Name: pre-publish-review
Rating: 68 (1 reviews)
Author: code-yeongyu

pre-publish-review

Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release synthesis. Runs ONLY when the user explicitly asks for a pre-publish review — a plain publish/release request MUST NOT trigger this; /publish ships directly. Triggers: 'pre-publish review', 'review before publish', 'release review', 'pre-release review', 'ready to publish?', 'can I publish?', 'pre-publish', 'safe to publish', 'publishing review', 'pre-publish check'.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

The canonical home for this skill is pre-publish-review in code-yeongyu/oh-my-openagent

Quality

Content

70%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable and clearly sequenced with strong validation, but penalized for verbosity (re-explained basics and redundant checklists) and a monolithic single-file structure with no progressive disclosure into bundle files.

Suggestions

Trim embedded explanations Claude already knows: drop the PATCH/MINOR/MAJOR semver definitions and the generic 'off-by-one errors, null handling, async edge cases' glosses from the agent-prompt checklists, keeping each checklist item as a terse prompt.

Extract the large ultrabrain and oracle prompt templates into scripts/ files (e.g. scripts/ultrabrain_prompt.txt, scripts/oracle_prompt.txt) referenced from SKILL.md to reduce inline bulk and improve progressive disclosure.

Deduplicate overlapping checklist items between the ultrabrain and oracle prompts (e.g. breaking-changes and edge-case checks appear in both) to cut token cost.

Dimension	Reasoning	Score
Conciseness	The ~428-line body re-explains concepts Claude already knows (semver 'PATCH: Bug fixes only…', 'Off-by-one errors, null handling, async edge cases') and carries overlapping 8–10-item checklists across the ultrabrain and oracle prompts; noticeably verbose with several padded sections.	2 / 5
Actionability	Fully executable guidance: concrete bash snippets (npm view, git diff) and complete task() call templates with clearly marked {PLACEHOLDERS} that are copy-paste ready and cover the common cases.	5 / 5
Workflow Clarity	Phases 0–4 are clearly sequenced with explicit validation checkpoints ('Do NOT deliver the final report until ALL agents have completed'), a verdict-logic block, blocking-issue aggregation, and an anti-patterns table — a batch operation that genuinely embeds validation.	5 / 5
Progressive Disclosure	Well-sectioned with clear headers and tables, but monolithic: no references/, scripts/, or assets/ bundle files exist and everything — including the large prompt templates — is inlined in one 428-line file, so content that could live separately is inline.	3 / 5
	Total	15 / 20 Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: concrete actions, explicit what/when, rich natural triggers, and explicit boundary against conflicting with a plain /publish request. The only weakness is the marketing-leaning 'Nuclear-grade 12-agent' framing, which is mild buzzword/over-claim.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('detect all changes since last npm release', 'spawns up to 10 ultrabrain agents for deep per-change analysis', 'invokes /review-work… for holistic review', '1 oracle for overall release synthesis'), giving comprehensive coverage; held at 4 rather than 5 because the opening 'Nuclear-grade 12-agent… gate' framing is a buzzword/over-claim the rubric says to penalize.	4 / 5
Completeness	Explicitly answers both 'what' (the four orchestrated actions) and 'when' ('Runs ONLY when the user explicitly asks for a pre-publish review — a plain publish/release request MUST NOT trigger this') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural user phrasings including synonyms and question forms — 'pre-publish review', 'ready to publish?', 'can I publish?', 'safe to publish', 'pre-publish check' — matching the 5 anchor's 'natural terms including synonyms'.	5 / 5
Distinctiveness Conflict Risk	Clear niche (pre-publish npm release gate) with explicit conflict avoidance ('a plain publish/release request MUST NOT trigger this; /publish ships directly') and distinct triggers, minimizing wrong-skill activation.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: code-yeongyu/oh-my-openagent
Path: .agents/skills/pre-publish-review/SKILL.md
Commit: 6108673

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.