patch-notes
Skill40 starsChanged 7 months agoMITView on GitHub
Generate user-facing patch notes from git history, sprint data, and the internal changelog. Translates engineering language into clear, store-appropriate user communication. Respects App Store / Play Store character limits.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- striderZA/OpenCodeGameStudiostheir own version, first seen Nov 4, 2026
- Donchitos/Claude-Code-Game-Studiostheir own version, first seen Oct 19, 2026
- venus2099/codex-game-studiostheir own version, first seen Oct 17, 2026
- scotidev/GameDevStudiotheir own version, first seen Oct 9, 2026
- HunLuanZhiZhu/Game-Studios-Plugintheir own version, first seen Oct 5, 2026
- dawn840705/claude-code-studiostheir own version, first seen Aug 28, 2026
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- pixel-cellar/Claude-Code-Game-Studios★ 324same name
- striderZA/OpenCodeGameStudios★ 118same name
- CoralGame/Claude-Code-Game-Studios★ 19same name
- dawn840705/codex-code-studios★ 17same name
- CodePhobiia/claude-roblox-game-studio★ 9same name
- lilangMax/ClaudeCodeGameStudios★ 8same name
- hongyuanc/codex-game-studios★ 5same name
- dawn840705/claude-code-studios★ 1same name
- HunLuanZhiZhu/Game-Studios-Plugin★ 1same name
2 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository77 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- design/CLAUDE.mdCLAUDE.md
- docs/CLAUDE.mdCLAUDE.md
- src/CLAUDE.mdCLAUDE.md
- tests/CLAUDE.mdCLAUDE.md
- adoptSkill
- architecture-decisionSkill
- architecture-reviewSkill
- asset-auditSkill
- asset-specSkill
- balance-checkSkill
- brainstormSkill
- bug-reportSkill
- bug-triageSkill
- changelogSkill
- code-reviewSkill
- consistency-checkSkill
- content-auditSkill
- create-architectureSkill
- create-control-manifestSkill
- create-epicsSkill
- create-storiesSkill
- day-one-patchSkill
- design-bibleSkill
- design-reviewSkill
- design-systemSkill
- dev-storySkill
- estimateSkill
- extractSkill
- gate-checkSkill
- helpSkill
- hotfixSkill
- launch-checklistSkill
- localizeSkill
- map-systemsSkill
- milestone-reviewSkill
- onboardSkill
- perf-profileSkill
- prd-reviewSkill
- project-stage-detectSkill
- propagate-design-changeSkill
- prototypeSkill
- qa-planSkill
- quick-designSkill
- regression-suiteSkill
- release-checklistSkill
- retrospectiveSkill
- reverse-documentSkill
- review-all-prdsSkill
- scope-checkSkill
- security-auditSkill
- setup-frameworkSkill
- skill-improveSkill
- skill-testSkill
- smoke-checkSkill
- soak-testSkill
- sprint-planSkill
- sprint-statusSkill
- startSkill
- story-doneSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
9
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 26
If no internal changelog exists, read git log for the version window and any associated story / bug records.
- Distinctive: line 53
Keep Features, Improvements, Fixes, Security in user-friendly form.
- Distinctive: line 62
Avoid passive voice unless required by tone.
- Distinctive: line 63
Avoid "we fixed a bug where..." — be specific.
- Distinctive: line 65
Keep entries punchy — one line per change unless context truly helps.
- Distinctive: line 128
If target locales include non-English markets:
- Distinctive: line 131
Write source files to:
- Distinctive: line 150
Ask before each write:
- Distinctive: line 156
If localized files were generated, ask per locale.
“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Patch Notes
A focused twin of /changelog. Produces only the user-facing,
store-ready patch notes for a release. Haiku tier — this is formatting
and rewording, not synthesis.
Phase 1: Locate Inputs
Parse --version=<v>. Default: most recent unreleased tag.
Read in parallel:
production/releases/changelog-internal-[version].md(preferred source).- If no internal changelog exists, read git log for the version window and any associated story / bug records.
.claude/docs/technical-preferences.mdfor target locales.
Phase 2: Pick the Tone
Parse --tone. If not given, propose options via AskUserQuestion:
warm— friendly, first-person plural ("We've added...").neutral— direct, third-person ("[App] now supports Apple Pay").formal— precise, legal-friendly ("Version [N] introduces support for Apple Pay").
Default: warm.
Apply the tone to every line consistently. Mixing tones is a smell.
Phase 3: Distill the Internal Changelog
For each entry in the internal source:
- Drop Internal / Refactor / Reverted entries unless user-visible.
- Drop test-only changes.
- Keep Features, Improvements, Fixes, Security in user-friendly form.
Apply rewriting rules:
- Replace developer terms with user terms: "reducer" -> drop; "background fetch" -> "while the app is closed"; "Hermes upgrade" -> "faster startup".
- Lead with user benefit: "Cold start improvements" -> "App opens faster".
- Avoid passive voice unless required by tone.
- Avoid "we fixed a bug where..." — be specific. "Sign-in no longer fails when switching from Wi-Fi to cellular."
- Keep entries punchy — one line per change unless context truly helps.
Phase 4: Compose Long Form
# What's New in [App] [version]
## New
- [bullet]
## Improvements
- [bullet]
## Fixes
- [bullet]
## Notes
[1-3 lines of plain language about anything users should know — new
permission, etc. Optional.]
Thanks for using [App]. Got feedback? [contact].Show the result. Ask for tone adjustment if needed.
Phase 5: Compose Short Form (Store-Specific)
App Store What's New (4000 chars)
Allowed to be the long-form essentially. Trim if over 4000 chars.
Play Store What's New (500 chars)
This is the hard one. Strategy:
- Lead with the headline feature in one sentence.
- Mention up to two other notable changes in one sentence.
- Mention "stability and bug fixes" if there are fixes but they don't need names.
- Stop.
Aim for 300-450 chars to leave room for localized expansion (some languages run longer).
Example:
We've added Apple Pay at checkout and a dark mode for the home feed.
The app now opens faster and scrolls more smoothly. Plus stability
fixes including a more reliable sign-in.Render character count alongside.
Phase 6: Localization
If target locales include non-English markets:
- Tag the long-form and short-form English strings as the source.
- Write source files to:
production/releases/whats-new-[version]-en-app-store.mdproduction/releases/whats-new-[version]-en-play-store.md
- For each target locale, check whether:
- A translation vendor pipeline is configured -> tag as
# UNTRANSLATED — for vendor. - The previous release used machine translation -> propose same approach.
- The team translates manually -> tag for localization-lead review.
- A translation vendor pipeline is configured -> tag as
For Play Store, remind the user: each locale has its own 500-char limit, and verbose translations may overflow. Generate per-locale guidance: "Spanish typically runs 110-115% of English length — consider a tighter source string."
Phase 7: Save
Ask before each write:
production/releases/whats-new-[version]-en-long.mdproduction/releases/whats-new-[version]-en-app-store.mdproduction/releases/whats-new-[version]-en-play-store.md
If localized files were generated, ask per locale.
Phase 8: Update State
Append to production/session-state/active.md:
## Patch Notes — [date]
- Version: [version]
- Tone: [tone]
- Long form: [path]
- App Store: [path] ([N] chars)
- Play Store: [path] ([N] chars)
- Locales pending: [list]
- Next: localization handoff or paste into store consolesQuality Gates / PASS-FAIL
- PASS — long form covers every user-visible change; short form fits within store limits with margin; tone is consistent; no engineering jargon leaked through.
- FAIL — short form over limit, internal jargon present ("reducer", "Hermes", "race condition" without user phrasing), or any reference to internal IDs (BUG-NN, STORY-NN).
Examples
Example 1 — v1.3.0 with three features and two fixes: Long form: 6 bullets across New / Improvements / Fixes. App Store: fits. Play Store: 412 chars. Tone warm. 3 locales tagged for translation.
Example 2 — v1.2.1 hotfix: Single bullet: "Fixed an issue that could cause sign-in to fail when switching networks." Long form 1 line, App Store 1 line, Play Store 86 chars.
Next Steps
- Paste short form into App Store Connect / Play Console.
- For locales, run vendor pipeline.
- Refer to
/release-checklistto confirm metadata is uploaded.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

