跳到正文
cccskills
免费在 GitHub 公开

release-manager

Automates release management with changelog generation, semantic versioning, and release readiness checks. Use when preparing releases, generating changelogs, bumping versions, or validating release candidates.

中文简介正在准备中。当前显示原文说明。

集成工具Docker
查看安装方法

包含的文件(16)

  • SKILL.md6.3 KB
  • assets/sample_commits.json7.3 KB
  • assets/sample_git_log_full.txt5.9 KB
  • assets/sample_git_log.txt2.0 KB
  • assets/sample_release_plan.json8.5 KB
  • changelog_generator.py19.2 KB
  • expected_outputs/changelog_example.md1.3 KB
  • expected_outputs/release_readiness_example.txt927 B
  • expected_outputs/version_bump_example.txt742 B
  • README.md14.4 KB
  • references/conventional-commits-guide.md9.1 KB
  • references/hotfix-procedures.md15.4 KB
  • references/release-workflow-comparison.md13.0 KB
  • references/workflows-and-tool-reference.md13.9 KB
  • release_planner.py38.5 KB
  • version_bumper.py22.7 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Release Manager

The agent automates release management by parsing conventional commits into structured changelogs, determining semantic version bumps, and assessing release readiness with checklists, rollback runbooks, and stakeholder communication plans.

Core Capabilities

  • Changelog generation — parse conventional commits since the last tag into Keep-a-Changelog Markdown/JSON, grouped by type with breaking-change highlights and issue links.
  • Semantic version bumping — determine MAJOR/MINOR/PATCH from commit types, support pre-release tracks (alpha → beta → rc), emit bump commands for npm, Python, Rust, Git, Docker.
  • Release readiness — score a release plan across features, quality gates, approvals, and timelines; surface blocking issues.
  • Rollback & comms — generate rollback runbooks with triggers and time estimates, plus stakeholder communication plans with timed message templates.
  • Workflows — changelog+bump, readiness assessment, and expedited hotfix releases, each with validation checkpoints.

When to Use

  • Preparing a release — generate the changelog and determine the next version.
  • Validating a release candidate — assess readiness and surface blockers.
  • Shipping a hotfix — expedited fix, pre-release versioning, tested rollback.
  • Auditing commit hygiene — confirm conventional commits drive clean changelogs.

Clarify First

Before preparing the release, confirm these inputs. If any is unknown or vague, ASK — do not assume:

  • Last release tag / commit range — defines the changelog window and the basis for the version-bump decision
  • Release type — standard / hotfix / pre-release (alpha→beta→rc) (selects the workflow and versioning track)
  • Target ecosystem — npm / Python / Rust / Git / Docker (determines which bump commands are emitted)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

Tools

ToolPurposeCommand
changelog_generator.pyGenerate Keep-a-Changelog from conventional commitsgit log --oneline v1.0.0..HEAD | python changelog_generator.py --version 1.1.0 --format both
version_bumper.pyDetermine SemVer bump + emit bump commandsgit log --oneline v1.0.0..HEAD | python version_bumper.py --current-version 1.0.0 --analysis
release_planner.pyAssess release readiness, checklist, rollback, commspython release_planner.py --input release-plan.json --include-checklist --include-rollback

References

Load the reference that matches the task — keep this file lean and pull detail on demand:

  • references/workflows-and-tool-reference.md — quick start, the 3 core workflows with checkpoints, version-bump rules, rollback triggers, anti-patterns, troubleshooting table, success criteria, and the full CLI flag reference for all three scripts. Read when running a release or looking up a flag.
  • references/conventional-commits-guide.md — conventional-commit format, types, and footer conventions. Read when fixing commit hygiene so changelog/version tooling works.
  • references/hotfix-procedures.md — severity classification (P0–P3), hotfix procedures, and best practices across workflows. Read when shipping an emergency fix.
  • references/release-workflow-comparison.md — Git Flow vs GitHub Flow vs Trunk-based, with structure, branch types, and trade-offs. Read when choosing or aligning a branching model.

Scope & Limitations

This skill covers:

  • Parsing conventional commits and generating structured changelogs in Markdown and JSON formats
  • Determining semantic version bumps (major/minor/patch) with pre-release support (alpha, beta, rc)
  • Assessing release readiness across features, quality gates, approvals, and timelines
  • Generating rollback runbooks, communication plans, and release checklists from structured input

This skill does NOT cover:

  • Actual CI/CD pipeline execution or deployment automation (see engineering/ci-cd-pipeline-generator)
  • Live monitoring, alerting, or incident response during deployments (see engineering/monitoring-alerting-setup)
  • Code review processes or pull request management (see engineering/code-review-automation)
  • Infrastructure provisioning, container orchestration, or environment management (see engineering/infrastructure-as-code)

Integration Points

SkillIntegrationData Flow
engineering/ci-cd-pipeline-generatorEmbed changelog generation and version bumping as pipeline stagesGit log output flows into changelog_generator.py; version bump output feeds pipeline tagging steps
engineering/code-review-automationValidate that PR commits follow conventional commit format before mergeCommit messages validated upstream ensure clean input for changelog generation
engineering/monitoring-alerting-setupDefine rollback triggers based on monitoring thresholds from the rollback runbookRollback trigger thresholds (error rate >2x, latency >50%) feed into alert rule configuration
engineering/api-design-reviewerBreaking API changes flagged by the reviewer map to MAJOR version bumpsAPI review findings populate breaking_changes arrays in the release plan JSON
engineering/infrastructure-as-codeDeployment steps in the rollback runbook reference infrastructure rollback commandsRollback runbook command fields contain infrastructure-specific commands (kubectl, DNS, load balancer)
project-management/release-planningRelease plan JSON structure aligns with PM release tracking artifactsPM feature lists and approval statuses feed directly into release_planner.py input format

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

This skill should be used when the user asks to "check accessibility", "audit WCAG compliance", "scan HTML for a11y issues", "check color contrast", or "find accessibility violations in web pages".

中文简介正在准备中。当前显示原文说明。

borghei/Claude-Skills9532026年10月7日 更新

Design and run statistically rigorous A/B tests and experiments. Use when planning experiments, calculating sample sizes, designing test variants, selecting metrics, analyzing results, or when someone says "let's test that."

中文简介正在准备中。当前显示原文说明。

borghei/Claude-Skills9532026年10月7日 更新

Design and analyze A/B tests: sample size, test duration, and statistical significance for conversion experiments. Use when setting up an A/B test, calculating sample size, designing an experiment, or analyzing results.

中文简介正在准备中。当前显示原文说明。

borghei/Claude-Skills9532026年10月7日 更新

Sales execution across pipeline, discovery, demos, negotiation, and closing. Use when qualifying opportunities, running MEDDIC discovery, building account plans, handling objections, structuring proposals, or forecasting pipeline.

中文简介正在准备中。当前显示原文说明。

borghei/Claude-Skills9532026年10月7日 更新

Design ad creative across Google, Meta, LinkedIn, Twitter/X, and TikTok with platform format specs, headline formulas, and A/B testing. Use when writing ad copy, generating headline variations, creating ad sets, or validating creative.

中文简介正在准备中。当前显示原文说明。

borghei/Claude-Skills9532026年10月7日 更新

aeo

免费

Answer Engine Optimization (AEO): optimize content to be cited by LLMs (ChatGPT, Claude, Perplexity, Gemini) in their answers. Use when designing content for LLM citation, auditing citability, or structuring Q&A schema.

中文简介正在准备中。当前显示原文说明。

borghei/Claude-Skills9532026年10月7日 更新

查看 borghei 的全部技能

报告此技能的问题