Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →code-yeongyu/pre-publish-review
Nuclear-grade 16-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 Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (5 agents) for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 r
Passed 16 of 18 test cases with the skill, and 6 of 18 without it.
and 9 more in the full report
12 fixed7 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Which model identifier is assigned to the ultrabrain per-change tasks during the pre-publish review procedure?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies gpt-5.6-sol as the model for ultrabrain review tasks | Missed | Passed |
The instructions your model reads when the skill loads.
Three-agent-layer review before publishing to npm. Every layer covers a different angle, and every result is mapped onto the release layers below.
| Layer | Agents | Type | What They Check |
|---|---|---|---|
| Per-Change Deep Dive | up to 10 | ultrabrain | Each logical change group individually — correctness, edge cases, pattern adherence |
| Holistic Review | 5 | review-work | Goal compliance, QA execution, code quality, security, context mining across full changeset |
| Release Synthesis | 1 | oracle | Overall release readiness, version bump, breaking changes, deployment risk |
Every phase classifies evidence and risk across:
| Release Layer | Scope | Required version decision |
|---|---|---|
omo pure components | Core packages, MCP packages, shared skills, reusable scripts, platform binary inputs | Patch/minor/major impact for shared logic consumed by adapters. |
omo opencode | Root oh-my-opencode / oh-my-openagent, src/, OpenCode plugin hooks/tools/CLI/config/docs, .opencode/, .agents/ | Semver bump for the OpenCode/OpenAgent npm release. |
omo codex | packages/omo-codex, lazycodex-ai, Codex plugin metadata/hooks, bundled MCP runtimes, code-yeongyu/lazycodex marketplace payload | Codex adapter bump, LazyCodex npm publish risk, and marketplace/GitHub release need. |
Run /get-unpublished-changes FIRST. This is the single source of truth for what changed and must include omo pure components, omo opencode, and omo codex layer-specific version recommendations.
skill(name="get-unpublished-changes")
This command automatically:
Save the full output — it feeds directly into Phase 1 grouping and all agent prompts.
test cases passed, vs 6 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.