Interactive /gobby review launcher. Dispatches holistic-reviewer for an epic.
Scanned 5/28/2026
Install via CLI
openskills install GobbyAI/gobby---
name: review
description: "Interactive /gobby review launcher. Dispatches holistic-reviewer for an epic."
version: "1.0.0"
category: core
triggers: review, gobby review, holistic review, epic review
metadata:
gobby:
audience: interactive
depth: 0
---
# /gobby review
Use this skill when the user invokes `/gobby review` to run the same holistic
epic reviewer that lifecycle dispatch uses, independent of `gobby build`.
The workflow definition is `src/gobby/install/shared/workflows/review.yaml`.
## Inputs
Resolve an epic task ref before dispatch. Accept `#N`, a numeric ref, or a
dotted task path. If the user does not provide one, ask for the task ref.
## Mode Selection
Ask for the I/D mode unless it is already clear from the user's request:
```text
I) Interactive - dispatch holistic-reviewer and surface the run ids.
D) Delegated - dispatch holistic-reviewer and end the turn.
```
Persist the choice as `value="interactive" | "delegated"` for the handoff.
Both modes use the `holistic-reviewer` agent and the shared workflow YAML.
## Verdict Contract
The holistic review loop checks the approved plan, aggregate implementation
diff, validation evidence, and child task outcomes. The reviewer emits exactly
one verdict:
- approve with `approve_review(stage_name="holistic_qa")`
- reject with `reject_review(stage_name="holistic_qa")`
- escalate with `escalate_task`
Use the explicit user-facing summary `approve / reject / escalate` when
describing possible outcomes.
## Dispatch
Run the `review` workflow with the resolved epic task id:
```python
call_tool("gobby-workflows", "run_pipeline", {
"name": "review",
"inputs": {
"task_id": "<epic_task_ref>",
"mode": "<interactive|delegated>"
}
})
```
Surface the returned execution id. The spawned `holistic-reviewer` owns the
review verdict and terminates through its agent workflow.
## Boundaries
- Do not approve, reject, or escalate directly from this skill.
- Do not call `close_task`; lifecycle dispatch owns closure.
- Do not replace the `holistic-reviewer` or `holistic-review` methodology here.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.