Agent skill

Pre-Publish Release Review

by code-yeongyu in code-yeongyu/oh-my-openagent

Runs a multi-agent review before an npm release, with per-change analysis, a holistic review and a final readiness verdict, and only when you ask for it.

Custom licenceAuto-check passedDevOps & Cloud

Install Pre-Publish Release Review

skills CLI
$ npx skills add code-yeongyu/oh-my-openagent --skill pre-publish-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install code-yeongyu/oh-my-openagent pre-publish-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/pre-publish-review .claude/skills/pre-publish-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pre-publish-review
GitHub stars
70k
Token cost
~4.3k tokens
SKILL.md length
734 words
Files
1
Skills in repo
45
Repo updated
First seen
Licence
Custom licence

At a glance

Runs a multi-agent review before an npm release, with per-change analysis, a holistic review and a final readiness verdict, and only when you ask for it.

  • Works in 5 steps: Detect Unpublished Changes → Parse Changes into Groups → Spawn All Agents → …
  • Checking whether a package is safe to publish to npm
  • SKILL.md covers Release Layer Taxonomy, Phase 0: Detect Unpublished…, Phase 1: Parse Changes into… and Phase 2: Spawn All Agents, plus 3 more sections
  • Calls git, npm and node

What it does

The release gate has three layers. It begins by running the get-unpublished-changes skill, which compares the published npm version with the local one, lists commits since the last release, reads the real diffs, groups changes by type, flags breaking changes and recommends a version bump. Up to ten agents then each examine one logical group of changes for correctness, edge cases and adherence to existing patterns.

A second layer runs the review-work skill, in which an orchestrator does manual QA and one reviewer checks goal compliance, code quality, security and missed context across the whole change set. A single oracle agent then writes the release synthesis covering readiness, version bump, breaking changes and deployment risk, with findings mapped onto three release layers of the project.

It is written around one project's package layout and runs only when you explicitly ask for a pre-publish review. An ordinary publish or release request does not trigger it, because a separate command ships directly.

When your agent uses it

  • Checking whether a package is safe to publish to npm
  • Reviewing everything changed since the last npm release before shipping
  • Deciding the version bump and spotting breaking changes ahead of a release

Example prompts

  • “Do a pre-publish review of everything since the last npm release.”
  • “I want to know if this release is safe to publish, so check it before I ship.”
  • “Review the unpublished changes and tell me which version bump they need.”

Requirements

  • An npm package with a published version to compare against
  • The get-unpublished-changes and review-work skills
  • An agent setup that can spawn parallel review agents

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Detect Unpublished Changes
  2. Parse Changes into Groups
  3. Spawn All Agents
  4. Collect Results
  5. Final Verdict

What it can do on your machine

Read from SKILL.md and the folder at commit ae4ddd2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • npm
    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git and npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pre-Publish Release Review loads about 4.3k tokens when it runs. Until then it costs about 175 tokens; SKILL.md has 734 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~175
When it runs · the whole SKILL.md, loaded when a task matches
~4.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 734 words (~4,296 tokens).

“Three-agent-layer review before publishing to npm. Every layer covers a different angle, and every result is mapped onto the release layers below.”

— opening of SKILL.md by code-yeongyu, Custom licence
name
pre-publish-review

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/pre-publish-review of code-yeongyu/oh-my-openagent.

Open the folder on GitHubat commit ae4ddd2

Compare with similar skills

Pre-Publish Release Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Pre-Publish Release Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pre-Publish Release Review this skillcode-yeongyu/oh-my-openagent70k—~4.3kAutomated safety check: PassCustom licence
GitHub Swarm Code Reviewruvnet/agentic-flow8196 repos~6.5kAutomated safety check: PassNone
Solo ReviewLeoYeAI/openclaw-master-skills2.2k—~5.6kAutomated safety check: NotesMIT
Release-Green Validationdiegosouzapw/OmniRoute74k—~740Automated safety check: PassMIT
CI Triageandymai/brepjs115—~3.7kAutomated safety check: PassApache-2.0
Open Code Review CLIalibaba/open-code-review45k—~3.1kAutomated safety check: PassApache-2.0

Similar skills

  • GitHub Swarm Code Review

    ruvnet/agentic-flow

    Reviews GitHub pull requests with a swarm of specialized agents covering security, performance, architecture, style and accessibility, driven by the gh CLI and ruv-swarm.

    819 GitHub starsUsed in 6 repos~6.5k tokens
    DevelopmentAuto-check passed
  • Solo Review

    LeoYeAI/openclaw-master-skills

    Final code review and quality gate — run tests, check coverage, audit security, verify acceptance criteria from spec, and generate ship-ready report.

    2.2k GitHub stars~5.6k tokensUpdated 2 mo ago
    DevelopmentAuto-check: notes
  • Release-Green Validation

    diegosouzapw/OmniRoute

    Runs or reads a local Release-Green observer for an exact base or PR candidate and separates hard failures, advisory drift and incomplete evidence.

    74k GitHub stars~740 tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • CI Triage

    andymai/brepjs

    This skill should be used when a brepjs GitHub Actions job is red or behaving oddly on github.com (a remote CI run, not a local pre-commit/pre-push hook) — "CI failed", "ci-pass is failing", "npm ci…

    115 GitHub stars~3.7k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Open Code Review CLI

    alibaba/open-code-review

    Runs the ocr command-line tool to review Git changes, a commit or a branch comparison with an AI model, returning line-level comments and optionally applying fixes.

    45k GitHub stars~3.1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • O2 Review Loop

    openobserve/openobserve

    Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

    22k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from code-yeongyu/oh-my-openagent

All 45 skills in this repo
  • ast-grep Structural Search

    code-yeongyu/oh-my-openagent

    Searches and rewrites code by syntax-tree shape across 25 languages with ast-grep, for codemods, structural queries and YAML lint rules, using a Python wrapper script.

    70k GitHub stars~3.3k tokensUpdated today
    Auto-check passed
  • Browser Control with Omowright

    code-yeongyu/oh-my-openagent

    Drives a real browser through the omowright library, either the user's own signed-in browser or a separate browser the code launches, for forms, QA, screenshots and scraping.

    70k GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Codex Plugin QA

    code-yeongyu/oh-my-openagent

    Tests the omo Codex plugin in an isolated CODEX_HOME with a local mock model, proving hooks fired through app-server notifications without touching ~/.codex.

    70k GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Coding Agent Session Finder

    code-yeongyu/oh-my-openagent

    Finds, reads and reconstructs past coding-agent sessions across Codex, Claude, OpenCode, Senpi and many other local agent logs.

    70k GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • LSP Setup

    code-yeongyu/oh-my-openagent

    Detects which languages a project uses, installs the matching language server, writes its config and checks it with a real call so diagnostics and go-to-definition work.

    70k GitHub stars~1.4k tokensUpdated today
    Auto-check: notes
  • OpenCode QA Toolkit

    code-yeongyu/oh-my-openagent

    Tests the opencode coding agent itself: its CLI, server, plugin hooks and events, the terminal UI under tmux, and its SQLite session database, using tested helper scripts.

    70k GitHub stars~2.9k tokensUpdated today
    Auto-check passed

Works with

Questions about Pre-Publish Release Review

What does Pre-Publish Release Review do?

Runs a multi-agent review before an npm release, with per-change analysis, a holistic review and a final readiness verdict, and only when you ask for it. The release gate has three layers. It begins by running the get-unpublished-changes skill, which compares the published npm version with the local one, lists commits since the last release, reads the real diffs, groups changes by type, flags breaking changes and recommends a version bump.

When should I use Pre-Publish Release Review?

Pre-Publish Release Review fits situations like: checking whether a package is safe to publish to npm; reviewing everything changed since the last npm release before shipping; deciding the version bump and spotting breaking changes ahead of a release.

How do I install Pre-Publish Release Review in Claude Code?

Run `npx skills add code-yeongyu/oh-my-openagent --skill pre-publish-review -a claude-code`. Or copy the skill folder (.agents/skills/pre-publish-review in code-yeongyu/oh-my-openagent) into .claude/skills/pre-publish-review in your project. Claude Code loads it when a task matches its description.

How do I install Pre-Publish Release Review in Codex?

Run `npx skills add code-yeongyu/oh-my-openagent --skill pre-publish-review -a codex`. Or copy the skill folder (.agents/skills/pre-publish-review in code-yeongyu/oh-my-openagent) into .agents/skills/pre-publish-review in your project. Codex loads it when a task matches its description.

Can I use Pre-Publish Release Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add code-yeongyu/oh-my-openagent --skill pre-publish-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pre-publish-review, .gemini/skills/pre-publish-review, .github/skills/pre-publish-review and .opencode/skills/pre-publish-review in your project.

What does Pre-Publish Release Review need to run?

Going by SKILL.md and its folder, Pre-Publish Release Review needs the command-line tools its instructions call (git, npm and node). Our summary lists: An npm package with a published version to compare against; The get-unpublished-changes and review-work skills; An agent setup that can spawn parallel review agents.

Does Pre-Publish Release Review access the network?

SKILL.md contains no URLs. Its commands use git and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Pre-Publish Release Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Pre-Publish Release Review use?

Pre-Publish Release Review has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Pre-Publish Release Review use?

About 4.3k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Pre-Publish Release Review?

Skills that share tags, products or a category with Pre-Publish Release Review: GitHub Swarm Code Review (ruvnet/agentic-flow, 819 stars), Solo Review (LeoYeAI/openclaw-master-skills, 2.2k stars), Release-Green Validation (diegosouzapw/OmniRoute, 74k stars) and CI Triage (andymai/brepjs, 115 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pre-Publish Release Review?

code-yeongyu (a GitHub user) maintains it in code-yeongyu/oh-my-openagent, which has 69,917 GitHub stars. The repository holds 45 skills in this directory. The repository was last updated on October 9, 2026.

Source: code-yeongyu/oh-my-openagent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.