prepare-release skill
Prepare a new release by collecting commits, generating bilingual release notes, updating version files, and creating a release branch. Use when asked to prepare/create a release, bump version, or run `/prepare-release`.
Is the prepare-release skill safe?
Clean: nothing in its files matched our rules. We read 1 file in the folder on 2026-09-28.
No findings.
Install the prepare-release skill
A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.
git clone --depth 1 https://github.com/CherryHQ/cherry-studio.git /tmp/cherry-studio mkdir -p ~/.claude/skills cp -r /tmp/cherry-studio/.agents/skills/prepare-release ~/.claude/skills/prepare-release
In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub
The instructions your agent would load
SKILL.md as published, without the frontmatter. Read it on GitHub
Prepare Release
Automate the Cherry Studio release workflow: collect changes → generate bilingual release notes → update files → create release branch → trigger CI/CD.
Arguments
Parse the version intent from the user's message. Accept any of these forms:
- Bump type keyword: patch, minor, major
- Exact version: strict x.y.z or x.y.z- without build metadata (e.g. 1.8.0, 1.8.0-beta.1, 1.8.0-rc.1)
- Natural language: "prepare a beta release", "bump to 1.8.0-rc.2", etc.
Defaults to patch if no version is specified. Always echo the resolved target version back to the user before proceeding with any file edits.
- --dry-run: Preview only, do not create a release branch.
Workflow
Step 1: Determine Version
- For an interactive local run, fetch origin/main and all tags, then verify that the checkout is a clean main at exactly origin/main:
git fetch origin refs/heads/main:refs/remotes/origin/main --tags
test "$(git branch --show-current)" = main
test -z "$(git status --porcelain)"
test "$(git rev-parse HEAD)" = "$(git rev-parse origin/main)"Stop before editing files if any check fails. This prevents a standalone run from creating a release branch from an arbitrary or stale checkout. In GitHub Actions, use the workflow's frozen dispatch SHA and leave checkout validation to the workflow. Do not fetch or compare the later origin/main head.
- Read the current version from package.json. Use it for version increments even if that release has since been withdrawn; never reuse the withdrawn version.
- Select the latest published, non-draft GitHub Release whose tag is strict v as the release-note baseline. Non-semver preview releases and drafts are never a baseline:
gh release list --limit 1000 --json isDraft,publishedAt,tagName --jq '[.[] | select(.isDraft == false and (.tagName | test("^v(0|[1-9][0-9]*)\\.(0|[1-9][0-9]*)\\.(0|[1-9][0-9]*)(-[0-9A-Za-z-]+(\\.[0-9A-Za-z-]+)*)?$")))] | sort_by(.publishedAt) | last | .tagName // empty'Stop if no published baseline exists or its Git tag is missing (git rev-parse --verify refs/tags/{baseline-tag}). Compare its version with the current package version using semver: if main is behind, stop and require the latest Post Release metadata PR to be merged. If main is ahead, allow preparation using the published baseline for release notes and the package version for version increments. For example, after withdrawing 2.1.1, main at 2.1.1 with a published baseline of 2.1.0 prepares 2.1.2 and includes changes since 2.1.0. In GitHub Actions, use the workflow-provided baseline tag and collection base without repeating these checks.
- Compute the new version based on the argument:
- patch / minor / major: bump from the current version.
- An exact version must match ^(0|[1-9][0-9])\.(0|[1-9][0-9])\.(0|[1-9][0-9])(-[0-9A-Za-z-]+(\.[0-9A-Za-z-]+))?$ and pass semver.valid; build metadata such as +build.1 is not accepted.
- In both cases, require the result to be strictly greater than the current version according to semver precedence. Reject equal versions and downgrades.
Step 2: Collect Commits
- Determine the release-note collection base from the published baseline selected in Step 1, not from the package version:
- If the baseline tag is an ancestor of HEAD, use the tag.
- Otherwise, use the latest commit whose full message contains the exact marker release-metadata-boundary: . This machine marker is added to the Post Release pull request body and survives the required squash merge.
- For metadata pull requests created before the machine marker existed, accept a subject exactly equal to chore(release): sync metadata or that subject followed only by GitHub's squash suffix (#).
- Stop with an error if the tag is not an ancestor and its metadata sync commit is missing; otherwise already-released hotfixes could be included again.
- List all commits since that base:
git log <collection-base>..HEAD --format="%H %s" --no-merges- For each commit, get the full body:
git log <hash> -1 --format="%B"- Extract the content inside release-note code blocks from each commit body.
- Extract the conventional commit type from the title (feat, fix, refactor, perf, docs, etc.).
- Skip these commits:
- Titles starting with 🤖 Daily Auto I18N
- Titles starting with Merge
- Titles starting with chore(deps)
- Titles starting with chore: release
- Titles starting with chore(release)
- Commits where the release-note block says NONE
Step 3: Generate Bilingual Release Notes
Using the collected commit information, generate release notes in both English and Chinese.
Recommended format:
<!--LANG:en-->
Cherry Studio {version} - {Brief English Title}
✨ New Features
- [Component] Description
🐛 Bug Fixes
- [Component] Description
💄 Improvements
- [Component] Description
⚡ Performance
- [Component] Description
<!--LANG:zh-CN-->
Cherry Studio {version} - {简短中文标题}
✨ 新功能
- [组件] 描述
🐛 问题修复
- [组件] 描述
💄 改进
- [组件] 描述
⚡ 性能优化
- [组件] 描述
<!--LANG:END-->The language markers are the machine-readable contract: include each marker once, keep them in order, and provide non-empty English and Chinese sections. Titles and surrounding explanatory text are presentation choices, not validation requirements.
Rules:
- Only include categories that have entries (omit empty categories).
- Each commit appears as exactly ONE line item in the appropriate category.
- Use the release-note field if present; otherwise summarize from the commit title.
- Component tags should be short: [Chat], [Models], [Agent], [MCP], [Settings], [Data], [Build], etc.
- Chinese translations should be natural, not machine-literal.
- Do NOT include commit hashes or PR numbers.
- Read the existing release notes in electron-builder.yml as a style reference before writing.
IMPORTANT: User-Focused Content Only
Release notes are for end users, not developers. Exclude anything users don't care about:
- EXCLUDE internal refactoring, code cleanup, or architecture changes
- EXCLUDE CI/CD, build tooling, or test infrastructure changes
- EXCLUDE dependency updates (unless they add user-visible features)
- EXCLUDE documentation updates
- EXCLUDE developer experience improvements
- EXCLUDE technical debt fixes with no user-visible impact
- EXCLUDE overly technical descriptions (e.g., "fix race condition in Redux middleware")
INCLUDE only changes that users will notice:
- New features they can use
- Bug fixes that affected their workflow
- UI/UX improvements they can see
- Performance improvements they can feel
- Security fixes (simplified, without implementation details)
Keep descriptions simple and non-technical:
- ❌ "Fix streaming race condition causing partial tool response status in Redux state"
- ✅ "Fix tool status not stopping when aborting"
- ❌ "Auto-convert reasoning_effort to reasoningEffort for OpenAI-compatible providers"
- ✅ "Fix deep thinking mode not working with some providers"
Step 4: Update Files
- package.json: Update the "version" field to the new version.
- electron-builder.yml: Replace the content under releaseInfo.releaseNotes: | with the generated notes. Preserve the 4-space YAML indentation for the block scalar content.
- resources/cherry-studio/release-history.json: Never edit by hand; the notes must match electron-builder.yml byte for byte. Run node scripts/release/sync-release-history.js --target-version {version}, which prepends (or replaces) the entry for a stable release and leaves the file untouched for a prerelease. In GitHub Actions, the workflow runs this itself after the Claude step.
- Validate source metadata: For an interactive local run, run node scripts/release/validate-prepared-release.js --target-version {version} before generating the product manifest, and stop if it rejects the changed paths, version ordering, bilingual sections, or stable history. In GitHub Actions, leave validation to the workflow step that runs after Claude.
- Built-in knowledge: For an interactive local run, run pnpm build:builtin-knowledge after validation. This refreshes resources/builtin-agents/cherry-assistant/product-manifest.json with the new package version. Never edit the generated manifest by hand. In GitHub Actions, do not run the generator: the workflow runs the same validator first, then runs the trusted generator itself.
Step 5: Present for Review
Show the user:
- The new version number.
- The full generated release notes.
- A summary of which files were modified.
If --dry-run was specified, stop here.
Otherwise, ask the user to confirm before proceeding to Step 6.
Step 6: Create Release Branch
- For an interactive local run, repeat Step 1 items 1-3 immediately before creating the branch, reading the original package version from HEAD:package.json. Require the published baseline to still match the one used to collect release notes; otherwise regenerate the notes before proceeding. Because Step 4 has intentionally prepared and validated release metadata, replace Step 1's clean-worktree assertion with git status --short and stop unless every listed path is one of the four allowed release metadata files. Then create and push a signed, DCO-compliant release commit:
git fetch origin refs/heads/main:refs/remotes/origin/main --tags
test "$(git branch --show-current)" = main
test "$(git rev-parse HEAD)" = "$(git rev-parse origin/main)"
test "$(node -p "require('./package.json').version")" = "{version}"
CURRENT_VERSION="$(git show HEAD:package.json | jq -r .version)"
LATEST_PUBLISHED="$(gh release list --limit 1000 --json isDraft,publishedAt,tagName --jq '[.[] | select(.isDraft == false and (.tagName | test("^v(0|[1-9][0-9]*)\\.(0|[1-9][0-9]*)\\.(0|[1-9][0-9]*)(-[0-9A-Za-z-]+(\\.[0-9A-Za-z-]+)*)?$")))] | sort_by(.publishedAt) | last | .tagName // empty')"
test "$LATEST_PUBLISHED" = "{baseline-tag}"
git rev-parse --verify "refs/tags/$LATEST_PUBLISHED"
node -e "const semver = require('semver'); process.exit(semver.gte(process.argv[1], process.argv[2]) ? 0 : 1)" "$CURRENT_VERSION" "${LATEST_PUBLISHED#v}"
REPO="$(gh repo view --json nameWithOwner --jq .nameWithOwner)"
gh api --paginate --slurp "repos/$REPO/releases?per_page=100" | TAG="v{version}" node scripts/release/validate-release-state.js prepare
test -z "$(git ls-remote --heads origin refs/heads/release/v{version})"
git status --short
UNEXPECTED_RELEASE_PAT- In GitHub Actions, stop after updating package.json and electron-builder.yml. Temporary helper files and local Git operations are allowed; the workflow extracts those two file changes, restores the frozen source SHA, and discards everything else. It then derives the release history, validates, generates the product manifest, creates the branch, and uses GitHub's API to create and verify the signed, DCO-compliant commit. Never push from the Claude step.
- Report the release branch and next steps. Do not create a PR yet: the release must be built and published from this branch first.
CI Trigger Chain
- Wait for the CI push run on the new release/v{version} commit to succeed. auto-release-build.yml revalidates that exact live branch head and dispatches release.yml with all; it builds macOS, Windows, and Linux and creates or updates the draft GitHub Release. Use release.yml manually only to retry a failed all-platform build or one platform for the unchanged tagged commit.
- While a single draft semantic-version release is active, backport-release-fixes.yml opens a backport PR for the first merged hotfix: or hotfix(): PR from main, applies any optional bilingual release note, then appends consecutive hotfixes and source markers to that same open topic branch. It manages every source PR's hotfix and backport-status labels and reports failures on the source PR; never merge main into the release branch.
- Review the backport PR, wait for its CI, and merge it. After the resulting release-branch push passes CI, the exact-head all-platform draft rebuild starts automatically.
- A successful exact-head all-platform build starts publish-release.yml. Approve the release Environment deployment after inspecting the draft. Publication then acquires the release-state lock, revalidates the approved run, release branch, tag, draft, artifacts, open PRs, and pending hotfixes, and publishes only if they still agree. The draft body contains the bilingual electron-builder.yml notes followed by GitHub's generated changes. The final fetched main SHA is the hotfix cutoff; a hotfix merged after that snapshot belongs to the next release. Publication triggers post-release.yml, which uses the published tag as its source, applies only the release metadata delta to the latest main, and creates a release-sync/v{version} metadata-only PR.
- The metadata PR synchronizes only package.json, electron-builder.yml, release history, and the generated product manifest. It triggers ci.yml; merge it only after CI passes.
- When squash-merging the metadata PR, set the commit title to exactly chore(release): sync v{version} metadata with only GitHub's optional PR-number suffix, and keep release-metadata-boundary: v{version} on its own line in the squash commit body so the next release can find the boundary reliably.
Constraints
- Always read electron-builder.yml before modifying it to understand the current format.
- Never retain changes outside package.json, electron-builder.yml, resources/cherry-studio/release-history.json, and the generated resources/builtin-agents/cherry-assistant/product-manifest.json.
- Never push directly to main.
- Never create the release metadata PR before the GitHub Release is published; post-release.yml owns that step.
- Always show the generated release notes to the user before creating the release branch (unless running in CI with no interactive user).
More skills from CherryHQ/cherry-studio
- Acherry-assistant-guide从当前安装包查询 Cherry Studio 产品信息并排查运行问题。当用户询问功能、路由、快捷键、Provider、语言、Agent、频道、定时任务、Code CLI、当前版本,或报告运行错误、连接失败、配置异常并需要诊断时触发。
- Acherry-browserInteract with the user's visible Agent browser in Cherry Studio. Use for page navigation, authenticated websites, screenshots, forms, clicks, and browser debugging. Check live browser tools first; browser control requires the Browser setting and an available Agent pane.
- Acherry-electron-devDevelop, fix, and profile Cherry Studio in a tracked Electron instance. Use for everyday implementation, UI and interaction work, bug fixing, runtime debugging, DevTools inspection, lag or jank investigation, CPU and memory monitoring, leak checks, and startup-performance analysis; reuse a verified workspace instance across instructions and launch or replace one only when required.
- Acherry-pr-testTest Cherry Studio PRs by resolving and checking out a PR, statically inspecting its changes, running interactive UI tests against a safely tracked Electron instance through CDP, producing a structured report, cleaning up only the owned test instance, and restoring the original branch.
- Acherry-regression-testRun Cherry Studio critical-path system regression tasks through the repository-owned Playwright E2E workflow. Use for full regression, release acceptance, development-branch system validation, or a named cherry-regression-test task on GitHub-hosted macOS and Windows runners.
- Acherry-skill-marketplace当用户明确要求搜索、安装、查看、卸载或创建 Skill,或内置 Skill / 工具出现能力缺口、无法完成当前任务时触发。通过 `mcp__skills__search_skills` 搜索并用 `mcp__skills__install_skill` 安装;已安装 Skill 的查看和删除通过产品清单导航到 Skills UI;没有合适结果时调用内置 `skill-creator` 创建并验证自定义 Skill,再继续原任务。普通任务仍先尝试内置能力。
- Acherry-studio-feedbackUse when Cherry Studio 用户希望报告、提交或整理 BUG、UI/UX 问题或功能建议,但未明确要求创建 GitHub Issue。
- Acherry-tool-guideCherry Studio first-party tool and bundled-shell routing for general agents. For straightforward local work in shell-capable sessions, run JS/TS with `bun <file>` and one-off JS tools with `bun x`; run Python with `uv run [--with <pkg>] python` and one-off Python CLIs with `uvx`; search with `rg`. Load this guide before changing project dependencies, deciding whether a tool should be ephemeral or reusable, reading or converting local Office/PDF files, coordinating or delegating across Agent Sessions, or using Cherry-owned web/browser, knowledge, persistent memory, schedules/notifications, IM channels, image generation, artifact reporting, managed CLI, skill, or MCP-server-registration capabilities—even if the user names no tool. Consult it before shell/file workarounds; live tool schemas are authoritative.
- Aclaude-automation-recommenderAnalyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.
- Acode-mate-antigravityRuns Antigravity CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Antigravity CLI or compare its result with another coding agent.
- Acode-mate-claude-codeRuns Claude Code non-interactively for code analysis and implementation tasks. Use when the user asks to delegate repository work to Claude Code or compare its result with another coding agent.
- Acode-mate-codexRuns Codex CLI non-interactively for code analysis and implementation tasks. Use when the user asks to delegate repository work to Codex or obtain a second coding-agent result.