changelog
Skill15 starsChanged 20 days agoApache-2.0View on GitHub
Use when a release is being prepared and the site changelog page needs the new version, after `task release:prepare` regenerated CHANGELOG.md, or when the user asks to update the changelog page, write release notes for the site, or backfill a version on `docs/src/content/docs/changelog.md`. User-facing write-up per release — features by outcome with doc links, not the commit list.
165 other projects use a version of this.
Adopted by
Most recently taken up by
- deg/beads-utilstheir own version, first seen Nov 16, 2026
- raphaeltm/simple-agent-managertheir own version, first seen Nov 15, 2026
- lengrufeng2008/dsh-skill-librarytheir own version, first seen Nov 15, 2026
- Kuan-AI-com/agent-skillstheir own version, first seen Nov 15, 2026
- chuanglibs/Claude-Code-Game-Studios-Codextheir own version, first seen Nov 15, 2026
- rust-works/omni-devtheir own version, first seen Nov 15, 2026
Used with
Projects with it also use playtest-report, soak-test and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
CoralGameSkillplaytest-report
Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.
Also in 12 projects that use this
lilangMaxSkillsoak-test
Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.
Also in 9 projects that use this
lilangMaxSkillteam-live-ops
Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.
Also in 9 projects that use this
CoralGameSkillteam-polish
Orchestrate the polish team: coordinates performance-analyst, technical-artist, sound-designer, and qa-tester to optimize, polish, and harden a feature or area for release quality.
Also in 14 projects that use this
- +5 more from lilangMax
- +3 more from CoralGame
Other versions165 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 165
- meteor/meteor★ 45ksame name
- Donchitos/Claude-Code-Game-Studios★ 39ksame name
- MaaAssistantArknights/MaaAssistantArknights★ 25ksame name
- pipecat-ai/pipecat★ 17ksame name
- elie222/inbox-zero★ 13ksame name
- hashicorp/terraform-provider-aws★ 11ksame name
- JetBrains/ideavim★ 10ksame name
- BuilderIO/agent-native★ 7.7ksame name
- UnigramDev/Unigram★ 5.5ksame name
- entireio/cli★ 5.3ksame name
155 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 repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/research/hooks_vendor_reports/claude.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- code-docs-cleanupSkill
- docs-instrumentSkill
- docs-planSkill
- docs-reviewSkill
- hex-architectSkill
- hex-coreSkill
- hex-discussSkill
- hex-executeSkill
- hex-finalizeSkill
- hex-initSkill
- hex-loopSkill
- hex-planSkill
- hex-retroSkill
- hex-reviewSkill
- nox-reviewSkill
- bugfixSkill
- builderSkill
- code-checkSkill
- code-docs-cleanupSkill
- commitSkill
- docs-instrumentSkill
- docs-planSkill
- docs-reviewSkill
- docsSkill
- finalizeSkill
- hex-architectSkill
- hex-coreSkill
- hex-discussSkill
- hex-executeSkill
- hex-finalizeSkill
- hex-initSkill
- hex-loopSkill
- hex-planSkill
- hex-retroSkill
- hex-reviewSkill
- meta-maintain-configSkill
- meta-validate-contextSkill
- nextSkill
- nox-reviewSkill
- qa-engineerSkill
- security-auditorSkill
- upstream-refreshSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 0 are distinctive, and 7 are very specific to this project.
0
Common
Most of the 154 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 24
Before writing, load the docs skill, .claude/rules/docs-style.md and .claude/rules/product-context.md for voice and link conventions.
- Very specific: line 57
Never let a bullet list follow a feature's body directly — it reads as that feature's sub-items.
- Very specific: line 74
Never derive it from git tags.
- Very specific: line 76
Source: Read that version's section in CHANGELOG.md (git diff CHANGELOG.md right after release:prepare).
- Very specific: line 78
Filter: Keep what a user notices: new commands, flags, clients, config keys, behaviour changes, fixes to visible bugs.
- Very specific: line 92
Gate: Run /docs-review on the page, then python3 .claude/rules/docs-quality/checks/page_type.py docs/src/content/docs/changelog.md and task …
- Very specific: line 95
Hand off: Leave the page changed in the working tree so it lands in the same release: vX.Y.Z commit as CHANGELOG.md and Cargo.toml.
“Common” is measured: kept by at least 6 in 10 of the 154 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
/changelog — Site Changelog for a Release
CHANGELOG.md is git-cliff's commit-level record. The site page
docs/src/content/docs/changelog.md (served at /changelog.html) is the
user-facing one: what a user can do now that they could not before, why it
matters, and which doc page shows how. This skill adds one release to it.
Runs in the release ceremony between task release:prepare and the
release: vX.Y.Z commit (workflow-release.md).
An AI performing a release runs it too — the release is incomplete without it.
Before writing, load the docs skill, .claude/rules/docs-style.md and
.claude/rules/product-context.md for voice and link conventions.
Page contract
Newest first. page_type.py requires every ### inside a version section
to start with a version number, so feature headings are ####.
## 0.15 — <theme of the minor, user words> {#v0-15}
<2–3 sentences: who benefits and what changed for them, linking the
headline `####` sections across its releases.>
### 0.15.1 — 2026-10-12 {#v0-15-1}
<Highlights: 1–2 sentences naming this release's changes, each linked to
its `####` below.>
#### <Feature as the user's gain> {#v0-15-1-<slug>}
<Problem the user had → what they can do now → one short command or
config example → link to the guide or reference.>
#### Smaller improvements {#v0-15-1-more}
- <outcome bullet> — [doc page][ref].- Every version (
###) opens with a highlights sentence or two that links each####in it. No release body starts with a heading or a list. - One
####per notable change: a feature, a new client, a TUI change, a breaking change (heading says so, body gives the migration). Never let a bullet list follow a feature's body directly — it reads as that feature's sub-items. Loose items go under a closing#### Smaller improvements(and#### Fixeswhen fixes are worth listing on their own). - Minor (x.y.0) — new
##section above the previous minor, plus### x.y.0. - Patch (x.y.z) — new
###directly under the minor's theme paragraph (patches newest first, abovex.y.0). A patch with nothing notable is highlights plus#### Smaller improvementsonly. Revisit the minor's theme paragraph when the patch shifts it. - Heading anchors:
{#vX-Y},{#vX-Y-Z},{#vX-Y-Z-<slug>}— never change an anchor once published. - Date = the version heading date in
CHANGELOG.md.
Procedure
- Version.
$ARGUMENTS, else[package] versioninCargo.toml. Never derive it from git tags. Stop if the page already has that### x.y.zheading. - Source. Read that version's section in
CHANGELOG.md(git diff CHANGELOG.mdright afterrelease:prepare). - Filter. Keep what a user notices: new commands, flags, clients,
config keys, behaviour changes, fixes to visible bugs. Drop
Changedrefactors, CI, tests, internal docs, AI-config work. When unsure what an entry does, read the commit (git log --grep,git show) or its PR (gh pr view). - Link. For every kept item, grep
docs/src/content/docs/for the page and heading anchor that documents it. Behaviour changes that need action also link the matching anchor indocs/src/content/docs/upgrading.md. An item with no doc page is a docs gap — report it, still write the entry. - Write. Group related entries into one feature. Per feature: problem → capability → example → link. User's words, not commit subjects (DOC-TYPE-38). No hype adjectives; the example makes the case. Reference-style links only, definitions at the bottom of the page.
- Gate. Run
/docs-reviewon the page, thenpython3 .claude/rules/docs-quality/checks/page_type.py docs/src/content/docs/changelog.mdandtask docs:check. Fix every finding. - Hand off. Leave the page changed in the working tree so it lands in
the same
release: vX.Y.Zcommit asCHANGELOG.mdandCargo.toml. Report docs gaps from step 4 as one line each.
$ARGUMENTS
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.

