Automated summary
This skill lays out a repeatable release procedure: locate the version source, pick the semver level, update the version and changelog, then verify before proposing a commit.
Strengths
- Explicit detection order for version sources (VERSION, CHANGELOG, package.json, pyproject.toml) with clear precedence.
- Detailed semver rubric backed by concrete examples (public API, config keys, MCP tools, parity fixtures).
- Named verification step using the repo's own scripts, with a hard stop on failing checks.
- Strong guardrails: never invent a version file, and never commit, tag, or push without an explicit request.
Limitations
- Tightly coupled to the ProjectTwelve repository: scripts, AGENTS.md, and internal tooling are hardcoded.
- The Unity path (bundle version in ProjectSettings.asset) is explicitly left to a human Editor workflow and not automated.
- Covers preparation only — publishing and pushing tags are out of scope.
Use it when you need to cut a release, bump the project version, or prepare an annotated tag with a promoted changelog section.
Avoid it on a repo with no defined version source, or when you actually want to publish and push a release, which the skill deliberately does not do.
Security analysis
SafeThe skill instructs running local verification scripts and git commands, but these are standard, non-destructive release tasks. It explicitly avoids committing, tagging, or pushing without user approval, and there is no exfiltration, obfuscation, or destructive behavior.
No concerns found
How this analysis is madeExamples
Cut a release for the offline tooling and tell me which semver level you picked and why.Bump the version to the next minor and promote the Unreleased section of CHANGELOG.md to a dated release entry, then run the verification checks.There's no root VERSION file — should we tag tile-viz@x.y.z instead? Walk me through the options before changing anything.name: release-bump description: Bump the project version with a semver rubric, promote the Unreleased changelog section, and verify before committing. Use when the user asks to cut a release, bump the version, or tag a new version.
Release bump
Repeatable release procedure: decide the semver level, update the version and changelog, verify, and prepare (not push) the release commit.
1. Detect the version source
Find where the version lives, in this order:
- Root
VERSIONfile orCHANGELOG.md(Keep a Changelog) — preferred when present tools/tile-viz/package.jsonortools/world-viz/package.json(offline tooling only)pyproject.toml/setup.cfg(Python), if added later
ProjectTwelve note: There is no root CHANGELOG.md or VERSION file yet. For game releases,
Unity uses ProjectSettings/ProjectSettings.asset (bundle version) — that is a human Editor workflow,
not an agent semver bump. If no semver source exists, ask the user whether to:
- Create
VERSION+CHANGELOG.mdat repo root for agent-infra / tooling releases, or - Tag a specific subsystem only (e.g.
tile-viz@x.y.z), or - Skip versioning until a release process is defined.
Do not invent a version file without explicit approval.
2. Choose the bump (semver rubric)
Review changes since the last release (git log <last-tag>..HEAD and the Unreleased section of
CHANGELOG.md when it exists):
- major — any breaking change: removed/renamed public API, config key, schema field, MCP tool contract, or autotile/visual behavior that breaks parity fixtures without migration.
- minor — new backward-compatible capability (new command, skill, MCP tool, gameplay feature).
- patch — bug fixes, docs, internal refactors with no contract change.
State the chosen level and the one or two changes that justify it.
3. Update files
- Bump the version in the detected source.
- When
CHANGELOG.mdexists: rename## [Unreleased]to## [X.Y.Z] — YYYY-MM-DD, keeping its subsections, and add a fresh empty## [Unreleased]above it.
4. Verify
Run checks from AGENTS.md for the changed areas:
python scripts/sync_assistant_trees.py --check
python3 scripts/check_markdown_links.py
python3 scripts/check_paid_assets.py --staged
# Unity / offline tests as applicable — see AGENTS.md test vocabulary
Do not proceed with failing checks.
5. Commit and tag — only when the user asks
Suggest a Conventional Commit (chore(release): vX.Y.Z) and the matching annotated tag
(git tag -a vX.Y.Z). Do not commit, tag, or push without an explicit request.
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/release-bump-mryiqfy6/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/release-bump-mryiqfy6' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/release-bump-mryiqfy6/download' --output '.skill-downloads/release-bump-mryiqfy6/SKILL.md.part' && mv '.skill-downloads/release-bump-mryiqfy6/SKILL.md.part' '.skill-downloads/release-bump-mryiqfy6/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/release-bump-mryiqfy6/SKILL.md' && test -s '.skill-downloads/release-bump-mryiqfy6/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/release-bump' && cp -R '.skill-downloads/release-bump-mryiqfy6' '.claude/skills/release-bump'Cursor
test -f '.skill-downloads/release-bump-mryiqfy6/SKILL.md' && test -s '.skill-downloads/release-bump-mryiqfy6/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/release-bump' && cp -R '.skill-downloads/release-bump-mryiqfy6' '.cursor/skills/release-bump'Codex
test -f '.skill-downloads/release-bump-mryiqfy6/SKILL.md' && test -s '.skill-downloads/release-bump-mryiqfy6/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/release-bump' && cp -R '.skill-downloads/release-bump-mryiqfy6' '.agents/skills/release-bump'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/release-bump-mryiqfy6'openskills read 'release-bump-mryiqfy6'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/release-bump-mryiqfy6/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.