changelog-from-diff

Turn a set of commits or a diff into a clean, user-facing changelog entry. Use before a release or PR description.

Jump to install Review files

Repository: Archive228/loopkit
Last source activity: June 29, 2026 at 21:52
Detected SKILL.md language: English
Stars: 757
Forks: 124

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/Archive228/loopkit/tree/main/skills/changelog-from-diff.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/Archive228/loopkit --skill changelog-from-diff

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

SKILL.md

Source instructions · Read-only preview

name: changelog-from-diff
description: Turn a set of commits or a diff into a clean, user-facing changelog entry. Use before a release or PR description.
when_to_use: cutting a release, writing release notes, summarizing a branch

# Changelog from Diff Read the actual diff/commits, not the commit messages (they lie). Group into: **Added · Changed · Fixed · Removed · Security** (skip empty groups). Each line: user-facing impact, not implementation. "Fixed login failing for emails with uppercase characters" — not "fixed bug in user lookup". - Lead with what the user notices. Bury internals. - Call out breaking changes loudly, with the migration step. - Link the PR/issue. No marketing fluff. Output: markdown ready to paste. If a change has no user impact, leave it out.

View on GitHub

Back to search Back to installation

active-memory-reminder

Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable). Read it alongside claude-progress.txt at session start — prose is for humans, JSON is for the loop.

2026-07-14

model-routing

Split the Plan/Act/Verify loop across three model tiers — frontier planner, cheap executor, frontier judge — via env vars read by run.sh.

2026-07-14

progress-reading-protocol

Run the fixed 6-step session-opening sequence — pwd, read progress, git log, count remaining features, init.sh, smoke-test last feature — before touching any new work. The orientation ritual that lets fresh-context sessions reconstruct project state in under a minute.

2026-07-14

View all from this repository

changelog-from-diff

Source facts

Install options

Install with an AI assistant

Review the source files

More from this repository

Install with an AI assistant

More from this repository