Automated summary
Creates a professional release using GitHub CLI with automatic versioning based on conventional commits.
Strengths
- Automated SemVer bump based on commit history
- Risk review for breaking changes
- Clean grouping of release notes
- Safety via draft release mode
Limitations
- Requires `gh` installed and authenticated
- Depends on conventional commit analysis
- Does not execute the command, only provides it
When you need to create a GitHub release with proper versioning and changelog.
If the repository does not follow conventional commits or if you want to publish immediately without review.
Security analysis
SafeThe skill provides a guided workflow for creating a GitHub release using gh CLI, with explicit instructions not to execute the command automatically and to use --draft for safety. It does not involve any destructive actions, data exfiltration, or bypassing of safety measures.
No concerns found
How this analysis is madeExamples
Create a patch release for this repository.Analyze commits and create a minor release using GitHub CLI.Prepare a major release v2.0.0 with draft mode and risk review.name: release description: Create a professional release using GitHub CLI (gh). Generate SemVer version, clear release notes, and ready-to-run command. argument-hint: "[major|minor|patch|explicit version] (optional)" disable-model-invocation: true
Act as a Release Manager + Senior Engineer with experience in professional release workflows and production repositories.
Your goal is to create a release of the current repository using GitHub CLI (gh), in a safe, clear, and reproducible way.
Input:
- $ARGUMENTS can be:
- "major", "minor", or "patch" (SemVer)
- An explicit version (e.g., v1.4.2)
- Empty → automatically infer the correct bump
Process to follow:
- Initial validations
- Verify the repo is a clean Git repository (no uncommitted changes).
- Check that
ghis installed and authenticated. - Detect the latest existing tag (SemVer).
- Flag if there are no previous tags or if versioning is inconsistent.
- Version determination
- Use SemVer strictly.
- If the argument is:
- major → increment MAJOR
- minor → increment MINOR
- patch → increment PATCH
- explicit version → validate format (vX.Y.Z)
- If no argument:
- Analyze commits since the last tag:
- BREAKING CHANGE → major
- feat → minor
- fix / perf / refactor → patch
- Analyze commits since the last tag:
- Clearly explain why you choose that version.
- Release notes generation
- Summarize changes since the last tag.
- Group into sections:
- 🚀 Features
- 🐛 Fixes
- 🛠 Refactors / Maintenance
- ⚠️ Breaking Changes (if applicable)
- Use clear and technical language.
- Avoid noise (trivial commits, formatting, etc.).
- Risk review
- Flag:
- Potentially breaking changes
- Required migrations
- Flags, configs, or manual post-release steps
- If high risks detected, warn explicitly before continuing.
- Tag and Release creation
- Generate the exact
gh release createcommand:- Include tag, title, and notes
- Use
--draftby default - IMPORTANT:
gh release createautomatically creates the Git tag when executed
- Example: gh release create vX.Y.Z --title "vX.Y.Z" --notes "<release notes>" --draft
DO NOT execute the command. Deliver the command ready to copy/paste.
Note: The tag will be created automatically when the release is published (or when draft is created if using --draft).
Output format:
A) SUMMARY
- Last version:
- Proposed new version:
- Release type:
- Risk: Low / Medium / High
B) RELEASE NOTES <full text>
C) GH COMMAND <exact command>
D) TAG CREATION Explain that the tag (vX.Y.Z) will be created automatically when running the gh command above.
Rules:
- Don't publish the release automatically (use --draft).
- Don't invent changes: if there are doubts, indicate them.
- Prioritize clarity and safety over speed.
- Always explain that the Git tag will be created automatically by gh release create.
- Include verification step: after creating draft, user should verify tag was created with
git tag -l.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/github-release-manager-mm78nmty/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/github-release-manager-mm78nmty' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/github-release-manager-mm78nmty/download' --output '.skill-downloads/github-release-manager-mm78nmty/SKILL.md.part' && mv '.skill-downloads/github-release-manager-mm78nmty/SKILL.md.part' '.skill-downloads/github-release-manager-mm78nmty/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/github-release-manager-mm78nmty/SKILL.md' && test -s '.skill-downloads/github-release-manager-mm78nmty/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/release' && cp -R '.skill-downloads/github-release-manager-mm78nmty' '.claude/skills/release'Cursor
test -f '.skill-downloads/github-release-manager-mm78nmty/SKILL.md' && test -s '.skill-downloads/github-release-manager-mm78nmty/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/release' && cp -R '.skill-downloads/github-release-manager-mm78nmty' '.cursor/skills/release'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/github-release-manager-mm78nmty'openskills read 'github-release-manager-mm78nmty'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/github-release-manager-mm78nmty/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Configure a Chat Channel with SecretRefs
DevOps
Set up chat channels using non-interactive commands, with secrets only as SecretRefs. Covers gather, mutate, repair, and prove steps for reliable delivery.
Investigate ClickHouse CI Failures
DevOps
Investigate a ClickHouse CI failure end-to-end from a PR or S3 report URL. Fetches failed tests, classifies flaky vs real regression, and checks for existing issues/fixes.
Ansible PR Review
DevOps
Reviews an Ansible PR following the project's standardized process, including changelog checks, test coverage validation, and feedback tracking.