A release assistant that uses Changesets to manage software versions and commits. It supports patch, minor, major, and specific version releases.

Use it to analyze code changes, choose a release version, create a bilingual changelog, commit changes, and prepare releases for projects published through GitHub Actions and npm.

It organizes version updates, changelogs, branches, pull requests, and publishing steps so releases follow a repeatable process.

How UfoMiao/zcf configures Claude Code

About the project

ZCF is a command-line setup tool for configuring Claude Code and Codex with agents, instructions, skills, hooks, commands, and settings. It is for developers who want to install and personalize these coding-agent workflows through an interactive setup.

UfoMiao/zcf · 6,079 stars · on GitHub · zcf.ufomiao.com

Reuse

Borrowing it

Nothing to install: this file belongs to UfoMiao/zcf. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/UfoMiao/zcf/main/.claude/skills/zcf-release/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/UfoMiao/zcf

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ufomiao/zcf/zcf-release/github.svg)](https://agentmods.dev/skills/ufomiao/zcf/zcf-release)

Your own site

<a href="https://agentmods.dev/skills/ufomiao/zcf/zcf-release"><img src="https://agentmods.dev/badge/skills/ufomiao/zcf/zcf-release/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ufomiao/zcf/zcf-release"><img src="https://agentmods.dev/badge/skills/ufomiao/zcf/zcf-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 707 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Agent Snooping · line 281
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
high Tool Misuse · line 347
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
medium Excessive Agency · line 242
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
medium Excessive Agency · line 449
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00025	$0.00707
Opus 5.5	$0.00010	$0.00283
Sonnet 5.5	$0.00005	$0.00141
Haiku 4.5	$0.00003	$0.00071

Measured 2d ago against content hash 72c1e44055cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zcf-release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/zcf-release/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ZCF Release

Prepare a release PR. Merging it to main makes .github/workflows/release.yml run the tests, publish to npm and create the tag and GitHub Release.

Usage: /zcf-release [-p|-mi|-ma|<version>]: -p/--patch (default), -mi/--minor, -ma/--major, or an exact semver such as 3.8.0 or 4.0.0-beta.1. Arguments: $ARGUMENTS

Never create or push git tags yourself; the release workflow does it after merge.

Steps

Start clean. Fetch and work from an up-to-date main. If there are uncommitted changes, show them and ask whether they belong in this release. Commit them separately with a proper Conventional Commits message, staging files by name.
Collect changes. Last tag: git describe --tags --abbrev=0. Read git log <tag>..HEAD and the diff, and group user-visible changes into New Features / Optimization / Fixes / Documentation. Skip internal-only commits (CI, tests, chores) unless they matter to users.
Write the changeset. Create .changeset/release-<timestamp>.md:
```
---
"zcf": patch
---

## New Features

- English entry

## 新功能

- 中文条目
```
Each section is in English first, then the same section in Chinese; never mix languages on one line. Changesets only accept patch, minor or major here. For an exact version, pick the bump type that reaches it. If none does (for example a pre-release), run step 4 with patch, then set version in package.json and the new top heading in CHANGELOG.md to the exact version.
Apply. Run pnpm changeset version, which bumps package.json, updates CHANGELOG.md and deletes the changeset file. Read the new version from package.json and show the user the CHANGELOG diff.
Verify. Run pnpm typecheck, pnpm test:run and pnpm build. Stop and report if any of them fail.
Branch, commit, PR.
- git checkout -b release/v<version>
- git add package.json CHANGELOG.md, then git commit -m "chore: release v<version>"
- git push -u origin release/v<version>
- gh pr create --title "chore: release v<version>" with a body based on .github/PULL_REQUEST_TEMPLATE that contains the changelog section. Tick only the checks that you ran in step 5.
Report the PR URL and remind the user that merging it publishes to npm.

Read the full file on GitHub · 45 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago Changed · -418 lines · +11 tokens per session scan B → A 72c1e44055cb
1mo ago First seen · 463 lines · 14 tokens per session scan B 1e7031b9721f

Subscribe to this mod's changes

zcf-release is a skill published in the GitHub repository UfoMiao/zcf (6,079 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 707 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Git and workflow Releases ai ccr claude claude-ai cli

cli-forge-github

Audit and fix GitHub repository health: rulesets vs CI alignment, branch hygiene, PR lifecycle, release automation flow, permission issues, and transient CI failures. Detects misconfigurations that cause PRs to hang, CI to fail silently, branches to accumulate, and releases to stall. Use when the user says 'PR stuck'…

Destynova2/cli-code-skills · 165 tokens

cli-git-conventional

Enforce Conventional Commits v1.0.0, SemVer 2.0.0, branch naming, commit guard, full-directory AI marker audits, and human ghostwriter style on all git/jj operations. Zero AI markers. Use on 'commit', 'branch', 'tag', 'release', 'changelog', 'semver', 'bump version', 'next version', 'CHANGELOG.md', 'audit markers'…

Destynova2/cli-code-skills · 128 tokens

codew-release-qa-sweep

Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.

Hmbown/CodeWhale · 31 tokens

github

Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.

AtomicBot-ai/atomic-agent · 48 tokens

skillshare-changelog

Generate CHANGELOG.md entry from recent commits in conventional format. Also syncs the website changelog page. Use this skill whenever the user asks to: generate a changelog, document what changed between tags, or create a new CHANGELOG entry. If you see requests like "write the changelog for v0.17", "what changed…

runkids/skillshare · 134 tokens

commit-pr

Mandatory Codex/Copilot publication adapter for opencode-swarm. Use for every GitHub issue assignment that results in code changes, commits, pushes, draft PRs, PR body edits, PR readying, release notes, or CI closeout. Must be loaded before git push, gh pr create, gh pr edit, or gh pr ready. Routes to the single…

ZaxbyHub/opencode-swarm · 100 tokens

zcf: Skill for Claude Code