click install
npx skills add https://github.com/burningportra/agent-flywheel-plugin --skill changelog-md-workmanship-burningportra
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: changelog-md-workmanship
Source: https://github.com/burningportra/agent-flywheel-plugin/tree/main/skills/changelog-md-workmanship
Command: npx skills add https://github.com/burningportra/agent-flywheel-plugin --skill changelog-md-workmanship-burningportra

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve? Most changelogs are either vague summaries written from memory or unreadable commit dumps. This Skill turns changelog writing into an evidence-driven research process, producing an agent-friendly historical record grounded in real git history, release metadata, and issue tracker data. ## Core Features & Use Cases - Evidence-first research workflow: Builds a version spine from git tags and GitHub Releases, distinguishes releases from plain tags, and mines issue trackers (beads, GitHub Issues, Linear, Jira, milestone docs) for intent. - Chunked reconstruction for large histories: Splits long histories into bounded slices with a durable research memo and coverage ledger, updating CHANGELOG.md incrementally after each chunk. - Automation scripts and templates: Includes scripts to bootstrap the workspace, build a version timeline, extract tracker workstreams, cluster commits into capability waves, and validate the finished changelog, plus copy-paste markdown templates. - Use Case: Point it at a multi-year repository and ask for a full-history CHANGELOG.md; it researches tags, releases, commits, and tracker items chunk by chunk, then produces a version timeline plus thematic capability sections with live commit links. ## Quick Start Ask the AI to rebuild this repository's CHANGELOG.md from the full git history, tags, releases, and issue tracker, using chunked research if the history is large.

Frequently Asked Questions about changelog-md-workmanship

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I rebuild a CHANGELOG.md from git history?

Start by building a version spine from git tags and GitHub Releases, then research commit history in bounded chunks and distill each chunk into the changelog immediately. The skill's bootstrap script creates the CHANGELOG.md skeleton and research memo, and build-version-spine.py generates the timeline.

How to write a changelog for a large repository with years of history?

Use chunked reconstruction: split history by tag range, date window, or 50-150 commit slices, maintain a coverage ledger in a research memo, and update CHANGELOG.md after each chunk. The ULTRA-LARGE-REPOS reference and --huge bootstrap mode scaffold this multi-pass workflow.

What is the difference between a git tag and a GitHub Release in a changelog?

A GitHub Release is a published release page with metadata, while a tag is only a git ref. The changelog must link releases to releases/tag pages and tag-only versions to tree pages, and mark draft releases explicitly rather than fabricating release links.

Can I extract issue tracker history from beads, GitHub, Linear, or Jira for a changelog?

Yes. The extract-tracker-workstreams.py script normalizes beads .beads/issues.jsonl files, GitHub Issues via the gh CLI, Linear and Jira JSON exports, and milestone markdown into a common workstream list usable as the intent layer of the changelog.

Why does my changelog read like a raw commit dump?

A commit dump means the synthesis step was skipped. Group commits into capability waves with a short narrative, delivered capability, closed workstreams, and representative commit links; the cluster-history.py script proposes candidate waves from commit subjects.

How do I validate a finished CHANGELOG.md for structural problems?

Run validate-changelog-md.py on the file to check for a scope window, version timeline, representative commits, live commit URLs, and vague filler phrases. Add --verify-links to perform HTTP checks on the markdown links.