Cull Release Publish Skill for Claude
Use when the user explicitly asks to publish or complete a prepared Cull release, or when the authorized cull-release orchestrator reaches publication after every repository and artifact gate passes.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/glebis/claude-skills --skill cull-release-publishWhat comes with it
277 bytes besides the instructionThe instruction itself
3 sections, as written by the authorCull Release Publish
Authority
An explicit “Release Cull patch|minor|major” or direct “Publish prepared Cull
release X.Y.Z” request authorizes publication. Do not ask for another confirmation
after gates pass. That authority does not waive or bypass any gate.
Implicit invocation is disabled. Without that explicit authority, stop before any
tag, push, workflow dispatch, release, or tap mutation.
Publish
- Resolve the Cull checkout and parse one JSON envelope from
npm run release:cull -- state show --version "$VERSION" --json.
- Require state
prepared, exact metadata, a clean release commit already pushed
on main, green required checks, active branch/tag protection, publication
enablement, and no conflicting tag.
- Create one annotated tag for the prepared commit and push that tag normally.
Never move, replace, or force-push a tag.
- Watch the tag-bound GitHub release workflow. Never substitute a local build.
- Require the secret-free verifier's exact artifact inventory, signatures,
notarization, checksums, and provenance before automatic publication.
- Wait for checksum-pinned Homebrew promotion and its audit/install/launch proof.
- Record evidence transitions through
publishedandhomebrew-promotedusing
the repository CLI's state commands.
On failure, use cull-release-recover. Never delete or rewrite a tag, delete a
release, replace published assets, bypass verification, or force workflow state.
Other skills for the same job
different authors, same section of the catalogue
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
How to use it
Take glebis/cull-release-publish from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.